Code Execution MCP servers

LLMs rely on outdated or generic information about the libraries you use. You get: - ❌ Code examples are outdated and based on year-old training data - ❌ Hallucinated APIs that don't even exist - ❌ Generic answers for old package versions Context7 pulls up-to-date, version-specific documentation and code examples straight from the source — and places them directly into your prompt. Context7 fetches up-to-date code examples and documentation right into your LLM's context. No tab-switching, no hallucinated APIs that don't exist, no outdated code generation.

5 tools · Fetch current docs, Get real code examples

Chrome DevTools for agents (chrome-devtools-mcp) lets your coding agent (such as Antigravity, Claude, Cursor or Copilot) control and inspect a live Chrome browser. It acts as a Model-Context-Protocol (MCP) server, giving your AI coding assistant access to the full power of Chrome DevTools for reliable automation, in-depth debugging, and performance analysis. A CLI is also provided for use without MCP. - Get performance insights: Uses [Chrome DevTools](https://github.com/ChromeDevTools/devtools-frontend) to record traces and extract actionable performance insights. - Advanced browser debugging: Analyze network requests, take screenshots and check browser console messages (with source-mapped stack traces). - Reliable automation. Uses puppeteer to automate actions in Chrome and automatically wait for action results.

6 tools · click, lighthouse_audit

Mastra supports the Model Context Protocol (MCP), an open standard for connecting AI agents to external tools and resources. It serves as a universal plugin system, enabling agents to call tools regardless of language or hosting environment. Mastra can also be used to author MCP servers, exposing agents, tools, and other structured resources via the MCP interface. These can then be accessed by any system or agent that supports the protocol. To use MCP, install the required dependency: Mastra currently supports two MCP classes:

4 tools · Connect agents to external MCP servers, Expose Mastra agents via MCP

Connect your AI assistant to GitHub repositories, issues, pull requests, and search.

4 tools · create_issue, get_pull_request

Kubeshark MCP (Model Context Protocol) server enables AI assistants like Claude Desktop, Cursor, and other MCP-compatible clients to query real-time Kubernetes network traffic. The MCP provides the tools — AI skills teach agents how to use them. Skills turn raw MCP capabilities into domain-specific workflows like root cause analysis, traffic filtering, and forensic investigation. See the skills README for installation and usage. - L7 API Traffic Analysis: Query HTTP, gRPC, Redis, Kafka, DNS transactions - L4 Network Flows: View TCP/UDP flows with traffic statistics - Cluster Management: Start/stop Kubeshark deployments (with safety controls) - PCAP Snapshots: Create and export network captures - Built-in Prompts: Pre-configured prompts for common analysis tasks

6 tools · create_snapshot, enable_dissection

Generate images using Amazon Nova Canvas with text prompts and color guidance.

Open-source localization engineering tools. Connect to Lingo.dev localization engineering platform for consistent, quality translations. Lingo API • Lingo React MCP • Lingo CLI • Lingo GitHub Action • Lingo Compiler for React (Early alpha) These tools connect to localization engines – stateful translation APIs you create on the Lingo.dev localization engineering platform. Each engine persists glossaries, brand voice, and per-locale instructions across every request, reducing terminology errors 16.6–44.6%. Or bring your own LLM.

3 tools · Prevent hallucinated APIs, Set up i18n in React apps

This repository contains a list of Google's official Model Context Protocol (MCP) servers, guidance on how to deploy MCP servers to Google Cloud, and examples to get started. These remote MCP servers are managed by Google, and are available via endpoint. Below are a few key remote servrs. For a comprehensive list of all remote MCP servers managed by Google in General Availability (GA) and public preview vist the supported products pager AlloyDB for PostgreSQL BigQuery Bigtable Cloud Resource Manager Cloud SQL for MySQL Cloud SQL for PostgreSQL Cloud SQL for SQL Server Compute Engine (GCE) Developer Knowledge API (Google Developer Documentation) Firestore Google Maps (Grounding Lite) Google Security Operations (Chronicle) Kubernetes Engine (GKE) Spanner Cloud Run (GA) Cloud Storage

6 tools · Access Google developer documentation, Generate images and video

The Firebase Model Context Protocol (MCP) Server gives AI-powered development tools the ability to work with your Firebase projects and your app's codebase. The Firebase MCP server works with any tool that can act as an MCP client, including: Firebase Studio, Gemini CLI, Claude Code, Cline, Cursor, VS Code Copilot, Windsurf, and more! An editor configured to use the Firebase MCP server can use its AI capabilities to help you: - Create and manage Firebase projects - Initialize new projects, list existing ones, and manage Firebase apps - Manage Firebase Authentication users - Retrieve, update, and manage user accounts - Work with Cloud Firestore and Firebase SQL Connect - Query, read, write, and manage database documents - Retrieve Firebase SQL Connect schemas - Generate schemas and operations with AI assistance - Understand security rules - Validate and retrieve security rules for Firestore, Cloud Storage, and Realtime Database - Send messages with Firebase Cloud Messaging - Send push n

6 tools · apphosting_list_backends, auth_get_users

Model Context Protocol (MCP) is an open protocol that standardizes how applications provide context to large language models (LLMs). It allows AI applications to connect with various data sources and tools in a consistent manner, enhancing their capabilities and flexibility. MCP follows a client-server architecture: - MCP Hosts: Applications like AI assistants or IDEs that initiate connections. - MCP Clients: Connectors within the host application that maintain 1:1 connections with servers. - MCP Servers: Services that provide context and capabilities through the standardized MCP.

The Figma MCP server brings Figma directly into your workflow by providing important design information and context to AI agents generating code from Figma design files. > [!NOTE] > Rate limits apply to Figma MCP server tools that read data from Figma. Some tools, such as those that write to Figma files, are exempt from the rate limits. > <br><br> > Users on the Starter plan or with View or Collab seats on paid plans will be limited to up to 6 tool calls per month. > <br><br> > Users with a Dev or Full seat on the Professional, Organization, or Enterprise plans have per minute rate limits, which follow the same limits as the Tier 1 Figma REST API. As with Figma’s REST API, Figma reserves the right to change rate limits.

6 tools · Generate code from selected frames, Generate designs from web pages

Read, search, and inspect local Git repositories without leaving your assistant.

3 tools · git_diff, git_log

A ModelContextProtocol server that gives your AI coding tool or agent access to documentation for APIs, services, libraries etc. It's your one-stop-shop to keep your agent up-to-date on documentation in a fast and token-efficient way. Ref's tools are designed to match how models search while using as little context as possible to reduce context rot. The goal is to find exactly the context your coding agent needs to be successful while using minimum tokens. Depending on the complexity of the prompt, LLM coding agents like Claude Code will typically do one or more searches and then choose a few resources to read in more depth.

4 tools · Get token-efficient context, ref_read_url

This repository is no longer maintained. The core functionality has been integrated into all IntelliJ-based IDEs since version 2025.2. The built-in functionality works with SSE and JVM-based proxy (for STDIO) so this NPM package is no longer required. Migration: Please refer to the official documentation for details on using the built-in functionality. Issues & Support: For bugs or feature requests related to the built-in MCP functionality, please use the JetBrains YouTrack%7D%20). The server proxies requests from client to JetBrains IDE.

3 tools · Configure which IDE instance to target, Connect your AI assistant to a running JetBrains IDE

https://github.com/user-attachments/assets/eeb9c4cb-c80d-42da-bf63-c0c4ecb1e5d6 Every AI coding agent today — Cursor, Claude Code, Cline, Copilot — works the same way: 1. You type a prompt 2. Agent immediately starts writing code 3. You have zero visibility into what it's doing 4. You realize it misunderstood your request 5. Hundreds of lines of code need to be discarded 6. You've wasted tokens, time, and patience Some agents show plans as text in chat. But text fails to show: - Dependencies — which tasks depend on what? - Branch points — what alternative approaches exist? - Context requirements — which files, APIs, or secrets are needed? - Complexity — which steps are risky? - Progress — what's done, what's next?

5 tools · check_pause, get_resume_info

The SonarQube MCP Server is a Model Context Protocol (MCP) server that enables seamless integration with SonarQube Server or Cloud for code quality and security. It also supports the analysis of code snippet directly within the agent context. > 🔒 Important: Your SonarQube token is a sensitive credential. Follow these security practices: When using CLI commands: - Avoid hardcoding tokens in command-line arguments – they get saved in shell history - Use environment variables – set tokens in environment variables before running commands

5 tools · analyze_code_snippet, Check quality gates

AI coding agents waste tokens exploring codebases. Every grep, glob, and file read costs money. On complex tasks, agents spawn multiple Explore sub-agents that scan hundreds of files just to build context. tokensave gives agents a pre-indexed semantic knowledge graph. Instead of scanning files, the agent queries the graph and gets instant, structured answers -- the right symbols, their relationships, and source code, in one call. Without tokensave: Agents use grep, glob, and Read to scan files -- many API calls, high token usage.

6 tools · login, tokensave_branch_search

Deploy apps and provision cloud infrastructure from scratch on AWS, Azure, GCP, DigitalOcean, and Hetzner: in accounts you control. One platform to replace many tools: Terraform + Ansible + Jenkins + PaaS (Vercel, Heroku, etc), and stack-specific server panels. Manage apps, Linux servers, and cloud infrastructure from anywhere: web, mobile, API, or natural language in your AI agent through MCP. No SSH or cloud console for routine work. Ask your AI agent to provision servers, deploy apps, migrate between clouds, and manage infrastructure through one MCP server: not a separate integration per cloud or stack.

4 tools · Deploy applications, Manage role-based permissions

> Deprecated: This project is no longer actively maintained. It may not receive further updates or bug fixes. This repository contains the source code for the E2B MCP server. The E2B MCP server allows you to add code interpreting capabilities to your Claude Desktop app via the E2B Sandbox. See demo here. You can also install E2B for Claude Desktop automatically via Smithery:

3 tools · Analyze data with code interpreter, Execute code in a secure sandbox

Repo for the official Svelte MCP server. 1. Set the VOYAGE_API_KEY for embeddings support > [!NOTE] > Currently to prevent having a bunch of Timeout logs on vercel we shut down the SSE channel immediately. This means that we can't use server.log and we are not sending list-changed notifications. We can use elicitation and sampling since those are sent on the same stream of the POST request - Transport type: Streamable HTTP - http://localhost:5173/mcp

3 tools · ask_svelte, get_examples

The Postman MCP Server implements the Model Context Protocol (MCP) to connect AI agents and coding assistants — including Claude Code, Cursor, VS Code Copilot, GitHub Copilot CLI, and Gemini CLI — directly to your Postman workspaces, collections, specifications, and environments. Postman also offers the server as an npm package. For the full installation guide with agent-specific setup, see Postman's MCP Server product page. The Postman MCP Server collection is the quickest way to explore, test, and connect to the Postman MCP Server. Use it to:

5 tools · Create specs from code, Generate client code

MCP Server for ForeverVM, enabling Claude to execute code in a Python REPL. - Create a Python REPL. - Returns: ID of the new REPL. 2. run-python-in-repl - Execute code in a Python REPL. - Required Inputs: - code (string): code that the Python REPL will run. - replId (string): ID of the REPL to run the code on. - Returns: Result of the code executed. In the MCP client, set the command to npm and the arguments to:

3 tools · Chain multiple code executions in one session, Run Python code in an existing REPL

MCP (Model Context Protocol) is an open standard that lets AI assistants (ChatGPT, Claude, VS Code Copilot, JetBrains AI, Codex, and others) use external tools. This server exposes the entire Zabbix API as MCP tools — allowing any compatible AI assistant to query hosts, check problems, manage templates, acknowledge events, and perform any other Zabbix operation. The server runs as a standalone HTTP service. AI clients connect to it over the network. - Complete API coverage - All 58 Zabbix API groups (223 tools): hosts, problems, triggers, templates, users, dashboards, and more - Extension tools (14) - Pre-correlated views: host_status_get, hostgroup_overview_get, infrastructure_summary_get, item_history_summary_get, problem_active_get (fold 3-5 raw API calls into one round-trip). Plus graph_render (PNG export), anomaly_detect (z-score analysis), capacity_forecast (linear regression), item_threshold_search (filter items by lastvalue thresholds), report_generate (PDF reports), action_pre

6 tools · action_prepare, anomaly_detect

> The blazing-fast, privacy-first MCP server for deep code intelligence A Rust-powered MCP (Model Context Protocol) server providing AI assistants with deep code understanding through 90 specialized tools. - Code Intelligence - Symbol extraction, semantic search, call graph analysis - Neural Semantic Search - Find similar code using embeddings (Voyage AI, OpenAI) - Security Analysis - Taint analysis, vulnerability scanning, OWASP/CWE coverage - Supply Chain Security - SBOM generation, dependency auditing, license compliance - Advanced Analysis - Control flow graphs, data flow analysis, dead code detection

6 tools · find_symbols, generate_sbom

Manage test cases, execute manual or automated tests, debug issues, and even fix code—directly within tools like Cursor, Claude, or any MCP-enabled client, using plain English. Easily connect the BrowserStack Test Platform to your favourite AI tools, such as IDEs, LLMs, or agentic workflows. Manage, execute, debug tests, and even fix code using plain English prompts. Stay in flow—keep all project context in one place and trigger actions directly from your IDE or LLM. Click on the buttons below to install MCP in your respective IDE:

6 tools · Execute and debug automated tests, Generate and heal tests with AI

Model Context Protocol (MCP) server for Hostinger API. If you don't want to install or run anything locally, connect directly to Hostinger's hosted MCP server: This opens a browser window to authorize via OAuth. Once approved, all tools below are available in your session. Add https://mcp.hostinger.com as a remote Streamable HTTP MCP server in your client's configuration and complete the OAuth prompt when it appears. Refer to your client's docs for how it exposes "add remote MCP server" / "custom connector" settings.

5 tools · Configure PHP and WordPress, Deploy websites from archives

Skene reads your codebase and produces a user journey for your product: the lifecycle stages a user moves through, the milestones inside each stage, and the code or database evidence that proves each milestone is real. Install and launch the interactive terminal UI: The wizard walks you through provider selection, authentication, and analysis — no configuration needed upfront. Skene turns a repository into a single journey.yaml describing your product's user lifecycle, and renders it as an interactive diagram.

4 tools · Analyze a codebase into a user journey, Combine code and SQL schema analysis

Here's a step-by-step tutorial for setting up and deploying a project with wxflows, including installing necessary tools, deploying the app, and running it locally. This example consists of the following pieces: - MCP TypeScript SDK (mcp server) - wxflows SDK (tools) > You can use any of the supported MCP clients. This guide will walk you through installing the wxflows CLI, initializing and deploying a project, and running the application locally. We’ll use google_books and wikipedia tools as examples for tool calling with wxflows.

4 tools · Connect the server to an MCP client, Deploy custom tool configurations

DINO-X Official MCP Server — powered by the DINO-X and Grounding DINO models — brings fine-grained object detection and image understanding to your multimodal applications. - Fine-Grained Understanding: Full image detection, object detection, and region-level descriptions. - Structured Outputs: Get object categories, counts, locations, and attributes for VQA and multi-step reasoning tasks. - Composable: Works seamlessly with other MCP servers to build end-to-end visual agents or automation pipelines.

4 tools · Detect all objects in a scene, Estimate human pose keypoints

A Model Context Protocol (MCP) server that provides browser automation capabilities using kogiQA. This server enables LLMs to interact with web pages through natural language, bypassing the need for screenshots or visually-tuned models. - Debug style issues on your page - Automatically fix console errors. - Map and document the functionality of your web app - Automatically write end-to-end tests - Automate exploratory testing of your application The kogiQA MCP Server provides a browser which incorporates the capabilities of the kogiQA browser control algorithm. This enables agents to interact with pages without a selector, saving time and tokens.

5 tools · Debug style issues, Fix console errors

This project follows the Model Context Protocol standard, allowing AI assistants to interact with Square's connect API. Get up and running with the Square MCP server using npx: ACCESS_TOKEN=YOUR_SQUARE_ACCESS_TOKEN SANDBOX=true npx square-mcp-server start Replace YOUR_SQUARE_ACCESS_TOKEN with your actual Square access token. You can obtain your access token by following the guide at Square Access Tokens. You can also set environment variables before running the command. Square now offers a hosted remote MCP server at:

4 tools · get_service_info, get_type_info

Octopus makes it easy to deliver software to Kubernetes, multi-cloud, on-prem infrastructure, and anywhere else. Automate the release, deployment, and operations of your software and AI workloads with a tool that can handle CD at scale in ways no other tool can. Model Context Protocol (MCP) allows the AI assistants you use in your day to day work, like Claude Code, or ChatGPT, to connect to the systems and services you own in a standardized fashion, allowing them to pull information from those systems and services to answer questions and perform tasks.

6 tools · find_feature_toggles, find_releases

The Cycode Command Line Interface (CLI) is an application you can install locally to scan your repositories for secrets, infrastructure as code misconfigurations, software composition analysis vulnerabilities, and static application security testing issues. This guide walks you through both installation and usage. 1. Prerequisites 2. Installation 1. Install Cycode CLI 1. Using the Auth Command 2. Using the Configure Command 3. Add to Environment Variables 1. On Unix/Linux 2. On Windows 2. Install Pre-Commit Hook 3. Cycode CLI Commands 4. Certificates and Proxies 5. MCP Command 1. Starting the MCP Server 2. Available Options 3. MCP Tools 4. Usage Examples 5. Advanced Configuration 6. Platform Command 1. Discovering Commands 2. Examples 3. Notes & Limitations 7. AI Guardrails 1. Data Collected by AI Guardrails 8. Scan Command 1. Running a Scan 1. Options 1. Severity Threshold 2. Monitor 3. Cycode Report 4. Package Vulnerabilities 5. License Compliance 6. Lock Restore 7. Stop on Error 2.

5 tools · cycode_iac_scan, cycode_sast_scan

> Control your real browser with AI through the Model Context Protocol An MCP (Model Context Protocol) server that lets AI assistants control your actual browser (Chrome, Firefox, or Opera) through a browser extension. Unlike headless automation tools, this uses your real browser profile with all your logged-in sessions, cookies, and extensions intact. Perfect for: AI agents that need to interact with sites where you're already logged in, or that need to avoid bot detection. Chrome / Edge / Opera - Chrome Web Store (works for all Chromium browsers) - Manual: Download from Releases, then load unpacked at chrome://extensions/ (Chrome), edge://extensions/ (Edge), or opera://extensions/ (Opera)

6 tools · browser_evaluate, browser_interact

An MCP (Model Context Protocol) server that gives AI agents full access to the Harness.io platform through 11 consolidated tools and 240 resource types. Most MCP servers map one tool per API endpoint. For a platform as broad as Harness, that means 240+ tools — and LLMs get worse at tool selection as the count grows. Context windows fill up with schemas, and every new endpoint means new code. - 11 tools, 240 resource types. A registry-based dispatch system routes harness_list, harness_get, harness_create, etc. to any Harness resource — pipelines, services, environments, orgs, projects, feature flags, cost data, and more. The LLM picks from 11 tools instead of hundreds. - Full platform coverage. 39 default toolsets spanning CI/CD, GitOps, Feature Flags, Cloud Cost Management, Security Testing, Chaos Engineering, Database DevOps, Internal Developer Portal, Software Supply Chain, Infrastructure as Code Management, Release Management, Governance, Service Overrides, Knowledge Graph, and more

6 tools · Build and deploy end-to-end, Cross-project execution monitoring

AI-powered browser testing via the Model Context Protocol. Point it at any URL (or localhost) and describe what to test — an AI agent browses your app and returns pass/fail with screenshots. Requires Node.js 20.20.0 or later (transitive requirement from posthog-node@^5.26.0). Testing http://localhost:... URLs requires the caddy binary — check_app_in_browser, probe_page, and trigger_crawl tunnel localhost targets through a local Caddy reverse proxy. This installs automatically: the @radically-straightforward/caddy npm dependency downloads a pinned Caddy release for your platform during npm install/npx, same as this project already does for the ngrok binary — nothing to install yourself in the normal case. If that download never ran (npm install --ignore-scripts, an offline/air-gapped install), point CADDY_BIN at your own install (brew install caddy / apt install caddy / see caddyserver.com/docs/install) — missing it surfaces as a clear error on the first localhost-URL call, not a silent

6 tools · check_app_in_browser, environment

ZooData is the data infrastructure built for agents. Not a scraping API. Not a human dashboard. A purpose-built data layer that gives your AI agents direct access to Amazon commerce signals — 200M+ indexed products, 2+ years of history, and 1B+ reviews pre-processed into structured insights. Clean JSON, real-time, agent-ready. https://github.com/user-attachments/assets/305a161b-7a53-49b8-afdc-4469a4fbf361 This repo contains 11 agent skills organized in two tiers: 🏗️ Foundation — data access and full-spectrum analysis:

6 tools · Competitor discovery, Historical trends

Archcore is a git-native context layer for AI coding agents. The CLI keeps specs, architecture decisions, rules, plans, and project knowledge in .archcore/, versioned with your code, and serves the relevant context to coding agents through MCP and session hooks. It ships as a CLI and a local stdio MCP server, so any MCP-compatible coding agent can read and write your project context through standard tools. Use it for persistent project context across Claude Code, Cursor, Codex CLI, GitHub Copilot, Gemini CLI, OpenCode, Roo Code, and Cline.

6 tools · add_relation, create_document

Single tool to control them all — VeyraX MCP is the only connection you need to access all your tools in any MCP-compatible environment. VeyraX MCP (Model Context Protocol) is an open protocol that allows you to provide custom tools to agentic LLMs. By connecting once to the VeyraX platform, you can use all tools you’ve already integrated with VeyraX in any MCP-compatible environment—such as Claude, Cursor, VS Code, or Windserf—without juggling multiple authentications. - Single Authentication: Connect once in VeyraX, then use your tools across all MCP clients without separate logins or credentials. - Instant Access to All Tools: Any tool you connect to VeyraX is immediately available in your favorite editor or AI assistant. - 5-Minute Setup: Connect VeyraX to any MCP client in under five minutes.

3 tools · Add new tools once and use them everywhere, Connect all your VeyraX tools to any MCP client

To add the MCP server in any config driven MCP Client, following is how the commands and arguments will look like For macOS/Linux: curl -LsSf https://astral.sh/uv/install.sh | sh For Windows: You can also visit the installation steps of uv for more details here You can run the MCP server using uvx using the following command To configure VideoDB Director MCP server in Claude, you can run the following command You can manually configure the MCP Server by following these steps: 1. Open the claude_desktop_config.json file

3 tools · get_video, search_video

> [!NOTE] > This server interacts with the Unstructured API to manage sources, destinations, and workflows. It is not actively maintained and is kept here for reference. > > If you want to parse and transform files into structured output (markdown, JSON, HTML, or plain text), use the Unstructured Transform MCP server instead. > > Unstructured Transform brings production-grade document processing to your agents as a hosted MCP server. It gives them the ability to turn 60+ file types into structured data that's ready for your applications, vector databases, and any downstream processes by parsing, enriching, chunking, and embedding files directly inside their current session. > > You can start using it by signing up here.

5 tools · create_source_connector, invoke_firecrawl_crawlhtml

- AppControl running with MCP API enabled - Windows only There are two ways to install the server: as an MCPB package (recommended for Claude Desktop) or as a standalone executable. 1. Download appcontrol.mcpb from the latest release. 2. Open Claude Desktop app, go to Settings -> Extensions -> Advanced Settings and click "Install Extension". Choose your newly downloaded .mcpb file — Claude Desktop will install it automatically. 3. Restart Claude Desktop app by right-clicking the Claude tray icon and selecting "Quit" then start it again.

6 tools · get_binary, get_monitoring

The MCP server for Bitrix24 provides AI assistants with structured access to the Bitrix24 API. It delivers up-to-date method descriptions, parameters, and valid values, allowing assistants to work with precise data instead of guesswork. This reduces code errors and accelerates Bitrix24 integration development.

This repository contains code to locally run an MCP server that can access [Scout Monitoring](https://www.scoutapm.com) data via Scout's API. We provide a Docker image that can be pulled and run by your AI Assistant to access Scout Monitoring data. This puts Scout Monitoring's performance and error data directly in the hands of your AI Assistant. For Rails, Django, FastAPI, Laravel and more. Use it to get traces and errors with line-of-code information that the AI can use to target fixes right in your editor and codebase. N+1 queries, slow endpoints, slow queries, memory bloat, throughput issues - all your favorite performance problems surfaced and explained right where you are working.

5 tools · get_app_endpoints, get_app_error_groups

Command-line interface for interacting with Reflag services. The CLI allows you to manage apps, flags, authentication, and generate TypeScript types for your Reflag flags. With this tool, you can streamline your flagging workflow directly from your terminal. Install the CLI as a development dependency in your project: Run the new command from your project's root directory to initialize the CLI, create a flag, and generate TypeScript types in one step: If you're migrating from the Bucket CLI, here are the key changes to be aware of:

6 tools · Configure MCP connection, Create a new flag

A purpose-driven Model Context Protocol (MCP) server for managing Unleash feature flags. This server enables LLM-powered coding assistants to create and manage feature flags following Unleash best practices. To share feedback, join our community Slack or open an issue on GitHub. This MCP server provides tools that integrate with the Unleash Admin API, allowing AI coding assistants to: - Create feature flags with proper validation and typing. - Detect existing flags to prevent duplicates or encourage reuse. - Evaluate changes to decide when a feature flag is needed. - Stream progress for visibility during operations. - Handle errors gracefully with helpful hints. - Follow best practices from the Unleash documentation.

6 tools · create_flag, detect_flag

> [!CAUTION] > This repository was archived on July 21, 2025. The Atla API is no longer active. An MCP server implementation providing a standardized interface for LLMs to interact with the Atla API for state-of-the-art LLMJ evaluation. > Learn more about Atla here. Learn more about the Model Context Protocol here. - evaluate_llm_response: Evaluate an LLM's response to a prompt using a given evaluation criteria. This function uses an Atla evaluation model under the hood to return a dictionary containing a score for the model's response and a textual critique containing feedback on the model's response. - evaluate_llm_response_on_multiple_criteria: Evaluate an LLM's response to a prompt across _multiple_ evaluation criteria. This function uses an Atla evaluation model under the hood to return a list of dictionaries, each containing an evaluation score and critique for a given criteria.

2 tools · evaluate_llm_response, evaluate_llm_response_on_multiple_criteria

Claude KVM is an MCP tool that controls remote desktop environments over VNC. It consists of a thin JS proxy layer (MCP server) and a platform-native Swift VNC daemon running on your macOS system. > [!TIP] > Phantom-WG could be a great alternative for you. Isolate your VNC server within your own network while enjoying self-hosted VPN performance with the extra privacy features you gain along the way. - Integration Test - Mac Integration Test - Mac Calculator Test - Mac Scientific Calculator Test - Mac Safari Browsing Test - Mac Drag & Drop Test - Mac Chess Test - Mac Chess Direct Test - Mac Phantom-WG Install Test

5 tools · configure, detect_elements

A Model Context Protocol (MCP) proxy server that translates tool calls into TypeScript code generation. Instead of making multiple tool calls back and forth, LLMs can write TypeScript code that calls multiple tools naturally, reducing token overhead and leveraging the LLM's superior code generation capabilities. LLMs make multiple sequential tool calls, burning tokens and struggling with complex workflows: - ❌ Multiple round-trips between LLM and tools - ❌ Complex tool calling sequences are error-prone - ❌ Data cannot easily be passed between tools - ❌ Limited error handling and control flow

5 tools · generate_and_execute_code, get_tool_definitions

Riza offers an isolated code interpreter for your LLM-generated code. Our MCP server implementation wraps the Riza API and presents endpoints as individual tools. Configure with Claude Desktop as below, or adapt as necessary for your MCP client. Get a free Riza API key in your Riza Dashboard. The Riza MCP server provides several tools to your LLM: - create_tool: Your LLM can write code and save it as a tool using the Riza Tools API. It can then execute these tools securely on Riza using execute_tool. - fetch_tool: Your LLM can fetch saved Riza tools, including source code, which can be useful for editing tools. - execute_tool: Executes a saved tool securely on Riza's code interpreter API. - edit_tool: Edits an existing saved tool. - list_tools: Lists available saved tools. - execute_code: Executes arbitrary code safely on Riza's code interpreter API, without saving it as a tool.

5 tools · create_tool, edit_tool

这是一个基于 ALAPI 的 MCP (Model Context Protocol) 服务器实现，可以通过MCP协议直接调用ALAPI的接口，轻松将ALAPI丰富的API资源集成到各类支持MCP的AI应用中。 - 🔍 丰富API资源 - 提供IP查询、天气查询、热搜榜单、企业信息等100+种常用API服务 - 🧩 MCP 协议支持 - 完全兼容 Model Context Protocol，轻松集成到各类AI应用 - 🔄 自动加载 - 自动加载 ALAPI OpenAPI 规范，无需手动配置 - 🎯 灵活调用 - 支持加载全部或指定API，按需使用（短视频解析、天气查询、每天60秒读懂世界、企业查询等） - 🛡️ 统一响应 - 提供统一的错误处理和响应格式，简化开发流程 - ⚙️ 可配置性 - 支持环境变量配置，轻松适应不同使用场景 ALAPI MCP Server 设计为与支持 MCP 协议的客户端配合使用，不支持独立的命令行配置。请按照以下步骤在您的 MCP 客户端中配置使用： 通过 Smithery 安装 ALAPI MCP Server，适用于 Claude Desktop 客户端：

6 tools · Company verification, Content moderation

> [!WARNING] > This repository is deprecated and no longer maintained. > > Scorable now runs a hosted remote MCP server at https://api.scorable.ai/mcp. It needs no > installation, no local process, and no container, and it tracks the platform automatically. > > bash > claude mcp add --transport http scorable https://api.scorable.ai/mcp \ > --header "Authorization: Bearer $SCORABLE_API_KEY" > > > The hosted server covers everything this one did and more: alongside running evaluators and > judges it can list, create, and update them, generate a judge from a plain-language > description, and query past execution logs — 14 tools in total. It also scores whole > conversations, not just single request/response pairs. > > See the MCP Server documentation for > install instructions for Claude Code, Codex, Cursor, and other clients. > > This repository stays available for anyone who specifically needs a stdio transport or wants > to run the MCP layer inside their own network, but it will not re

6 tools · list_evaluators, list_judges

A tool to manage Ephemeral Environments on the Shipyard platform. - Linux and macOS curl https://www.shipyard.sh/install.sh | bash - Windows Navigate to the releases page and download the executable for Windows. - Homebrew brew tap shipyard/tap brew install shipyard Run shipyard login to initialize the CLI. This will prompt you to log in to Shipyard in the browser. The CLI will then save your API token in a local config. You're ready to start running commands. Set your Shipyard API token as the value of the SHIPYARD_API_TOKEN environment variable.

6 tools · get_environment, get_environments

> [!IMPORTANT] > This project has been archived. It was built to address the lack of browser control in AI agents such as Claude and Codex, but the agents now have these functions built in without the need for a dedicated MCP based solution. YetiBrowser MCP is a fully open-source implementation of the Browser MCP workflow. It links a Node-based MCP server with Chrome/Firefox extensions so Model Context Protocol clients—Codex/Claude Code, Cursor, Windsurf, MCP Inspector, or your own tools—can automate a real browser tab while keeping every byte on your machine and auditable.

5 tools · browser_evaluate, browser_fill_form

A Model Context Protocol (MCP) server implementation for enabling agents to access observability insights using Digma for code observability and dynamic code analysis 🗣️ Observability-assisted code reviews: Check the PR branch for any issues discovered by pre-prod observability. 🔎 Find code inefficiencies with dynamic code analysis: Identify issues in the code/queries that are slowing the app down 🔭 Utilize code runtime usage data from distributed tracing: Check for breaking changes or generated relevant tests

5 tools · Assess impact of changing a function, Check for new issues in a specific environment

A Model Context Protocol (MCP) integration for managing content in the DevHub CMS system. You will need the uv package manager installed on your local system. To use this server with the Claude Desktop app, add the following configuration to the "mcpServers" section of your claude_desktop_config.json: After updating the config, restart Claude Desktop. This MCP can also be used in cursor with a similar configuration from above added to your Cursor global environment or to individual projects. Claude Code's command line supports MCP installs.

5 tools · create_blog_post, get_businesses

An MCP (Model Context Protocol) server that gives AI assistants on-demand access to the complete amCharts 5 knowledge base: 140+ documentation pages, 280+ code examples, and 1,000+ class API references. Works with Claude Code, Claude Desktop, Cursor, Windsurf, VS Code + GitHub Copilot, and any other MCP-compatible AI tool. Instead of loading the entire amCharts reference into the AI's context window, the MCP server lets the AI query exactly what it needs — a specific chart type reference, a code example, or an API lookup. This means better answers with less context waste.

5 tools · get_chart_reference, get_example

Allyson MCP Server - AI-powered animation generator that transforms static files into animated SVG components using the Model Context Protocol (MCP). Options: --api-key <key> Your Allyson API key (required) --help Show help message Examples: allyson-mcp --api-key your-api-key-here API_KEY=your-key allyson-mcp You can also set your API key as an environment variable: - AI-Powered Animation Generation: Transform static images into animated SVG components - MCP Protocol Compatible: Works with any MCP-compatible AI assistant or tool - File Upload Support: Supports various image formats (PNG, JPG, SVG, etc.) - Custom Animation Prompts: Describe exactly what animation you want - Local File Processing: Reads files from your local filesystem - Automatic Output Generation: Saves animated components to specified paths

3 tools · Create custom motion effects from images, generate_svg_animation

Control plane for autonomous software labor. Planwright is the objective-native planning board for agent-led software development. Humans define outcomes at the Objective layer; coding agents (Claude Code, Cursor, Codex, and others) claim work, decompose tasks, execute, and report back via native MCP—with every state change captured in a hash-chained, Ed25519-signed audit trail. Your browser opens for GitHub login. That's it. See the full agent setup guides for Cursor, Codex, Claude Desktop, and generic MCP clients.

6 tools · planwright_check_alignment, planwright_claim_objective

This repository provides a Model Context Protocol (MCP) Server for validating OpenAPI specifications using APIMatic. The server processes OpenAPI files and returns validation summaries by leveraging APIMatic’s API. - Validates OpenAPI 2.0 and 3.0 files - Uses APIMatic’s API for comprehensive validation - Supports both JSON and YAML formats - Implements Model Context Protocol (MCP) for seamless integration To use the server, an APIMatic API key is required. Sign up at APIMatic and obtain the API key.

3 tools · Check an API definition before implementation, Get a structured validation report

Work on dataset metadata with MLCommons Croissant validation and creation.

Scan your website, apps &amp; GitHub for vulnerabilities. Block attacks &amp; bad bots, rate-limit your APIs, monitor uptime, domain &amp; SSL expiry — all in one security platform. Scan &amp; pentest · Monitoring &amp; uptime · Instant alerts · API rate limits · 360° protection · MCP &amp; SDKs Defen.so is a developer-first web security SaaS. Managed WAF, uptime monitoring, quick pentest (headers, TLS, email security — SPF/DKIM/DMARC — and compliance-style findings), vibe-coder scan, repo/secret scan, Cloudflare DDoS wrap, bot detection, active deception, and file-upload scanning — installed in one line for Node, PHP/Laravel, Python, Go, Ruby, Java, .NET, Rust, Bun, or Deno.

6 tools · add_waf_rule, check_headers

Windsor MCP (Model Context Protocol) is a hosted MCP server that lets your AI assistant query, explore and analyze live business data from 350+ sources — Meta Ads, Google Ads, TikTok Ads, GA4, HubSpot, Salesforce, Shopify, Stripe, BigQuery, Snowflake and many more — with no SQL, no API keys, and no custom integrations. On connectors that support it, agents can also execute write actions — for example creating and managing campaigns and budgets on Meta Ads, Google Ads, TikTok Ads, LinkedIn Ads, and Microsoft Ads (Bing); publishing Instagram posts; managing Google Business Profile listings and reviews; updating Klaviyo flows and Salesforce records; and more.

6 tools · create_destination_task, execute_action

The official Model Context Protocol (MCP) server for Dash0. Enables AI assistants to navigate your OpenTelemetry resources, investigate incidents and query metrics, logs and traces on Dash0. The Dash0 MCP server is remote and uses the Streamable HTTP transport. See the Dash0 Integrations Hub for instructions on how to connect with the most popular AI agents and coding assistants like Claude, Cline, Cursor and Windsurf. For custom integrations or integrating with other MCP clients, follow the instructions below:

4 tools · Investigate incidents, Navigate monitored resources

A comprehensive Model Context Protocol (MCP) server for solving Constraint Satisfaction Problems (CSP), Linear Programming (LP), Minimax optimization, and SciPy-powered advanced optimization problems. Built on the gurddy optimization library with SciPy integration, it supports solving various classic problems through two MCP transports: stdio (for IDE integration) and streamable HTTP (for web clients). 🚀 Quick Start (Stdio): pip install gurddy_mcp then configure in your IDE 🌐 Quick Start (HTTP): docker run -p 8080:8080 gurddy-mcp or see deployment guide

6 tools · solve_24_point_game, solve_minimax_game

It uses the OpenSSH client already on your machine: your keys, your ~/.ssh/config, your jump hosts, your agent forwarding. Nothing bundled, nothing to compile, no native bindings. Works with Claude Code, Codex CLI, Cline, opencode, Gemini CLI, Qwen Code, Hermes and other MCP clients. Install · Tools · Setup · Security · Roadmap · Docs · Changelog No global installation required. npx downloads the package on first use: Add it to your MCP client — Claude Code, for example — for every project: Or write it by hand — the same server in the config shape most clients share:

4 tools · ssh_exec, ssh_file_read

Connect Claude Code, Codex, or Gemini to live human engineers. 1. npx codevf setup 2. In Claude Code, type claude 3. It works out of the box Use /cvf in Claude Code to force CodeVF. 1. npx codevf setup 2. In Codex, type codex 3. It works out of the box Use /mcp in Codex to confirm CodeVF is connected. 1. npx codevf setup 2. In Gemini, restart the client 3. It works out of the box Configure MCP server integration with Claude Code, Codex, and Gemini: - Authenticate with CodeVF using OAuth - Auto-configure Claude Code's ~/.claude.json file - Create Claude Code slash commands for CodeVF - Select default project for context

4 tools · Override the backend URL, Set up the MCP integration

Search, inspect, and submit MCP servers from your AI agent. MCPVault exposes more than 18,000 records with evidence-labelled grades, freshness, verification, install, and compatibility data. No installation required. Run directly with npx: Add to claude_desktop_config.json (typically ~/Library/Application Support/Claude/claude_desktop_config.json on macOS): Add to your MCP configuration in Cursor settings: Search the MCPVault directory by keyword, category, or status. - "Find me a working postgres MCP server" - "Search for MCP servers in the DevTools category with status verified" - "What MCP servers are available for file system access?"

4 tools · get_install_command, get_mcp_server

The agent control surface for Elementor. A Model Context Protocol server + companion WordPress plugin that let AI agents read, build, refactor and govern real Elementor sites the way engineers ship software — Editor V4 atomic elements first, V3 classic fallback — with authoritative server-side validation, diffs, backups and rollback on every write. - packages/server — TypeScript MCP server: 91 tools (elementor.page., widget, design, templates, media, nav, pro., HTML→Elementor convert), stdio + HTTP transports, lean/full tool profiles. - plugin/elementor-ultra-mcp — WordPress plugin exposing the authoritative REST seam (/wp-json/elementor-ultra/v1/): every write goes through Elementor's own Document::save() with backup snapshots, optimistic concurrency (base_hash), idempotency (op_id) replay, the authoritative validator, and mandatory CSS priming. - packages/shared — the frozen contract surface: REST route registry, error taxonomy, JSON-schema mirrors, golden fixtures. Byte-identical to

5 tools · Build a page, Convert HTML

MCP (Model Context Protocol) server for return0 - a tool for debugging production applications in real-time. return0 enables developers to debug production Node.js applications in real-time. It allows you to monitor and troubleshoot your applications by connecting to live variables, observing execution flow, and understanding runtime behavior directly within the Cursor IDE. This is especially powerful for debugging production applications built with Next.js and deployed on platforms like Vercel, where traditional debugging methods can be challenging.

3 tools · Debug production variables by file and line, Inspect multiple variables across files

Build and deploy full-stack apps with AI. This MCP server connects Claude Code, Cursor, Windsurf, and other AI tools to your AppsAI projects. Supported stacks: - Frontend: Next.js with React, Tailwind CSS, and shadcn/ui - Backend: Parse Server, Express, Fastify, Hono, Supabase Edge Functions, Firebase Cloud Functions, Serverless Framework, or custom - Database: MongoDB Atlas (managed) - Infrastructure: AWS (S3, CloudFormation, EC2, Lambda, and more) Add to claude_desktop_config.json: json { "mcpServers": { "appsai": { "command": "npx", "args": ["-y", "@appsai/mcp-server"], "env": { "APPSAI_API_KEY": "your_key" } } } }

6 tools · Configure custom domains, Create and manage full-stack projects

Stateful MCP server over real language servers. 50 tools, 30 CI-verified languages, 20 agent workflows. Persistent sessions keep the index warm across files and projects. Speculative execution simulates edits in memory before writing to disk.

Free instant HTML hosting API with paste, file upload, and ZIP deploy support. No API key required.

Multi-agent coordination bus over MCP: atomic gap-free claims, advisory file leases, a shared event ledger, presence, prose handoffs, and a task graph, so multiple coding agents (Claude Code, Cursor, Codex) stop colliding and re-deriving each other's work. Remote Streamable HTTP; self-hostable (AGPL-3.0) or hosted at llm-bus.com.

MCP server for [OpenClaw](https://github.com/openclaw/openclaw) AI assistant integration. Enables Claude to delegate tasks to OpenClaw agents with sync/async tools, OAuth 2.1 auth, and SSE transport for Claude.ai.

JMeter MCP Server for performance testing

Self-hosted AI teammate in Slack: @mention it and Claude Code or Codex investigates CloudWatch logs, runs tests, and opens pull requests. The bundled MCP server holds all credentials (GitHub, AWS, Slack) so the agent never sees keys. One-command deploy to your own AWS. MIT.

🐍 🏠 🍎 🪟 🐧 An MCP server that indexes local code into a graph database to provide context to AI assistants with a graphical code visualizations for humans.

Bring structure and preserve context in vibe coding by automatically tracking issues.

A local-first stdio MCP server for building token-efficient codebase context, with live preview, Git scopes, MCP-enforced secret redaction, and syntax-aware compression.

Drives the full App Store release cycle for iOS/macOS apps: version bump, archive + sign + TestFlight upload via your fastlane lane (as async jobs with log polling — the step REST-only ASC servers can't do), metadata updates, and review submission via the ASC API. Zero-dependency ES256 JWT auth. `npx appstore-release-mcp`

Companion Gallery for Codex: public read-only registry for Codex-compatible animated companion packs. Search, preview, install community pets, generate badges/embed cards, and discover the request flow via Streamable HTTP MCP.

MCP server that lets LLMs know everything about your OpenAPI specifications to discover, explain and generate code/mock data

AI-powered Kanban TUI and MCP server for autonomous development workflows. Orchestrates 14 coding agents across task tracking, isolated git worktrees, review, and merge.

Read-only MCP server to help gather metrics from [Swarmia](swarmia.com) for quick reporting.

SWI-Prolog execution for LLMs with CLP(FD), negation-as-failure, and recursion. Benchmarked 90% vs 73% LLM-only accuracy on 30 logic problems.

Read, write, analyze and test the VBA inside Excel, Word, PowerPoint and Access files, and edit the document around it. The file layer needs no Office installation and runs anywhere. Static analysis with 119 diagnostics measured against each host's own object model, writes guarded by a content token so one edit cannot silently discard another, and a git textconv driver that makes a workbook diff as VBA instead of "Binary files differ". Power Query, UserForms, sheets and Visual Basic 6 projects too. `uvx xlide-mcp`.

MCP server for interactive .NET / ASP.NET Core debugging via netcoredbg. 27 tools: breakpoints (line, function, exception, data), stepping, thread inspection, exception autopsy, hang/deadlock analysis, and request tracing.

Parallel multi-model code review, security analysis, and AI debate with ChatGPT, Claude, and Gemini. Orchestrates multiple LLMs for compare, consensus, and OWASP Top 10 security checks.

MCP Server that provides up-to-date documentation for npm packages by fetching the latest README doc from the package's GitHub repository or the README.

Domain-specific fine-tuning of open-source LLMs and SLMs with zero infrastructure. Specialized tuning agents deliver sovereign models trained on your data. Supports Qwen, Llama, DeepSeek, Mistral, Gemma 1B-72B. LoRA, QLoRA, full fine-tuning. Cost estimation, model management, S3 export.

Bug-report triage and fix-dispatch MCP for vibe coders. Ask your AI coding agent for a plain-English diagnosis of any user-reported bug — with evidence, blast radius, and a paste-ready fix prompt — then dispatch an automated GitHub fix PR without a second LLM key. 80+ tools, Supabase-backed, MIT SDK. `npx @mushi-mushi/mcp`

8 MCP tools for exploring and downloading AI agent blueprints. List blueprints, get summaries, download full Agent Skills directories for implementation by coding agents. Vendor-agnostic output works with any enterprise platform. Install: `npx agentblueprint`.

MCP server for the SLURM workload manager. Submit jobs, run YAML workflows, monitor GPU resources, manage SSH profiles, and sync files to remote HPC clusters from natural language. 14 tools spanning local SLURM and SSH-remote clusters; companion CLI and FastAPI Web UI ship in the same package.

Stop stitching context for Copilot and Cursor. With Sequa MCP, your AI tools know your entire codebase and docs out of the box.

Codebase intelligence for AI coding agents. Indexes a repo into a dependency graph, git history, defect-risk code health, auto-generated docs, and architectural decisions, served as 9 task-shaped MCP tools across 15 languages. Runs 100% local; hosted option available.

MCP server that provides Typescript API information efficiently to the agent to enable it to work with untrained APIs

Coding agent with basic read, write and command line tools.

AI ecosystem intelligence MCP server. Verified best practices, news, integrations, and MCP server directory across 22 AI ecosystems including Claude, ChatGPT, Gemini, LangChain, Groq, Cursor, and more. Claude-validated, injection-safe, refreshed twice daily. 📇 ☁️

MCP server for managing and serving dynamic prompt templates using elegant and powerful text template engine.

Regression testing for MCP servers. Auto-discovers servers from Claude configs, checks capabilities, invokes tools, detects schema drift between versions, and recommends new servers based on your environment. Works as both a CLI and an MCP server.

Enforces team naming consistency for AI-generated code via Cursor MCP integration. [Guide ↗](https://var.gg)

Full-featured Excel MCP server. 173 operations: Power Query, DAX, VBA, PivotTables, Tables, Charts, ranges, formatting. 100% Excel compatibility - uses Excel app instead of creating .xlsx files. Windows only.

A middleware server that enables multiple isolated instances of the same MCP servers to coexist independently with unique namespaces and configurations.

280+ free developer & security tools as MCP tools — encoders/decoders, hashes (MD5/SHA/HMAC/bcrypt/argon2/scrypt), JWT decoder, regex tester, JSON/YAML/XML formatters, network diagnostics (ping/traceroute/dig/whois/SSL/SPF/DMARC), OSINT (IP geo, EXIF, vendor lookups), and more. Proxies to the public API at onlinecybertools.com — no auth required. Published to npm with SLSA v1 provenance.

Official MCP server for Emailens, the rendering linter for email. Lint HTML email for rendering issues across 15 clients (Gmail, Outlook, Apple Mail and more), score CSS compatibility 0-100 per client, simulate dark mode, and get framework-native fix snippets for React Email, MJML, and Maizzle. `npx -y @emailens/mcp`

Deterministic architectural decision governance for agentic software development. Six local stdio tools let agents submit non-authoritative proposals and query canonical decisions, applicability, and lineage while human acceptance and enforcement authority remain outside the MCP surface. `uvx --from "mneme-hq[mcp]==0.9.1" mneme decision-mcp`

Developer toolkit: auto-detect stack for AI context files, catch port conflicts, validate .env schemas, spot docs drift, audit dependency licenses, and time coding tasks — 7 MCP tools, one install.

Local-first CLI and MCP wrapper for AI coding agents. Routes shell commands through `sage run --`, stores command history locally, and returns compressed terminal output to reduce context noise.

bash for AI agents on Windows via deterministic bash→PowerShell translation — no WSL, VM, or bash toolchain. MCP `bash` tool with GNU-style output, bash-style errors, coreutils exit codes, session-persisted cwd/env across calls, and per-file UTF-8/GBK sniffing (GBK files grep correctly, unlike Git Bash). Unsupported bash constructs fail loudly with the construct named; native commands (git/node/npm) pass through with argv quoting. `npm install -g fauxnix-cli`; verified with Claude Code, Codex, OpenCode, Kimi Code and Qwen Code.

Multi-perspective architecture review for AI-assisted development. Nine expert viewpoints (CTO, Security, Product, DevOps, Customer, Strategy, Investor, Unicorn Founder, Solo Entrepreneur) analyze your project and produce actionable findings. Includes AI collaboration coaching and quantitative idea scoring.

Self-hosted codebase priors and conventions server. Captures codebase design patterns, conventions, and implementation decisions from git history and developer feedback, serving them to coding agents to ensure local project standards are followed.

Deterministic slop detector for AI-generated prose. Flags filler phrases and clichés with zero false positives by design (curated phrase list, not a model), returns exact spans plus a pinnable 0-1 score, and runs offline with no API key. CLI + CI exit code + MCP server for agents to self-check their own output before it lands in a PR or doc. `pip install defluff`

GitHub Repo MCP allow your AI assistants browse GitHub repositories, explore directories, and view file contents.

Query Go package information on pkg.go.dev

Reports what your test suite is structurally unable to see and proves each gap with a real failing test, across six languages.

Built-in MCP server for [Radar](https://radarhq.io), a modern Kubernetes visibility tool. Lets AI agents query cluster topology, resources, events, logs, and Helm/GitOps state across multiple clusters. Single binary, no agents, no cloud dependency. Apache 2.0.

Record and share your AI-driven development journey. Auto-saves project milestones with summaries, generates structured AI prompts via 5-question planning, and publishes to [pmptwiki.com](https://pmptwiki.com) community platform.

Playwright for terminals - interact with TUI/CLI applications through structured Terminal State Tree representation with element detection.

🎖️ 📇 ☁️ – Give an agent a real Linux VM: run commands, move files, expose a preview URL, destroy it. Own kernel and dedicated VM per sandbox, never shared with another tenant, so untrusted model-generated code stays contained.

Check whether an LLM model id is deprecated, retiring, or retired, and what to migrate to. Covers OpenAI, Anthropic, Azure, Bedrock, Google, and Cohere. No API key. `npx -y @llmintel/mcp` or `https://llmintel.ai/v1/mcp`

MCP server for Jungle Grid, an agentic GPU execution layer that lets AI agents estimate, submit, monitor, and fetch logs for inference, training, fine-tuning, and batch workloads.

Adversarial test generation for AI coding sessions. Detects language and framework; writes tests; runs them; classifies failures via R12 (real_bug / environment / test_bug). Ships 8 adversarial scenario categories. Works in Cline directly and in 8+ editors via Cline host coverage. 162 plugin tests. MIT.

Run privileged, mutating commands — locally or over SSH — with a mandatory single-keypress human approval on every one. The model calls `execute`; a TUI Y/N prompt gates the command, then `sudo` escalates, and no password is ever stored. Sanitized env allowlist, no-shell `argv` execution, replay protection, and audit logging. `cargo install sudo-proxy`.

AST-based dependency analyzer that flags unused packages, calculates actual install sizes, and catches unmaintained legacy bloat. `npx pkgdiet mcp`

Save 30-75% on Manus AI credits through intelligent model routing, smart testing, and context hygiene. Audited across 53 scenarios with zero quality loss.

AI-powered code generator for the Arbitrum ecosystem. 19 MCP tools for Stylus smart contracts, SDK bridging, full-stack dApps, and Orbit chain deployment, backed by RAG-based retrieval over Arbitrum documentation.

Create, read, update, list, and search GitHub Gists from your IDE.

Streaming KoliBri MCP server (NPM: `@public-ui/mcp`) delivering 200+ guaranteed accessible web component samples, specs, docs, and scenarios via hosted HTTP endpoint or local `kolibri-mcp` CLI.

Delegate heavy tasks from Claude Code (or any MCP client) to the Antigravity CLI (Gemini): file analysis, repo archaeology, web lookups, and adversarial second-opinion code reviews. Quota-aware model failover with cooldowns, per-tool timeouts, and multi-turn session continuity.

Annotates any web page with hover labels for AI assistants — reverse proxy injection, zero browser extensions. `npx @mcpware/ui-annotator`

Subscription-aware LLM router for Claude Code. Routes tasks to 20+ providers (OpenAI, Gemini, Groq, Ollama, Codex) based on complexity classification, Claude subscription pressure, and cost. Free tasks stay on Claude subscription; expensive tasks fall back to the cheapest capable model. Includes 30 MCP tools, 6 auto-routing hooks, semantic dedup cache, prompt caching, daily spend cap, and a live web dashboard.

Fast SSH connection manager with TUI dashboard and MCP server for discovering, searching, and executing commands on remote hosts.

Deterministic execution guardrails, isolated AST math evaluation, SSRF-safe DNS routing, and autonomous malformed JSON repair.

MCP server that automatically converts any OpenAPI/Swagger specification into a set of usable MCP tools. Unlike manual tool definition, this approach auto-generates tools directly from the Swagger spec, ensuring consistency, reducing maintenance effort, and preventing mismatches between the tools and the actual API.

WordPress plugin exposing Rank Math SEO fields, JSON-LD schema, and content snapshots (stable content hash, confirm-token verified restore) as REST routes and Abilities API tools, surfaced as MCP tools through the official mcp-adapter. Additive-only write gate, kill switches, and an audit log. Pairs with Elementor MCP (EMCP) for layout editing; never writes `_elementor_data` itself.

Interactive PTY sessions for AI agents — local shells, SSH with persistent sessions (ai-tmux daemon for attach/detach), and serial ports. Single Go binary, no tmux dependency.

Exposes `.context/` folder files as MCP resources, giving Claude Code instant access to project documentation via `@` mentions.

Gives AI agents self-awareness about their cognitive state. Monitors token utilization, context quality degradation, and session fatigue. Returns health scores (0-100) and recovery recommendations based on model-specific degradation curves.

Visual feedback as agent work packets. Stakeholders drop pins on your live app; your AI coding agent reads each pin (selector, screenshot, DOM snippet, thread, acceptance criteria) via MCP and ships the fix, recording the commit/branch/PR on resolve. Install: `npx pincushion-mcp`.

Mobile E2E MCP (40 tools): iOS-simulator control, native UI automation, Maestro flows, React Native debugging (logs/network/state), and WebView DOM inspection. Requires macOS + Xcode.

🎖️ 📇 🏠 MCP Server that support for querying and managing all resource in [Apache APISIX](https://github.com/apache/apisix).

Run untrusted Python/JavaScript code in WebAssembly sandboxes.

Developer-focused MCP server for code analysis, JSON repair, encoding fixes, and import organization across local projects.

Enterprise AI coding usage analytics — track spend, model usage, and costs across Cursor/Claude Code sessions via MCP server

This MCP server provides a tool to download entire websites using wget. It preserves the website structure and converts links to work locally.

Copy/paste (duplicate code) detection for codebases. The jscpd detector's built-in MCP server lets agents check snippets and files for duplication against a scanned project — useful as a DRY gate before an agent commits generated code. Self-contained binary, stdio transport: `jscpd --mcp`.

A swiss-army-knife that can manage/execute programs and read/write/search/edit code and text files.

MCP server that connects your IDE or AI assistant to GitHub Copilot CLI for code analysis, review, and batch processing

Free HTML/URL to PDF conversion API powered by Playwright. No API key required.

Lets an AI build and maintain Altium Designer component libraries: reads and writes .PcbLib footprints and .SchLib symbols byte-exactly (34 tools, IPC-7351B-driven footprints, STEP models, one-click Claude Desktop install).

A MCP server that keeps your chat history organized and searchable—with AI-powered summaries, secure memory, and full control.

Nine-tool MCP server for n8n: generate workflow JSON from natural language, lint for deprecated node types, missing `typeVersion`, and broken connections, and debug per-node execution failures. Ships with a Claude Code skill. Install: `npx @automatelab/n8n-mcp`.

Dynamic API discovery and execution from OpenAPI specs. Uses semantic search and dependency graphs to find relevant endpoints across multiple registered APIs, plan multi-step workflows, and execute API calls — without dumping entire specs into context.

MCP server providing AI assistants with full control of Neovim instances via msgpack-RPC. Read/edit buffers, run commands, send keys, query LSP diagnostics, and annotate code with highlights. No plugin required.

MCP server for seamless document format conversion using Pandoc, supporting Markdown, HTML, PDF, DOCX (.docx), csv and more.

Multi-LLM deliberation with anonymized peer review. Runs a 3-stage council: parallel responses → anonymous ranking → synthesis. Based on Andrej Karpathy's LLM Council concept.

A zero-configuration Go library to automatically expose any existing Echo web framework APIs as MCP tools.

7 SQL tools (validate, format, parse, lint, security scan, metadata extraction, full analysis) over Streamable HTTP. Public remote server at mcp.gosqlx.dev - no install needed. 1.25M+ ops/sec, 6 SQL dialects.

Zuul CI integration with 14 tools for build failure analysis, log search, pipeline status, and job configuration.

Self-hosted MCP for live docs, code audits, snippets, and best practices across 445+ libraries. 14 tools, 107 audit patterns with file:line precision, BM25-ranked snippets, lockfile-aware version pinning, npm/PyPI/crates.io/Go fallback. No API keys, no rate limits, Context7 alternative. `npx -y @groundtruth-mcp/gt-mcp`

MCP server for [Perfetto](https://perfetto.dev) trace analysis. Runs PerfettoSQL queries on `.perfetto-trace` / `.pftrace` files via auto-downloaded `trace_processor_shell`, with dedicated Chrome tools for page loads, scroll jank, main-thread hotspots, and stdlib module discovery. Cross-client tested on Claude Code and Codex. Available via `cargo install`, Homebrew tap, and curl install script.

Token-efficient access to OpenAPI/Swagger specs via MCP Resources.

Semantic code index that extracts domain concepts, naming conventions, and behavioral similarity from codebases. One tool call instead of 19, ~20x fewer tokens for codebase understanding queries.

Locust MCP Server for performance testing

Structured planning, parallel execution in git worktrees, and deep validation for Claude Code. Turns a one-line objective into a validated DAG of modules executed by worker agents, each self-checked and cross-module-reviewed before merge-back. 7 MCP tools: `validate`, `validate_plan`, `memory_recall`, `memory_save`, `iteration_state` (per-run scoped, with stagnation/velocity/oscillation detection), `forge_logs`, `session_state`. Stdio-only. Zero telemetry.

MCP server that integrates Jira and GitHub to automate end-to-end developer workflows, from issue tracking to branches, commits, pull requests, and merges inside the IDE.

Delegate multi-file implementation from Claude Code, Codex, or Copilot CLI to Cursor's CLI agent (Composer 2.5) over ACP. Returns a typed result — final message, agent-reported changed files, session id, and plan — instead of scraped terminal output. Plan mode drafts first, then resumes the same session to implement; clarifying questions come back as normal results rather than stalling. Ships plugin manifests for Claude Code, Codex, and Copilot. MIT.

A real Excel-compatible spreadsheet engine for agents, over [LogiSheets](https://github.com/logisky/LogiSheets) (Rust, via WASM). Deterministic formulas the model does not compute in its head, named blocks addressed by (block, key, field) instead of coordinates so references survive inserted rows, whole-column field rules, batch scenario scans and goal-seek in a single call, and a genuine `.xlsx` at the end. Runs locally and opens no sockets. `npx logisheets-mcp`.

Cisco pyATS server enabling structured, model-driven interaction with network devices.

An MCP server that enable all IDEs/CLIs to access Claude Code Skills capabilities.

Endor lets your AI agents run services like MariaDB, Postgres, Redis, Memcached, Alpine, or Valkey in isolated sandboxes. Get pre-configured applications that boot in less than 5 seconds.

MCP server giving AI agents programmatic control over Android devices and emulators via ADB. 11 tools covering UI inspection, screen interaction, ADB commands, and change detection.

GitHub Actions — view workflow runs, read logs, re-run failed jobs, and manage CI/CD.

Autonomous coding pipeline: a frontier model plans, reviews, and adjudicates risk while a local model implements under TDD, acceptance-oracle grading, and a merge gate that re-runs the suite against the rebased branch.

Read-only access to self-hosted SonarQube Community Build: issues, security hotspots, rules and code snippets so an agent can fix findings locally.

Policy layer for multi-agent workspaces: one JSON policy file decides what each path is worth; agents can audit, explain and dry-run clean plans themselves, nothing is ever deleted by pattern, and every action lands in a hash-chained journal. Zero dependencies; `pip install workspace-metabolism` then `wm mcp`.

Free Open Graph image generator API with themes, Lucide icons, and custom layouts. No API key required.

Next-gen AST codebase map, token compression (70%~85% savings), and context packaging engine for AI coding agents & IDEs.

Formats files using `.editorconfig` rules, acting as a proactive formatting gatekeeper to ensure AI-generated code adheres to project-specific formatting standards from the start.

Forces every AI Agent code change to leave a structured problem / reason / approach audit record before commit. 11 MCP tools (all annotations filled); pre-commit hook blocks unaudited changes; GitHub Pages dashboard renders the audit trail in real time. M8ven Trust Index 100/A (Verified Publisher + Live Monitored). Install: `pip install pandaone-guard==0.7.14`.

MCP server with reasoning, code, anti-deception, and memory tools for AI agents.

Token usage tracker for OpenAI and Claude APIs with MCP support, real-time session tracking, and accurate pricing for 2025 models

Coordination server for parallel coding agents: TTL file claims that refuse overlaps with the owner, reason and expiry, a task board with dependencies, versioned interface contracts, change notices, a decisions log, and path-scoped memory notes delivered back with the claim. 22 tools over stdio or HTTP, single Rust binary with a live dashboard. Install with `cargo install tirith-mcp`. MIT.

A line-oriented text file editor. Optimized for LLM tools with efficient partial file access to minimize token usage.

Arch Linux MCP Server to the Arch Linux ecosystem of the Arch Wiki, AUR, and official repositories for AI-assisted Arch Linux usage on Arch and non-Arch systems. Features include searching Arch Wiki and AUR, getting package info, checking for updates, installing packages securely, and analyzing PKGBUILDs.

The Figma desktop app as an MCP server. Gives AI agents the full Plugin API on the open file, returns renders inline, reads design tokens, makes each call one undo step, and registers itself with every MCP client it finds. No cloud API, token or quota.

MCP server that gives AI assistants seamless access to shadcn/ui v4 components, blocks, demos, and metadata.

Security-hardened MCP server for Linux system administration via 189 typed actions instead of shell strings, with an Ed25519-signed hash-chain audit log, one-time TTL approval receipts, and automatic rollback. Works with Claude Code, Cursor, and Codex CLI.

MCP server providing accurate information about NixOS packages, system options, Home Manager configurations, and nix-darwin macOS settings to prevent AI hallucinations.

MCP AI Server for Visual Studio. 20 Roslyn-powered tools giving AI assistants semantic code navigation, symbol search, inheritance trees, call graphs, safe rename, build/test execution. Works with Claude, Codex, Gemini, Cursor, Copilot, Windsurf, Cline.

All-in-one developer tool and MCP Server for Roku development, featuring ECP device control, automated channel sideloading, BrightScript debugging, and real-time log monitoring.

Valkey-first observability with Redis compatibility. Query real-time metrics, analyze slow commands, detect hot keys, and investigate performance issues directly from AI coding assistants.

Official MCP server to interact with Docker Hub, providing access to repositories, hub search and Docker Hardened Images

Local-first codebase intelligence engine. Gives coding agents structured context packets, indexed code/schema facts, and diagnostics over MCP, backed by a local SQLite store — so agents stop rediscovering your repo with raw grep. Optional Postgres/Supabase awareness and a bundled Claude Code plugin.

Design-fidelity checks for AI agents: compare a Figma frame (or any design screenshot) against the rendered implementation and get structured discrepancies with CSS properties and severity. Resolves a natural-language component description to a URL + selector in your codebase, screenshots it with Playwright, and compares via vision AI using your existing Claude Code or Codex subscription — no API keys. 90% mutation recall, zero false positives on its golden eval set. `npx -y kiyas-cli mcp`

Outputs short-form Rust crate derived traits,interfaces, etc. from AST (uses same api as rust-analyzer), output limits (token estimation) & crate docs w/regex stripping.

Deterministic multi-agent orchestrator for 37 CLI coding agents (Claude Code, Codex, Cursor, Aider, Gemini CLI, GitHub Copilot CLI, OpenHands, OpenCode, Goose, Qwen, Ollama, and more). MCP server mode (stdio + HTTP/SSE) exposes the orchestrator to any MCP client. Git worktree isolation per agent, HMAC-chained audit trail, cost-aware model routing via contextual bandit. Apache 2.0.

A Model Context Protocol (MCP) server that provides a set of tools for retrieving information about SonarQube projects like metrics (actual and historical), issues, health status.

Generate deployment-ready PWA, iOS, and Android app icon sets from a text description. Produces all 27 required sizes, maskable icons, Xcode-ready iOS icons, Android mipmap folders, splash screens, and manifest.json — packaged as a ZIP. Powered by Google Imagen 4.

Omega Brain MCP Server. Hardened AI execution pipeline prioritizing NAEF logic constraints over narrative LLM hallucination. 15 VERITAS Build Gates for uncompromising determinism, semantic vault integration, and Tri-Node Cortex validations.

A Javascript code execution sandbox that uses v8 to isolate code to run AI generated javascript locally without fear. Supports heap snapshotting for persistent sessions.

MCP server for JetBrains TeamCity with 87 tools for builds, tests, agents, and CI/CD pipeline management. Features dual-mode operation (dev/full) and runtime mode switching.

MCP Server for the [Bitrise](https://bitrise.io) API, enabling app management, build operations, artifact management and more.

TMF checks source-context freshness against a selected Git working tree and retrieves source-linked code relationships on demand, helping coding agents revisit stale understanding and consider cross-file impact.

Browser-backed MCP wrapper for mcp-atlassian with Playwright SSO auth. Enables AI tools to access Atlassian Server/Data Center instances behind corporate SSO (Okta, SAML, ADFS) where API tokens are not available.

Provide coding agents direct access to Figma data to help them write Flutter code for building apps including assets exports, widgets maintenance and full screens implementations.

Dynamically load Claude Code skills into AI agents without copying files. Discover, read, and install skills on demand.

GitHub repository health monitoring for AI assistants. Analyze health scores (A-F grades), OpenSSF security checks, DORA metrics, code scanning alerts, and CI/CD status of any repo.

MCP server exposing SSH control for Linux and Windows servers via Model Context Protocol. Securely execute remote shell commands with password or SSH key authentication.

MCP server for [TaskBounty](https://www.task-bounty.com). AI agents fix GitHub bugs (every fix ships with a regression test) and raise test coverage on your codebase. Posters draft and fund bounties from chat (Stripe Checkout); solvers submit PRs verified end-to-end in a sandbox. Paid in USDC, ETH, or BTC. 11 tools.

Compiler-as-MCP-server for the Hirð language (typed actors and effect rows on the BEAM): type inference, definition lookup, effect-row explanation, IR fragments, actor protocol and supervision graphs, and token-budget-aware symbol summaries, so agents query the compiler instead of reading source. Errors come back structured, so an agent can self-correct from tool output alone. `cargo install --git https://github.com/no-materials/hird hird-mcp`

Search and contribute to a community-verified knowledge base of 25,000+ engineering issues and fixes. Find step-by-step solutions with trust scores, submit new issues, and verify fixes work in your environment.

A MCP Server that enhance your IDE with AI-powered assistance for Intlayer i18n / CMS tool: smart CLI access, access to the docs.

Test management over MCP. Author manual test cases, assemble and run manual executions with per-case results, cut releases, and link automated tests to the cases they cover. Guided prompts for flaky-test triage, release readiness and regression hunts. Hosted or self-hosted. Install: `npx -y @m00nsolutions/mcp-server`.

Guardrail that checks agent-written code against a repo's own git-history-learned patterns — flags foreign dependencies, reinvented functions, misplaced code, broken layering, and gamed tests. Exposes `voice_context` (the repo's familiar imports/idioms for a file, so agents write in-voice before generating), `check` (score a generated hunk against the repo's patterns), and `explain`. 100% local, no LLM, single Rust binary. `npm i -g @tmonier/argot`

Lets an AI agent gate its own work before claiming "done": a fail-closed ship checklist (`verify_gate` counts a check satisfied only if explicitly proven), required independent refute-first review, and an append-only sha256-chained receipts ledger that makes any edit to past receipts detectable. `pip install mcp-agent-gate`.

Encoding-aware, indentation-smart file tools for AI coding agents. 20+ tools including read/edit with automatic encoding detection, smart indentation conversion, SSH, SFTP, process management, and system utilities. Preserves file encoding (UTF-8, EUC-KR, Shift_JIS, etc.) and respects .editorconfig settings.

Run Codex agents from Claude Code through MCP and Channels, with live progress notifications, mid-task steering, and saved session continuation.

Scaffold, compose, and upgrade modern multi-language projects from your agent — a single MCP surface over the create-packkit generator family (any supported language) plus a fullstack composer that stitches a frontend and backend into one repo. Also available as a CLI and a web configurator. `npx -y packkit-mcp`

AI pilot for PTY operations enabling agents to control interactive terminals with stateful sessions, SSH connections, and background process management

Code graph context engine with 24 MCP tools for structural code intelligence. Tree-sitter parsing for 170+ languages, dependency graphs, blast radius, hotspots, dead code, and adaptive context injection. Benchmarked +27% F1 on change-localization.

An MCP server that bridges to multiple OpenAI-compatible LLMs - your AI rubber duck debugging panel for explaining problems to various AI "ducks" and getting different perspectives

Flatten Claude Code sessions: keep every prompt verbatim, resume at a lower token count instead of lossy compaction.

Gradle integration using the Gradle Tooling API to inspect projects, execute tasks, and run tests with per-test result reporting

Outbound-only remote shell, detached long-running jobs, and temporary file courier for AI agents (https://aicommander.dev). Hosted Streamable HTTP; no exposed SSH/ports/VPN. Install via npx -y @aicommander/mcp.

A MCP server that uses [gitingest](https://github.com/cyclotruc/gitingest) to convert any Git repository into a simple text digest of its codebase.

MCP server exposing SSH control for Linux and Windows servers. Allows long running commands and the ability to perform commands on multiple hosts at the same time.

MCP server for TNL (Typed Natural Language): per-feature English contracts for AI coding agents. 6 tools — `get_impacted_tnls`, `retrieve_tnl`, `trace`, `propose_tnl_diff`, `approve_tnl_diff`, `verify` — let agents look up relevant contracts, propose contract edits, and verify implementations against them. Drop-in via `npx typed-nl init` for Claude Code, Codex, Gemini.

A JetBrains IDE plugin that exposes an MCP server, giving AI coding assistants full programmatic control over the debugger.

Analyze React code locally, generate docs / llm.txt for whole project at once

Visualizes code, architecture and other concepts as mermaid diagrams in a locally hosted web app. Just ask your agent to "show me this in a diagram".

Java memory leak diagnostics via jcmd, jmap, jstat, JFR, Eclipse MAT, and async-profiler with structured confidence-based verdicts. Two-stage escalation model with conservative scan and deep forensics.

Figma MCP server with full read/write access via plugin bridge — no API token, no rate limits. 58 tools for design automation: styles, variables, components, prototypes, and content.

Agent-optimized MCP server replacing built-in file, search, exec, and git tools with compact structured JSON. Native plugins for git, cargo, gh, and docker. Semantic output filtering, read deduplication, batch operations, and token analytics. Benchmarked 20-45% token savings.

Run DeepSeek as a real sub-agent inside Claude Code / Codex CLI. DeepSeek gets its own 7-tool agent loop (Read/Write/Edit/Bash/Glob/Grep/NotebookEdit) in a sandboxed workspace, not just a single LLM call. Includes token-based command sandbox, pre-flight web-search pattern, and cross-platform installer.

Universal MCP server that transforms any CLI tool into an MCP server. Works with any CLI that has `--help` output, supports caching for performance.

Deterministic tech stack recommendations with 6-dimension scoring. Analyze, compare technologies, get optimal stack suggestions for any project type. 10 tools (4 free, 6 Pro).

A Model Context Protocol server that provides access to iTerm. You can run commands and ask questions about what you see in the iTerm terminal.

Give AI agents a persistent pixel-art character that reflects their state in real time. Report work state, mark tasks complete, signal errors, and check status. Characters live in rooms with emotions and creature companions.

Manage multiple SSH servers from one MCP: command execution, file transfer/rsync, database dump/import/query (MySQL/PostgreSQL/MongoDB), backups & restore, health monitoring, persistent sessions, tunnels, ProxyJump/bastion, and opt-in per-server security modes (readonly/restricted) with audit log. Linux, macOS & Windows OpenSSH.

Mechanical control plane for AI coding agents. Time-locks writing, requires evidence receipts for claims, runs adversarial review, and preserves a sealed verification record. Run as an MCP server with `uvx --from fable-engine==1.3.3 fable-engine`; optionally install its bundled Agent Skill with `uvx --from fable-engine==1.3.3 fable-mode install-skill --yes`.

Open-source registry of 75+ free animated React components (shadcn-compatible) exposed over MCP: eight read-only tools to list, search, fetch, and get install commands for components, design systems, and templates from the live aicanvas.me registry. `npx -y @aicanvas/mcp`

Turn markdown into a shareable link that renders as a typeset document (tables, Mermaid, math, pagination); the content lives in the URL, nothing is uploaded.

MCP server that lets LLMs execute code through the Piston remote code execution engine, with a zero-config `uv` setup and a ready-to-use Claude Desktop config example.

A Model Context Protocol (MCP) server for interacting with iOS simulators. This server allows you to interact with iOS simulators by getting information about them, controlling UI interactions, and inspecting UI elements.

Pin visual feedback on any live web page — localhost, staging or production — and hand it to your coding agent with the element, its CSS selector, a screenshot and the whole thread attached, then get a pull request back. Bridges to the Yocoolab browser extension locally and syncs threads through the Yocoolab API. Listed on the official MCP Registry (`io.github.Jonahbkerr/yocoolab`). `npx -y @yocoolab/mcp-server@2 setup`

Drives CT (Controller Tester) C/C++ verification from an MCP client: project setup, toolchain resolution, analysis, test generation and execution, statement/branch/MC-DC coverage, and report export. Requires a local CT 2026.06 or later installation; without one the server reports zero tools. Listed on the official MCP Registry (`io.github.SuresoftTechnologies/dvera-mcp`).

The ROS MCP Server supports robot control by converting user-issued natural language commands into ROS or ROS2 control commands.

Android MCP server for AI-assisted Android development. Build APKs, launch emulators, manage devices, automate UI, and analyze logs through natural conversation.

x402-native API gateway with 20+ capabilities (web-extract, web-search, translate, image-generate, screenshot, PDF, OCR, and more) payable with USDC on Base. No API keys — agents pay per call via HTTP 402.

Stateful, structured, auditable shell sessions for AI agents over local, SSH, and Docker. Secret redaction, output budgeting, SSH host-key verification, and a loopback read-only browser viewer that streams the live transcript.

A Model Context Protocol (MCP) server that enables LLMs to interact with iOS simulators (iPhone, iPad, etc.) through natural language commands.

Routes an AI coding agent's code search through an official language-server index (clangd / Roslyn / tsserver / pyright) instead of grep, returning a token-capped `file:line` list with no source bodies — ~20× fewer tokens. Also symbol-level edit-by-name, a Bash-grep→indexed-query rewrite hook, and git/p4 output compaction. Local-only, no IDE. Claude Code plugin + `vts` CLI.

Native stdio bridge for the hosted Delx Protocol MCP endpoint, with one-command client install, doctor checks and live tool discovery.

MCP server for npm package management — 36 tools for publish, version, search, audit, install, and more from your AI assistant.

Affected-test selection for Kotlin/Android projects: returns only the unit tests impacted by the current working-tree changes, so agents skip full test runs while iterating. Function-level static analysis via Kotlin Analysis API — call graph over functions, properties (initializers, delegates, accessors), constructors and callable references — with automatic multi-module and Android variant source-set discovery. Verified on Now in Android (34 modules, ~4s per query). `brew install mikhailhal/tap/ariadne`

🐍 ☁️ 🏠 – Jaeger distributed tracing MCP. 5 tools: list_services, list_operations, search_traces, get_trace, get_dependencies. Any Jaeger instance (HTTP API v3); PyPI + MCP Registry.

Simple MCP Server to enable a human-in-the-loop workflow in tools like Cline and Cursor.

MCP configuration health check, binary validator, and JSON auto-repair engine for Claude Desktop, Cursor, and Cline.

Official Ollama MCP Server. Exposes ollama_chat, ollama_generate, ollama_pull_model, ollama_list_models and ollama_show_model tools for advanced AI interactions.

Intelligent learning sidecar for AI coding assistants. Helps developers learn from AI-generated code changes through interactive blocking quizzes and provides agents with persistent project-specific debugging memory using silent RAG tools. Features 56% token optimization and multi-language support.

MCP Language Server helps MCP enabled clients navigate codebases more easily by giving them access to semantic tools like get definition, references, rename, and diagnostics.

📇 ☁️ – Remote MCP server at `https://drwho.me/mcp/mcp` with 10 developer utilities: base64 encode/decode, JWT decode (no verify), DNS lookup via Cloudflare DoH, UUID v4/v7, URL encode/decode, JSON format, User-Agent parse, IP lookup via ipinfo. Open access over streamable HTTP — point Claude Desktop at the URL.

Offload cheap work from your cloud LLM agent to a local Ollama model — summaries, drafts, extractions, and first-pass code reviews via purpose-built handoff tools with baked-in prompts, at zero cloud cost.

Manage Featureflip feature flags from AI agents: create and toggle flags, edit targeting rules, and find stale flags.

MCP server that helps AI agents explore OpenAPI specs, search endpoints, and generate TypeScript types.

Codebase intelligence and context engine for AI coding agents. Indexes a repo into a deterministic code graph (symbols, references, dependency and reverse-dependency edges) with semantic diffs and impact analysis - 10 tools, no API keys, 100% local. `npx -y ctxai-cli mcp`.

Enable AI assistants to interact with your feature flags in [Flipt](https://flipt.io).

"The official MCP server for the Nahook webhook platform — trigger webhooks, inspect deliveries, retry failures, and manage endpoints from your AI assistant."

MCP server for the POX SDN controller to provides network control and management capabilities.

On-demand .NET memory profiling MCP server. Wraps JetBrains dotMemory with a heuristic rule engine (10 rules) to detect memory leaks, LOH fragmentation, and anti-patterns, providing AI-actionable code fix suggestions.

🏎️ 🏠 🍎 🪟 🐧 Give hands to AI. MCP server to run shell commands securely, auditably, and on demand on isolated environments like docker.

The Unitree Go2 MCP Server is a server built on the MCP that enables users to control the Unitree Go2 robot using natural language commands interpreted by a LLM.

A Model Context Protocol (MCP) server that converts OpenAPI/Swagger specifications to MCP format, enabling AI assistants to interact with REST APIs through standardized protocol.

Code graph for AI agents: resolves Python and TypeScript calls to fully qualified names and reports the share it could not resolve instead of guessing. Multi-hop impact analysis and call tracing, authz reachability audit, coupling/PageRank metrics, architectural drift against declared patterns. Local, SQLite. `uvx --from codegraph-brain cgis-mcp`

An MCP server to manage test suites and cases, which is an alternative to Postman.

Reliable async execution for agent tool calls: schema-gate hallucinated payloads before they run, absorb rate limits and outages with retries/backoff/circuit breakers, idempotency keys, human approval gates, encrypted credentials, replay, and signed-webhook results. Errors come back with an `llm_hint` the agent can self-correct from. Hosted remote (`api.klanexai.com/mcp`, free sandbox) or `npx -y klanex-mcp`.

Hosted MCP server that parses TypeScript and Python codebases into Neo4j knowledge graphs for blast radius analysis, dead code detection, dependency tracing, and architectural context.

Context engineering MCP server. Generates CLAUDE.md from git history and architectural file sampling, and maintains a concept-map snapshot of features/flows → files so agents can skip grep/glob on repeat queries.

Multi-purpose API toolkit: email validation, DNS lookup, WHOIS, SSL certificate inspection, IBAN validation, business day calculator, hash encoding, and GPU pricing. Free tier included. `pip install kiprio-mcp`

Administer a Linux server from an MCP client such as Cursor or VS Code: read files and tail logs, check/reload/restart systemd services, manage cron jobs inside a dedicated crontab section, run read-only MySQL queries, drive WP-CLI on WordPress sites, run safe Git commands, and execute sandboxed Python. Directories, services and WordPress sites are allowlisted in `config.json`, and every tool returns a uniform `{success, data, error, meta}` response. Runs as a systemd service over HTTP.

.NET Template Engine MCP server for AI-driven project scaffolding. Search, inspect, preview, and create `dotnet new` projects via natural language with parameter validation, smart defaults, NuGet auto-resolve, and interactive elicitation.

📇 🏠 🍎 🪟 🐧 — Full-featured utility to test Next.js projects for unused files and APIs, with an MCP server that exposes project analysis tools to AI assistants.

Tool suite built around an MCP server for Android automation for developer workflow and testing

AI-powered time-travel debugger with bidirectional execution replay, audit-compliant hash-chain logging, and SIMD-accelerated stack unwinding. Free Hobby tier available.

MCP tools and Skills for Android/iOS runtime inspection and control: method hooks, state inspection, temporary overrides, UI actions, and screenshots. Built on Frida; requires debug-build integration.

Control HarmonyOS-next devices with AI through MCP. Support device control and UI automation.

The IDE for agents: read code by symbol, edit against a known revision with compiler diagnostics in the response, validate with the project's own build and tests, and revert to a checkpoint. Tree-sitter plus real language servers for Go, Java, Scala, TypeScript, Python, Rust and Ruby. Official MCP Registry: `io.github.julianbei/arno`. `curl -fsSL https://raw.githubusercontent.com/julianbei/arno/main/install.sh | sh`

Roslyn-based MCP server with 22 semantic code intelligence tools for .NET. Type hierarchies, call graphs, DI registrations, diagnostics, code fixes, complexity metrics, and more. Sub-millisecond lookups via pre-built indexes.

Semantic codebase search + persistent working memory for AI code editors. Hybrid dense + BM25 search over AST-aware chunks, a symbol graph for locate/trace, and typed notes that survive context compaction and session restarts. Local embeddings, zero config, no API key. `pip install vectr`

Generate and read PDFs for AI agents: a `generate_pdf` tool (HTML, a URL, or a template + JSON → PDF) and a `read_pdf` tool (a PDF → text/markdown). Run locally with `npx @docweave/mcp` or use the hosted streamable-HTTP endpoint. Chromium-rendered, priced per document.

Docker container management and operations through MCP

Structural graph map of any codebase for AI coding assistants. Scans entities, relationships, and feature flows across 13 languages so LLMs navigate by structure instead of grepping through everything.

Deterministic execution engine for AI agents with 412 modules across 78 categories (browser, file, Docker, data, crypto, scheduling). Features execution trace, evidence snapshots, replay from any step, and supports both STDIO and Streamable HTTP transport.

Persistent code index MCP server using Tree-sitter for fast, precise code search. Replaces grep with ~50 token responses instead of 2000+. Supports 11 languages including C#, TypeScript, Python, Rust, and Go.

Web accessibility testing MCP server that analyzes URLs and HTML for WCAG 2.0/2.1/2.2 compliance using axe-core. Tools for color contrast, ARIA validation, and orientation lock detection.

Production-grade MCP server for secure access to local dev environments (filesystem, databases, processes, OpenAPI). Includes scope enforcement, command allowlist, and read-only DB mode.

Deterministic guardrail for AI-written diffs, runnable from inside the coding agent's own loop over MCP. Zero-LLM-token, AST-precise rules (SQLi, SSRF, XXE, permissive CORS, prototype pollution, hardcoded secrets) across 8 languages, plus structural checks for reinvented helpers and over-abstraction — findings scoped to only the changed lines, same input always gives the same output, no false-block guarantee. `npm i -g diffgate-review` (registers as the `diffgate` command; `diffgate mcp` starts the server)

58 semantic C#/.NET analysis tools via Roslyn. Navigation, refactoring, find usages, and code intelligence for AI agents.

Reads the embedded images other Excel servers drop: diagrams and screenshots come back as `ImageContent` mapped to the cell they sit in, so specs where the workflow lives in a picture are actually readable. Also surfaces the formatting that carries meaning (bold, strikethrough, highlight and font colors) and skips hidden rows/columns unless a visible formula depends on them. Write support with atomic saves. `uvx excel-vision-mcp`.

📇 ☁️ 🏠 – A programming-focused task management system that boosts coding agents like Cursor AI with advanced task memory, self-reflection, and dependency management. [ShrimpTaskManager](https://cjo4m06.github.io/mcp-shrimp-task-manager)

Automatically converts feedback and bug reports from websites and web apps into actionable, context-enriched developer tasks. Delivered straight to your AI coding tools, the Webvizio MCP Server ensures your AI agent has all the data it needs to solve tasks with speed and accuracy.

A MCP server for LLDB enabling AI binary and core file analysis, debugging, disassembling.

Strict AI code reviewer powered by Groq. Finds bugs, vulnerabilities and SQL injections. Tools: analyze_code, compare_code, explain_code, generate_tests, analyze_file, HTML reports.

Local-first, read-only MCP server that audits test architecture across JavaScript/TypeScript, C#, Elixir, Go, Kotlin/JVM, PHP, Python, Ruby, Rust, and Swift, then produces evidence-backed findings, rankings, and repository-native test plans. `npx --yes repo-test-architect mcp`

OpenAPI-MCP: Dockerized MCP Server to allow your AI agent to access any API with existing api docs.

Local-first MCP runtime for coding agents with bounded workspace access, guarded writes, AST search, LSP navigation/diagnostics, and Git tooling.

AI 測試大師 — end-to-end QA loop over MCP. Drives pytest / Jest / Cypress / Go / Maestro from one surface; analyzes URLs (Web DOM) or live mobile screens (`maestro hierarchy`) to extract testable modules, generates runnable pytest or Maestro YAML with real selectors (not `# TODO` stubs), runs with auto-retry, then writes a prioritized `optimization-plan.md` ranked by evidence (flaky vs broken vs coverage gap). Mobile-first: iOS Simulator, Android Emulator, real devices, and BlueStacks (`QA_ANDROID_HOST=127.0.0.1:5555`). Install via `uvx mk-qa-master`.

Xcode integration for project management, file operations, and build automation

A personal MCP (Model Context Protocol) server for securely storing and accessing API keys across projects using the macOS Keychain.

An MCP server to communicate with the App Store Connect API for iOS Developers

Helping Your AI Agent Identify Hotspots for Refactoring; Help AI Understand How to 'Make Code Better'

A high-performance Rust reimplementation of WCGW for code agents, providing shell execution and advanced file management capabilities for LLMs via MCP.

Checks the context files a coding agent reads (CLAUDE.md, AGENTS.md, SKILL.md, .cursor/rules) against the git index: wrong letter case, broken links, missing paths, commands nothing defines, and agent configuration that points at nothing. Two more tools report which sections drifted from the code and what each file costs.

API governance server that detects breaking changes in OpenAPI specs. Diffs two spec versions, applies configurable policy rules (strict/default/relaxed), and returns structured pass/fail verdicts. 23 change types, 10 breaking. Supports OpenAPI 3.0, 3.1, and Swagger 2.0.

Free styled QR code generator API with custom colors, logos, frames, and batch generation. No API key required.

DNS lookups, reverse DNS, WHOIS, and domain availability checks. Zero auth, zero config.

Connect AI agents to MATLAB — execute code, run async jobs with progress reporting, get interactive Plotly plots, expose custom .m functions as tools, and monitor via live dashboard.

40 regulation-and-deadline linters as MCP servers (EU CRA/CSAF, DORA, NIS2, EU AI Act, PCI DSS 6.4.3, WCAG 2.1 AA, EN 16931 e-invoicing, KSeF, NF-e, TLS certificate lifetime, Kubernetes removed APIs). Every finding returns file, line and fix; `check_text` and `check_file` are free, `check_dir` sweeps a folder (licence, free for 7 days). `npx -y @readystack/<name> --mcp`

Code-intelligence engine that indexes a repo into a persistent knowledge graph — functions, classes, call chains, HTTP routes, cross-service links. 159 languages via tree-sitter + Hybrid LSP, sub-ms structural queries, ~99% fewer tokens than grep. Single static binary, zero dependencies, 100% local. `npx codebase-memory-mcp`

Workspace-aware prompt engineering. Refines, analyzes and generates prompts based on your project's tech stack, dependencies and context. Free to use.

Automatic enforcement of critical rules for Claude AI preventing 96 documented failure patterns. Provides compliance verification checklist and rules summary via MCP tools.

Universal local router for Agent Skills across Cursor, Claude Code, Antigravity, and MCP clients with zero-token sub-20ms hybrid matching on local CPU.

MCP server for NowSecure Platform mobile security testing. List applications, pull remediation findings via GraphQL, and generate PDF reports locally (bypasses broken UI export). Published as `nowsecure-mcp-server`. `npx -y nowsecure-mcp-server`

Start, observe, and interact with Claude Managed Agents from any MCP client — launch an agent, poll its events to watch it work, reply, approve the tools it wants to run, and stop it. Runs over stdio, an HTTP container, or AWS Lambda, with pluggable inbound auth (bearer/OIDC/Cognito).

MCP server for MDMA (interactive Markdown applications with mounted components). Exposes the MDMA spec, authoring prompts, package metadata, and live docs to AI assistants. Tools: `get-spec`, `get-prompt`, `build-system-prompt`, `validate-prompt`, `list-packages`, `list-docs`, `get-doc`. Install: `npx @mobile-reality/mdma-mcp`.

Provides up-to-date documentation context for a specific Rust crate to LLMs via an MCP tool, using semantic search (embeddings) and LLM summarization.

Prompt library MCP: versioned prompts, per-version model settings (reasoning, verbosity, and other API dials), text/image/JSON. Tracks edits and copy/download; refine proposes the next version. Hosted Streamable HTTP at https://mcp.getpromethic.com/v1

MCP server that provides SQL analysis, linting, and dialect conversion using [SQLGlot](https://github.com/tobymao/sqlglot)

Change tracking for AI-era codebases. AI agents call it to log structured change events (entity + diff + reasoning) before the session ends, then query history with diff, blame, history, changeset, and search. Captures the intent that would otherwise evaporate.

Hybrid search (vector + BM25 + code graph) with structural code graph analysis and persistent semantic memory in a single local server. 10 tools, <350MB RAM, fully local, no API keys.

Automatically generates Architecture Decision Records (ADRs) from Claude Code conversations using Claude Opus. Features AI quality review, duplicate detection, dependency graph, and stale ADR alerts.

An open-source observability layer for AI coding. Silently tracks dev tokens/time and auto-codifies AI deviations into persistent project rules.

Manage a 5dive agent fleet from any MCP client: file tasks, message and inspect agents, and read the fleet digest. Thin adapter over the 5dive CLI.

An implementation project of a JVM-based MCP (Model Context Protocol) server.

Codebeamer ALM integration for managing work items, trackers, and projects. Provides 17 tools for reading and writing items, associations, references, comments, and risk management data via Codebeamer REST API v3.

AI detection for text content with GPTZero API. Detect AI-generated text, get confidence scores, multilingual support (French/Spanish), and detailed probability breakdowns.

Lets AI agents explore elaborated SystemVerilog/Verilog designs (RTL or gate-level netlists) without pasting RTL into context: trace signal fan-in/fan-out, walk module hierarchy, and jump to exact `file:line` source, backed by the najaeda netlist engine.

An MCP server to flexibly fetch JSON, text, and HTML data

Answers "what did that command print?" from your real terminal history: a per-command PTY session recorder (OSC 133) stores every command's full output, exit code, cwd, and duration in local SQLite/FTS5, and the MCP server searches, retrieves, and diffs those outputs — secret redaction on by default before anything reaches the model.

Your Ionic coding buddy enabled via MCP – build awesome mobile apps using React/Angular/Vue or even Vanilla JS!

Unified MCP server for iOS development — build, run, screenshot, and interact with iOS Simulator.

Turn any OpenAPI spec into callable MCP tools for Claude. Point at any OpenAPI 3.x spec and Claude can call every endpoint through natural language. Supports Bearer, API key, and Basic auth.

A Model Context Protocol (MCP) server that queries multiple Ollama models and combines their responses, providing diverse AI perspectives on a single question.

AI code quality gate detecting hallucinated packages, phantom dependencies, stale APIs, and AI-specific code defects. MCP Server + CLI + CI/CD integration.

Zero-auth developer utilities: base64, UUID, hash, JWT decode, cron parse, timestamps, JSON, and regex.

A coding agent for Max (Max/MSP/Jitter), which is a visual programming language for music and multimedia.

Identifies resource-intensive processes on macOS and provides performance improvement suggestions.

TIBET provenance tracking for AI decisions. Cryptographic audit trails with ERIN/ERAAN/EROMHEEN/ERACHTER intent logging for compliance.

Manage AWS EC2, Hetzner, OVH and custom SSH servers: run commands, fetch logs, CloudWatch/CloudTrail queries, fleet health snapshots, IP banning, S3 — with readonly/standard/dangerous guard tiers and a JSONL audit trail.

Turnkey on-premise private Agentic AI systems by [ARADIA](https://aradia.com) on dedicated NVIDIA DGX hardware (Spark, Station, B200) with zero cloud data leakage. Operating since 1991, six tools cover hardware sizing (`query_hardware_specs`), CapEx token ROI payback modeling (`calculate_roi`), autonomous affiliate onboarding to earn 10% bounties (`onboard_partner`), and machine procurement via BTCPay Server (BTC/LN/USDT) or Stripe MPP Fiat (`execute_procurement_order`), plus `track_order_status` and `query_partner_stats`. Listed on the official MCP Registry (`com.aradia/sovereign-hardware`). Remote Streamable HTTP / SSE at `https://aradia.com/api/mcp` or `https://aradia.com/api/a2a/mcp-endpoint.php`.

Breaking-change diffs for npm packages so coding agents stop writing code against outdated API knowledge.

Hierarchical code intelligence for AI coding agents. Scans local source code, clusters files by behavioral roles, maps coupling seams, and provides in-repo twins/context for complex implementation tasks.

Demand-signal scanner for validating digital-product and dev-tool ideas: query GitHub repo signals, Hacker News attention, and npm/PyPI download counts through six stdio tools with TTL caching and backoff. Dependency-free, no API keys. Listed on the official MCP Registry (`io.github.baobabcat/demandscope`).

AI-powered architectural analysis server for software projects. Provides technology stack detection, ADR management, security checks, enhanced TDD workflow, and deployment readiness validation with support for multiple AI models.

Build smart-glasses apps with AI agents — scaffold, validate, and simulate Meta smart glasses integrations (camera capture, voice, audio) in Android and iOS apps. Runs locally via `npx -y @extentos/mcp-server`.

Extracts essential code structure from large codebases into AI-digestible format, helping AI agents write code that correctly uses existing APIs on the first attempt.

CI for [ink](https://github.com/inkle/ink) interactive-fiction stories. Compiles, exhaustively playtests every branch, and finds runtime errors (with a repro path), unreachable knots, and every distinct ending — so an agent can verify the story it wrote. Writes no prose. `claude mcp add inkcheck -- npx -y inkcheck mcp`

Drive full-screen terminal programs (vim, htop, lazygit) by reading the screen, not the byte stream: a live cell grid exposes which row is reverse-video selected, cursor position and alt-screen state, so waits are screen-state predicates instead of sleeps. The emulation is differentially tested against real tmux and GNU screen (cell-by-cell grid diffs plus a generative VT fuzz), which caught 12 emulation bugs including missing alternate-screen support. pip install smartcli-toolkit then smartcli-mcp, or uvx --from smartcli-toolkit smartcli-mcp.

npm intelligence — search packages, check bundle sizes, scan vulnerabilities, compare downloads.

MCP server for SSH-based control of remote Linux, macOS, and Windows servers with 46 purpose-built tools instead of one generic command-runner: line-level file editing (no download/edit/upload round-trip), background task launch/monitor/kill, real sudo support, host aliases, recursive directory ops, archive create/extract, and full Unicode via SFTP (avoids PowerShell OEM code page corruption on Windows targets). `pip install cygnus-ssh-mcp` or `uvx cygnus-ssh-mcp`.

Seamlessly Integrate Any API with AI Agents (with OpenAPI Schema)

MCP server for [quelllm.fr](https://quelllm.fr) — open-weights LLM catalog (250+ models with params, VRAM by quantization, tokens/sec, license). Tools: `list_models`, `get_model`, `compare`, `estimate_vram`, `estimate_cost` (API providers vs self-hosted hardware in EUR), `search_models`. Useful when picking a local model that fits your GPU/Mac.

Delegate real-world actions from Claude Code, Codex, or any MCP client to [Hermes Agent](https://hermes-agent.nousresearch.com/docs) — research, browser workflows, messaging, scheduling, and Hermes skills/tools — instead of reimplementing them in the coding agent. Conservative safety policy downgrades risky `execute` to `request-approval`; small surface (`hermes_run`, `hermes_plan`, `hermes_presets`, `hermes_status`). MIT.

Render and verify native Rust GUIs with no display or GPU: render to a typed accessibility tree, query/interact by semantic selector (never coordinates), check contrast/focus-order/hit-target-size, diff screenshots, and watch motion play as a captioned filmstrip. 13 tools. `cargo install fenestra-mcp`.

Creates a live webhook endpoint an agent can receive on, then reads the real deliveries back. The first call works without an account or a key, and the endpoint keeps working after the session ends.

Local, read-only retrieval over official Python standard library docs with exact symbol lookup, section-level results, and version-aware context.

Run commands on a machine you cannot SSH into. Publishes a step to a transport the far side already reaches (git, file share, S3-compatible storage, relay or a carried file); the whole run comes back as a log with every line timestamped in UTC, whether it passed or failed. For air-gapped, bastion-only and change-controlled estates: no tunnel, no proxy, nothing held open. The gates live on the far side, so a tool call can ask but cannot authorise. `heliograph mcp`.

Self-hosted webhook relay and tunnel with Noise NK encryption. 13 MCP tools to inspect requests, replay webhooks, trace AI pipelines, connect/disconnect tunnels, and manage subdomains. No tokens or passwords — the cryptographic handshake is the auth.

A council of 49 specialist agents + 93 tools for every major AI CLI (Claude Code, Codex, Gemini, Cursor, Windsurf). Deterministic agents that optionally upgrade to LLM, a self-learning router, cross-CLI memory, and guards for dependency hallucinations and decision drift. No API keys; zero extra cost on subscriptions.

🐍 🏠 – A fastAPI-based FastMCP server with a Vue frontend that sends uploaded images to VLM via the MCP to quickly extract handwritten mathematical formulas as clean LaTeX code.

Production-ready MCP server for AI-driven console automation and monitoring. 40 tools for session management, SSH, testing, monitoring, and background jobs. Like Playwright for terminal applications.

AI-native backend-as-a-service platform enabling AI agents to build and manage full-stack applications. Provides Auth, Database (PostgreSQL), Storage, and Functions as production-grade infrastructure, reducing MVP development time from weeks to hours.

Secure ADB-based MCP server for AI assistants (Claude, OpenCode, VS Code). Read-only logcat, UI hierarchy, package listing, and allowlisted shell commands. TypeScript/Node.js. Install: `npx @neem2004/android-mcp-server`.

56 semantic Java analysis tools via Eclipse JDT. Compiler-accurate navigation, refactoring, find references, call hierarchy, and code metrics for AI agents.

Search @imqueue docs and scaffold typed services & clients for AI coding agents, access CLI and manage your service fleet.

Local ledger for development ports: leases a block of ports to each working copy of a project (a clone or a git worktree), writes `.env` files, and resolves service names to URLs, so every parallel coding agent gets its own ports. No daemon and no network listener, so there is little to run and little to attack.

Cross-service API dependency graph for microservice codebases. Give it a business term or endpoint name; get back a ranked chain of GraphQL operations, REST endpoints, Kafka topics, and frontend queries across all services. Offline, local SQLite + TF-IDF + optional embeddings.

Billing infrastructure for MCP server operators. Add Stripe subscriptions, per-call credits, tiered pricing, and x402 crypto micropayments to any MCP server without writing billing code. Operator dashboard included.

Universal Maven Central dependency intelligence for JVM build tools (Maven, Gradle, SBT, Mill). Features bulk operations, version comparison, stability filtering, dependency age analysis, release patterns, and Context7 integration for upgrade guidance.

MCP server for the VerifyAX platform. Enables agent evaluation, simulation testing, and functional/non-functional verification workflows through natural language.

Native macOS markdown preview app with MCP server. Open and render Markdown files in MarkView directly from AI assistants via `npx mcp-server-markview`.

Control Google Colab notebooks and assign GPUs (T4/L4/A100) from any AI agent. Enhanced fork of Google's colab-mcp with all tools visible at startup, OAuth GPU control, and Windows support.

Durable control plane for long-running Codex Desktop tasks. Submit tasks asynchronously, poll operation/workflow state, approve Plan Mode, recover retries, and use hook-backed SQLite history for search and diagnostics.

AI council server: query CLI agents (Claude Code, Codex, Gemini, and OpenCode) in parallel with deliberation rounds

Search, extract sections, list headings, and find code blocks across markdown files.

Run GLM (Zhipu/Z.ai) as a real sub-agent inside Claude Code or GitHub Copilot. GLM gets its own agent loop (read/write/edit/run) on your repo — not a single LLM call — with peak-aware Opus-vs-GLM routing, diff/dry-run/git-revert oversight, and a usage ledger. ~10x cheaper than Opus. Requires a Z.ai GLM Coding Plan key.

Dynamic QR code service for AI agents. Create, update, track, and retarget QR codes without regenerating images. 37 tools covering 11 QR types, one-command install via `npx qr-for-agent`.

36 zero-auth developer utilities: MD5/SHA/bcrypt hashing, Base64/hex/URL encoding, UUID/password/passphrase generation, JWT decoding, JSON/YAML/XML formatting, timestamp conversion, CIDR calculator, and text tools.

Profile any MCP server into a reusable, read-only skill that captures how you actually use it — your workflows, the identifier hops that chain one call into the next, and each tool's safety class. Exploration runs behind a default-deny gate that provably never writes (a `SELECT` runs; a `DROP` on the same tool is refused by inspecting the statement). One static binary. `npx @ieranama/discomcp`

AI project intelligence MCP server. Tracks 300+ open-source AI projects across GitHub, PyPI, npm, HuggingFace, Docker Hub, and Hacker News. 47 MCP tools for discovery, comparison, trend analysis, and semantic search across AI repos, HuggingFace models/datasets, and public APIs.

Offline-core code & logic calculator for AI agents — run code in 31 languages, exact symbolic math, SMT/logic, complexity analysis, and cross-language/optimization verification, with an opt-in strict gVisor/AppContainer sandbox for untrusted code.

MCP server for Chrome Web Store extension management — 8 tools for upload, publish, status, staged rollout, and metadata updates.

Regression testing framework for AI agents. Save golden baselines, detect behavioral drift, and block regressions in CI. Works with LangGraph, CrewAI, OpenAI, Claude, and any HTTP API.

Screen-reader navigation cost analyzer. Models real AT user effort with per-profile scoring, graph-based pathfinding, and step-by-step navigation traces.

Connect any HTTP/REST API server using an Open API spec (v3)

📇 ☁️ 🏠 🐧 🍎 🪟 – Code-mode MCP server: collapses N user-defined tools into a two-tool surface (`execute_code` + `docs_search`). Backed by a unified capability manifest (`allowedHosts` / `cpuMs` / `memoryLimitBytes`) honoured across three sandbox kernels — in-process node:vm, WASM (QuickJS / Pyodide / Wasmtime), and remote microVM (E2B / Cloudflare Sandbox). Token-saving benchmark in repo CI.

iOS code quality analysis and test automation server. Provides comprehensive Xcode test execution, SwiftLint integration, and detailed failure analysis. Operates in both CLI and MCP server modes for direct developer usage and AI assistant integration.

MCP for BugBug API, to manage test and suites on BugBug

Atlassian Confluence Cloud integration. Enables AI systems to interact with Confluence spaces, pages, and content with automatic ADF to Markdown conversion.

A MCP server for interacting with [Go's Language Server Protocol (gopls)](https://github.com/golang/tools/tree/master/gopls) and benefit from advanced Go code analysis features.

The API-change deploy gate for AI coding agents: "is it safe to ship this API change to my consumers?" Analyze-only OpenAPI breaking-change detection + migration guides.

An MCP server for interacting with [Bugsnag](https://www.bugsnag.com/)

A semantic search engine for files and code — find files by describing what they do, not their names. Local reusable indexes, configurable embedding providers (OpenAI, Gemini, Voyage, any OpenAI-compatible API, or fully offline local models), AST-aware code chunking, optional reranking. `uvx vexor mcp` or `pip install vexor`.

Progressive code-intelligence MCP server: map project structure, fuzzy-find symbols, and assess change-impact across Python, JS/TS, and Go (powered by `ast-grep`).

A MCP server for replacing Rest Clients like Postman/Insomnia, by allowing your LLM to maintain and use api collections.

All-in-one 24-tool MCP runtime and 180-skill library providing protocol-level C4 workflow gates, hard-gated command execution with security guardrails, and cognitive reasoning engines (Tree of Thoughts DAG, Red-Team Grilling, 5-Whys Root Cause Tracer, Context Compactor, Self-Evolution) for coding agents across Antigravity, Cursor, Windsurf, Claude Code, and Codex.

In-loop design review of rendered UI for coding agents: submit a preview URL, get grounded findings with element references, then recheck the fix. Read-only by design — never edits code. OAuth 2.1 and SSRF-safe URL handling reference implementation. `npx -y @apatureai/bastion`

MCP server for AI prompt optimization — transforms vague prompts into platform-optimized prompts for 58+ AI platforms across 7 categories (image, video, voice, music, code, chat, document).

A zero-configuration Go library to automatically expose existing Gin web framework APIs as MCP tools.

Record Python/Rust/TypeScript program runs to local SQLite; query call trees, exceptions, and value flow over MCP (refuses rather than guesses). Local-first for coding agents — not LLM-prompt tracing; not the unrelated Telegram `sensorium-mcp`.

Intelligent token optimization achieving 95%+ reduction through caching, compression, and 80+ smart tools for API optimization, code analysis, and real-time monitoring.

PHP static analysis MCP server for architecture and maintainability. 11 tools exposing 60+ code quality metrics, problem detection, refactoring priorities, dependency graphs, git hotspots, test coverage, and impact analysis. Installable via Composer.

An MCP server for running code locally via Docker and supporting multiple programming languages.

Control Android devices with AI through MCP, enabling device control, debugging, system analysis, and UI automation with a comprehensive security framework.

MCP server that blocks AI coding agents from repeating mistakes — turns thumbs-up/down feedback into enforced pre-action gates via PreToolUse hooks. Install: `npx thumbgate`.

Queryable UniFi API documentation (Network, Protect, Site Manager, InnerSpace, Mobility, Carrier Fabric) — endpoint search, field-level schema drill-down, and code examples in curl/Go/Node.js/Python/Ansible. Read-only: serves scraped docs, never touches a controller.

Connects your TestDino testrun/testcase data to AI agents so you can review runs, debug failures, and manage manual test cases using natural language.

Lightweight MCP server to access any API using their OpenAPI specification. Supports OAuth2 and full JSON schema parameters and request body.

A Model Context Protocol (MCP) server that allows AI agents to generate secure smart contracts in multiples languages based on [OpenZeppelin Wizard templates](https://wizard.openzeppelin.com/).

MCP server for VibeKit. Lets an LLM in Claude Desktop, Cursor, or any MCP client build, deploy, and manage hosted apps and chat with each app's persistent server-side agent (every app gets its own agent and a live URL). Not to be confused with the unrelated `superagent-ai/vibekit` SDK.

MCP Server to do dynamic AI SOC Security Threat analysis for a Text2SQL AI Agent.

24-tool MCP server for Claude Code that catches vague prompts before they waste tokens. Includes 12-category prompt scorecards, session history search with LanceDB vectors, cross-service contract awareness, correction pattern learning, and cost estimation.

Full Figma control: create shapes, text, components, set styles, auto-layout, variables, export. 80+ tools.

Let your agent see the squiggles: any number of LSP servers from one YAML config — diagnostics, go-to-definition, rename — plus each server's custom powers, like expanding Rust macros or running govulncheck through gopls.

📇 🏠 – Agent-first programming language: agents produce JSON AST, the compiler validates, type-checks, effect-checks, verifies contracts via Z3/SMT, and compiles to WASM. 19 MCP tools for the full compile-and-execute loop.

📇 🏠 – A Node.js MCP server that spins up isolated Docker-based sandboxes for executing JavaScript snippets with on-the-fly npm dependency installation and clean teardown

Precise character-level string indexing for LLMs. Provides tools for finding, extracting, and manipulating text by exact character position to solve position-based operations.

Deterministic axe-core accessibility scanning (WCAG 2.1 AA, EN 301 549, PDF/UA) through a [wcagc](https://wcagc.com) account: scan any public URL or PDF, crawl a whole registered site, replay saved multi-step journeys, and read violation trends. Returns structured findings — rule, severity counts and the success criteria involved — so the assistant reasons over real results rather than guessing from markup. Every scan result carries an automated-coverage disclaimer instead of a score or a pass/fail verdict. Hosted at `https://mcp.wcagc.com/mcp`, or run it locally with `npx -y @wcagc/mcp`.

Convert source code repositories into searchable knowledge bases with AI-powered search using GPT-5, intelligent chunking, and OpenAI embeddings for semantic code understanding.

Local-first MCP safety and verification layer for AI coding agents with workspace confinement, command allowlists, scope-violation detection, and auditable task evidence. Install: `npx -y patchwarden@0.6.1`.

Multi-protocol API mock server with 18 MCP tools. Mock HTTP, GraphQL, gRPC, WebSocket, MQTT, SSE, and SOAP APIs with chaos engineering, stateful CRUD, 8 import formats (OpenAPI, Postman, HAR, WireMock, cURL, Mockoon, WSDL), and deterministic seeded responses.

MCP server that closes the feedback loop for AI coding agents — CI monitoring, process watching, file changes, HTTP polling.

The official MCP server for PNTR free dev subdomains — register a `*.pntr.dev` subdomain, manage its DNS records, receive email on a disposable inbox, and capture inbound HTTP requests for webhook debugging. Free tier, no key needed to start. Local stdio via `npx @pntr/cli` or hosted endpoint (`https://api.pntr.dev/mcp`, OAuth).

Universal persistent project context for Cursor, Windsurf, Cline, VS Code, and all MCP-compatible platforms (including Claude Desktop). IANA-registered format (application/vnd.faf+yaml). 17 native tools, AI-readiness scoring.

A sub-harness (both an MCP server and an MCP client). Delegates documentation and source code analysis, as well as interactions with related context-providing MCP servers, to a local or inexpensive OpenAI-compatible LLM. Drastically reduces token usage and context size for coding agents on the top-tier LLM. `uvx codebase-agent-mcp`

Local-first Project Telos MCP tool line for inspectable AI work: source intake, workspace context, routing ledgers, action receipts, and MATCH / DRIFT / UNVERIFIABLE verification packets across 5 stdio servers.

Swift code reviews, local Apple references and app scaffolding in one MCP connection. Bundled simulator tools require macOS/Xcode.

Code Intelligence for Elixir: module search, function tracking, and PR attribution through tree-sitter AST parsing

A DeepSeek MCP-like Server for Terminal

Read-only static scanner for MCP / agent-gateway production-readiness. The `scan_gateway` tool scores a repo across 7 security dimensions (RBAC, fail-closed, supply chain, observability, cost, secrets, prod-readiness). Never executes code or prints secret values.

🐍 ☁️ – A FastMCP-based server for interacting with webhook-test.com. Enables users to create, retrieve, and delete webhooks locally using Claude.

100% local semantic code search for AI agents: AST-aware chunking (tree-sitter), hybrid BM25+dense retrieval, and a code knowledge graph (callers, inheritance, imports) over codebases, docs sites, and PDFs. Install via `pipx install lynx-mcp`.

Generate engineer-grade SaaS specifications — design systems, database schemas, and RLS policies for AI build tools like Lovable, Cursor, and Claude Code.

Test, score, and inspect n8n workflows via MCP. Config-driven test suites with two-tier scoring, lightweight execution traces, and a built-in node catalog with 436+ nodes.

Exposes 100+ x402-paid APIs to AI agents via auto-discovery from Coinbase Bazaar. Handles USDC micropayments on Base mainnet.

Connect to JetBrains IDE

Connect to VSCode ide and use semantic tools like `find_usages`

Read-only view of a repository's CRAP scores, one per function: `ccn^2 * (1 - cov)^3 + ccn`, cyclomatic complexity joined to the branch coverage your own test command already writes. Twelve tools (`get_next_item`, `list_worklist`, `get_function_brief`, `get_function_history`, `check_gate`, `check_config`, `list_coupled_files`, `list_duplicate_functions`, `get_ratchet_report`, `get_trend`, `list_runs`, `list_claims`) hand the agent the worst function to fix next with its own source, its uncovered lines, its change-coupled files, its near-duplicates and a gate verdict on the edited file. None of the twelve runs a test suite or edits source files. Reads Python, TypeScript, JavaScript, Go, Rust, Swift, Java, C/C++ and more through lizard. `pip install crapkit`, then `crapkit mcp`.

MCP Server for Android/iOS application and device automation, development and app scraping. Simulator/Emulator/Physical devices like iPhone, Google Pixel, Samsung supported.

Index any TypeScript/React repo (including monorepos) into a queryable code graph. Reverse queries (who-renders, who-calls, find-references), blast-radius analysis, dependency cycles, dead-code orphans, and symbol signatures — exposed over stdio. Install: `npx code-graph-indexer`.

Fault injection + model-free reliability scorecard for MCP servers. Injects timeouts, malformed JSON-RPC, truncated & corrupted-but-valid outputs; grades `outputSchema` enforceability (31 servers, 265 tools — only 3% enforceable) + error conformance. `pip install mcp-drill[scan]` · `uvx mcp-drill scan -- npx -y @modelcontextprotocol/server-filesystem /tmp` · GitHub Action + badge. See [vs mcp-scan](https://timurrakhmatullin86.github.io/mcp-drill/vs-mcp-scan/).

Renders HTML in a headless browser and detects layout defects numerically (text overlap, element overflow, placeholder leftovers) without requiring baseline images. Read-only, no API key required.

Local-first MCP server for AI content governance — 13 tools for model/content CRUD, validation, normalization, and i18n across any framework.

Transform Claude Code with intelligent, real-time access to 90+ framework documentation sources. Get accurate, up-to-date code generation that follows current best practices for React, Next.js, Laravel, FastAPI, Tailwind CSS, and more.

Type-faithful calculator: evaluate expressions under fixed-point, IEEE-754 double, or exact rational arithmetic, with every answer labelled exact vs inexact. Tools: calculate, analyze, solver, help, info. Offline, no network. `uvx mcp-abacus`.

Give your AI assistant its own AI assistants. For example: "Could you ask openai to generate an image of a dog?"

Audits a domain email deliverability: SPF, DKIM, DMARC, MX, mail provider, DNS blacklist, catch-all, and domain age, returning a 0-100 health score via an Apify actor.

Enterprise-grade Jenkins CI/CD integration with multi-tier caching, pipeline monitoring, artifact management, and batch operations. Features 21 MCP tools for job management, build status tracking, and queue management with CSRF protection and 2FA support.

Git-backed message bus letting coding agents on different machines coordinate: rooms are folders, messages are files, git history is the log, and there is no server — the transport is a private git repository you already own. Questions, answers, decisions, collaborative tasks with claiming and recovery, and delegated repository reviews prepared in isolated worktrees at pinned revisions. Items marked `needs: human` cannot be answered by an agent, only relayed to a person.

Coding agent with basic list, read, replace_in_file, write, execute_command and web search tools. Supports multiple projects concurrently.

Structural analysis for any system — 12 deterministic graph tools (topology, bottlenecks, blast radius, trace, diff, centrality) from EN syntax descriptions. No AI inside the computation. Install: `npx @endiagram/mcp`

App Store Connect API server with 208 tools for managing apps, builds, TestFlight, subscriptions, reviews, and more — directly from any MCP client.

Zero-config CLI + MCP server that maps a .NET test-automation solution (Reqnroll/SpecFlow) into one queryable SQLite file, so coding agents can search existing step definitions, check change impact, and stop duplicating code. No build, no network, no AI. `dnx TestAtlas.Mcp`

MCP server that connects your IDE or AI assistant to Codex CLI for code analysis and editing with support for multiple models (gpt-5-codex, o3, codex-1)

MCP server + command line tool that allows agents to see & control long-running processes like web servers. Start, stop, restart, read logs.

High-performance, token-efficient spreadsheet analysis/editing (xlsx/xlsm) with region detection, structured reads, formula/style inspection, forking mechanics, and recalculation. Cross-platform.

Exposes a large catalog of coding assistant prompts as MCP tools with model-aware suggestions and persona activation to emulate agents like Cursor or Devin.

Weight-On-Wheels for AI - keeps agents grounded in your project's rules. Query coding standards, validate snippets, and get task-specific guidance from version-controlled rule files.

Unified MCP server for App Store Connect & Google Play Console — 91 tools for iOS/Android app management, TestFlight, builds, submissions, pricing, and sales reports.

MCP server providing task specific agentic instructions. No more outdated Markdown files and synchronisation overhead.

Full SSH access for AI agents with secret-safe environment injection and automatic output redaction. Persistent sessions, structured execution, SFTP, port forwarding — secrets are fed via stdin (invisible to `ps`) and scrubbed from all tool responses before reaching the LLM. `uvx mcp-remote-ssh`

Semantic code graph MCP server for AI coding agents. Indexes your codebase into a typed graph (functions/types/modules as nodes; CALLS/IMPORTS/DATAFLOW/EFFECTS as typed edges) and exposes 40+ tools for call-chain tracing, data-flow analysis, semantic search, and invariant checking — so agents navigate code structure instead of reading files line by line. `npm install -g grafema`

An MCP Server and VS Code Extension which enables (language agnostic) automatic debugging via breakpoints and expression evaluation.

Project-aware, read-only Nacos config & service-discovery server for Spring Cloud repos. Zero setup: auto-discovers every environment (dev/test/prod/...) from the repo's application/bootstrap files, with cross-environment key-level config diff. Single file, zero dependencies.

Atlassian Bitbucket Cloud integration. Enables AI systems to interact with repositories, pull requests, workspaces, and code in real time.

Containerized environments for coding agents. Multiple agents can work independently, isolated in fresh containers and git branches. No conflicts, many experiments. Full execution history, terminal access to agent environments, git workflow. Any agent/model/infra stack.

Apple-native execution layer for AI agents. Compiles TypeScript to validated Swift — App Intents, SwiftUI views, WidgetKit widgets, and full apps. 13 MCP tools, 150 diagnostics, 500 tests.

Shorten links, read click analytics, generate branded QR codes, and manage links on opn.onl — the open-source, self-hostable URL shortener. Works with the hosted service or your own instance.

A fully-featured coding agent that relies on symbolic code operations by using language servers.

Command line interface with secure execution and customizable security policies

Extracts component information from Storybook design systems. Provides HTML, styles, props, dependencies, theme tokens and component metadata for AI-powered design system analysis.

Autonomous testing for web apps — dispatch AI agents that open real browsers, execute test cases, and report pass/fail with screenshots. Generate user stories, test cases, and Playwright code from your app context. 8 tools for end-to-end test automation.

MCP server enabling automated access to **LeetCode**'s programming problems, solutions, submissions and public data with optional authentication for user-specific features (e.g., notes), supporting both `leetcode.com` (global) and `leetcode.cn` (China) sites.

Answers "why does this code exist?" by tracing any line back through the commit, GitHub PR description, and linked issues. Five tools: blame context, commit story, file history, commit search, and file contributors. `npx git-context-mcp`

Terminal MCP server for AI coding agents with persistent PTY sessions, ring-buffer incremental reads, headless xterm screen capture, multi-agent orchestration, and a real-time web dashboard.

Pharo Smalltalk integration enabling code evaluation, class/method introspection, package management, test execution, and project installation for interactive development with Pharo images.

Self-hostable GPU-aware job broker for your own machines. The MCP server exposes the queue as nine tools (submit, status, logs, list, cancel, preempt, workers, job-get, worker-delete) so an agent can dispatch long-running or GPU jobs that outlive the session, route them by VRAM tier, and babysit them across sessions. `pip install "jobd[mcp]"`.

MCP server that connects to [Apache Airflow](https://airflow.apache.org/) using official client.

An implementation of Claude Code capabilities using MCP, enabling AI code understanding, modification, and project analysis with comprehensive tool support.

Safe Python interpreter based on HF Smolagents `LocalPythonExecutor`

MCP server for API test case generation from Swagger/OpenAPI specs. Parses Swagger 2.0 and OpenAPI 3.x, generates test cases across 8 categories (happy path, validation, auth, error handling, boundary, security injection, idempotency, pagination/concurrency) with export to Markdown, Gherkin, Postman, k6, pytest, Allure, and TestRail.

MCP server that lets AI agents create and manage public tunnels to local services (webhooks, dev servers, sharing) — six tools covering HTTP/TCP/UDP tunnels, custom subdomains, regions, and load-balanced pools. Pairs with the rustunnel CLI; managed cloud or self-hosted (AGPL).

One MCP for all your integrations — powered by [Pica](https://www.picaos.com), the infrastructure for intelligent, collaborative agents.

Reusable prompt templates with multi-step workflow chains, quality gates, and reasoning frameworks. Compose workflows with an operator syntax (`>>prompt --> >>chain`), verify steps with blocking or advisory gates, and export prompts as native skills to Claude Code, Cursor, OpenCode, and Gemini CLI. `npx -y claude-prompts@latest`

MCP server for searching and getting up-to-date information about NPM, Cargo, PyPi, and NuGet packages.

A Model Context Protocol (MCP) server that provides AI-powered search and querying capabilities for the Vercel AI SDK documentation.

Agent-safe structured file edits for AI agents: JSON/YAML/TOML by selector, markdown, AST, dry-run, multi-file batch/tx. Not a generic filesystem MCP. `cargo install patchloom` / `npx -y patchloom mcp-server`.

lets your preferred AI agent create & run fully managed [Octomind](https://www.octomind.dev/) end-to-end tests from your codebase or other data sources like Jira, Slack or TestRail.

MCP server for Atlassian Jira and Confluence with schema-validated Markdown↔ADF conversion. Catches content-model violations at conversion time rather than silently dropping ADF-only nodes like panels, mentions, and layouts.

Reduced-motion / WCAG 2.2.2+2.3.3 verification for web animation: agents author validated specs; a deterministic compiler emits reduced-motion-safe, on-budget CSS. Keyless hosted endpoint (motion_catalog, motion_validate).

Eleven keyless read-only lookups for questions a model cannot answer from a training cutoff, because the fact changed after it: what a given AI model costs today, whether a dependency is still maintained, what a SaaS stack costs per month, item-level search across public shadcn registries, published agent skills and configs, AI app-builder App Store readiness, ADA Title II accessibility reports for US .gov sites, and nonprofit good-standing. No API key, no signup. `npx -y compound-mcp`

Pre-flight dependency-upgrade impact analysis: reports exactly which of your code's API usages break *before* you bump a dependency, with line numbers, severity, and fix hints. Also verifies AI-written code against the actually-installed API to catch hallucinated calls. Static analysis only — never runs third-party code. Python + .NET. `pip install bumpguard-mcp`

Eleven keyless read-only lookups for questions a model cannot answer from a training cutoff, because the fact changed after it: what a given AI model costs today, whether a dependency is still maintained, what a SaaS stack costs per month, item-level search across public shadcn registries, published agent skills and configs, AI app-builder App Store readiness, ADA Title II accessibility reports for US .gov sites, and nonprofit good-standing. No API key, no signup. `npx -y kynth-mcp`

Local CI/CD engine for AI agents: listens to [LGH](https://github.com/JoeGlenn1213/lgh) git events and runs plugin jobs (Go/Python/Java/web toolchains) in isolated checkouts, with structured results, AI failure diagnosis, approval gates, auto-rollback, a web console, and 22 MCP tools including one-call `dev_cycle_run` (commit → CI → verdict). `brew install JoeGlenn1213/tap/actiond`

Black-box flight recorder for RAG retrieval inside MCP agents. Logs chunks, scores, sources and rankings so you can audit, replay and diff retrieval runs.

Timezone-aware date and time operations with support for IANA timezones, timezone conversion, and Daylight Saving Time handling.

Production-ready MCP server starter templates in TypeScript and Python. Includes tool, resource, and prompt patterns with Claude Desktop integration configs.

An MCP Server to help LLMs suggest the latest stable package versions when writing code.

Provide coding agents direct access to Figma data to help them one-shot design implementation.

Sandboxed bash for agents. Run untrusted commands in WebAssembly sandboxes with no setup required.

🎖️ 📇 🏠 🍎 🪟 🐧 – Official MCP server for [UploadKit](https://uploadkit.dev). Gives AI assistants first-class knowledge of 40+ React upload components, Next.js route handler scaffolds, BYOS setup (S3/R2/GCS/B2), and full-text search across 88+ docs pages. Runs locally via `npx -y @uploadkitdev/mcp`.

Zero-config MCP server that gives AI coding assistants a real-time diagnostic snapshot of your local dev environment. Detects framework, running services, recent errors, and git state in one call.

An MCP server that enables AI models to search, retrieve, and solve LeetCode problems. Supports metadata filtering, user profiles, submissions, and contest data access.

The most complete API testing MCP — Postman inside your AI assistant. Per-project environment groups with {{variable}} interpolation, saved collections, multi-step flows with response extraction, assertions, load testing, and OpenAPI mock generation. 42 tools, zero cloud account needed.

One todo list and backlog every coding agent can write to (Claude Code, Codex, Cursor and any MCP host), filed per project from the git remote, with claims so two agents don't pick up the same item and a local web dashboard. Local-first, no account; optional self-hosting.

A framework for creating multi-agent systems using MCP for coordinated AI collaboration, featuring task management, shared context, and RAG capabilities.

15 semantic GDScript analysis tools via Godot's built-in LSP. Navigation, references, diagnostics, rename, and file sync for AI agents.

AI-powered Adaptive Card generation for Teams, Outlook, Copilot, and ChatGPT. 9 MCP tools for generating, validating, optimizing, templating, and transforming cards with accessibility scoring and host compatibility checks.

Local repo-intelligence index and MCP server for coding agents — "what a repository knows about itself." Hybrid BM25 + vector semantic search, a tree-sitter code graph (callers/callees/imports across Rust, TS/TSX, Kotlin, C/C++, Python) with an optional compiler-grade SCIP oracle, queryable git/GitHub history, and typed, source-anchored repo memories (Invariant, Decision, Risk, …) that persist across sessions. Every result carries provenance — confidence labels and coverage warnings. Keeps source read-only; a background watcher keeps queries fresh. PreToolUse hooks augment `grep` and flag near-duplicate code as you write it. `cargo install rag-rat`

Desktop GUI automation using accessibility APIs. Control Windows, macOS, and Linux applications without vision models or screenshots. Supports workflow recording, structured data extraction, and browser DOM inspection.

Read-only server exposing the agentic-os governance, SDLC, and QE methodology to any MCP host; never writes to your repo and never executes code. Ships install planning and install verification. `npx -y agentic-os-mcp`

Full-text search over your shell history (zsh / bash / fish) via SQLite FTS5. Local-only. 11-pattern secret redaction runs BEFORE insert. Captures cwd / exit code / duration via opt-in shell hook. Tools: `search_history`, `recent_in_dir`, `failed_commands`, `command_chains`, `reindex`.

Read and drive a self-hosted [Woodpecker CI](https://woodpecker-ci.org) instance: find the failed pipeline, read the failing step's log as text (the API returns base64 chunks), then restart, cancel or approve it, and manage secrets, registries, crons, agents and the server queue. 71 tools, or a curated eight via `WOODPECKER_ALLOW_TOOLS=essential`; irreversible operations need a confirmation token and agent tokens are redacted. `npx -y @ni-c/woodpecker-ci-mcp`

A Model Context Protocol (MCP) server for generating a beautiful interactive mindmap.

Code intelligence MCP server with 80+ tools for semantic code search, impact analysis, call graphs, ownership detection, and architectural understanding. Supports Go, TypeScript, Python, Rust, Java via SCIP indexing.

MCP Agent Health Reporter — advisory agent health scan under AOS discipline (manifest, services, immune loop, evidence). Stdio MCP: `mcp-agent-health`. Install: `pip install mcp-agent-health==0.3.1` · [PyPI](https://pypi.org/project/mcp-agent-health/0.3.1/)

Go-based MCP server for LynxPrompt prompt management. Create, search, and organize AI prompts and AGENTS.md/CLAUDE.md configuration files. Docker image available.

MCP server for [Dash](https://kapeli.com/dash), the macOS API documentation browser. Instant search over 200+ documentation sets.

Integrates, discovers, manages, and codifies cloud resources with [Firefly](https://firefly.ai).

EOQ-based context economics for coding agents. Monitors LLM token cache with inventory theory, signals optimal session restart timing via live dashboard and terminal statusline. Zero context pollution — no metric ever enters the model's context.

🍎 Build iOS Xcode workspace/project and feed back errors to llm.

Look up SDKs, frameworks, and dependencies used by 12,000+ macOS and Windows desktop apps. Search by technology adoption, compare stacks, and discover SDK usage patterns via the Desktop Insights API.

Multi-agent AI consultation framework for Claude Code. Three MCP servers wrapping CLI tools (Codex, Gemini, Qwen) for parallel code review and problem-solving with fallback chains and error detection. Includes ready-to-use Claude Code skill.

21-tool Android device control via ADB — screenshots with compression, UI tree inspection, touch automation, logcat, and compound actions like tap-and-wait. One-command install via `npx android-mcp-server`.

DevDocs-MCP is a MCP server that provides version-pinned, deterministic documentation sourced from [DevDocs.io](https://devdocs.io) in offline mode

Analyzes your codebase identifying important files based on dependency relationships. Generates diagrams and importance scores, helping AI assistants understand the codebase.

Agent Skill Ninja for MCP: Search, install, and manage AI agent skills (SKILL.md files) from GitHub repositories. Features workspace analysis for personalized recommendations and supports 140+ pre-indexed skills.

49-tool MCP server for AI control of Android devices and iOS simulators. AI visual analysis (Claude + Gemini), Flutter widget tree inspection, smart element finding (<1ms), video recording, and test script generation. `npx mobile-device-mcp`

Shared session bus for Claude Code, Codex, Cursor, Grok, and friends: MCP + CLI to list/read/handoff/send/spawn across live agent sessions. Install: `brew install abnegate/tap/magents`.

Huawei AppGallery Connect publishing: upload APK/AAB, update metadata and localizations, submit for review, and manage phased rollouts.

MCP server for authenticated REST API calls — auto-login, token caching, 2FA/OTP support, Swagger spec fetch, and fuzzy endpoint search. Works with any REST API without writing auth code.

🐍 🏠 ☁️ — Service-boundary-aware document exchange center for coordinating heterogeneous LLM code agents. Versioned Markdown store, pub-sub notifications, diff-aware updates, and lifecycle stage tracking. Each service registers as a sub-project; agents subscribe to cross-service document changes and receive structured diffs via MCP.

Docker operations — manage containers, images, volumes, networks, and compose services.

Offline access to TwitterAPI.io documentation for AI assistants. 52 API endpoints, guides, pricing info, and authentication docs.

Set up a WordPress site running the Sweipe or FlatMobile theme: import a demo, plan and build a site from a one-paragraph brief, review it, rewrite page copy, change core settings. Talks to the theme's REST surface with a WordPress Application Password.

Design contract layer for your codebase. Scans Figma, code, Storybook, and token files, reconciles conflicts, and serves a single machine-readable source of truth over MCP so every agent gets the same authoritative design rules before it builds. Local-first — your code never leaves your machine.

AI-powered task management system for AI-driven development. Features PRD parsing, task expansion, multi-provider support (Claude, OpenAI, Gemini, Perplexity, xAI), and selective tool loading for optimized context usage.

C++26 paper reference MCP (`cpp26-ref`) backing a Claude Code plugin: `lookup_paper`, fuzzy `search`, `compiler_status` over a 216-paper ISO/IEC 14882:2026 corpus. The plugin's skill + reviewer subagent use these tools to bias Claude toward reflection, contracts, `std::execution` senders, `#embed`, expansion statements — even when the local compiler lags. 95% on a held 39-task eval gate.

A script workflow management system that transforms complex, repetitive AI interactions into persistent, executable scripts. Supports multi-language execution (Bash, Python, Node.js, TypeScript) with guaranteed consistency and reduced hallucination risks.

A Mermaid diagram rendering MCP server for Claude Code with live reload functionality, supporting multiple export formats (SVG, PNG, PDF) and themes.

Visual DOM element selector for agentic coding tools. Chrome extension + MCP server bridge for Claude Code, Cursor, Windsurf etc. Option+Click to capture elements.

Interact with [Postman API](https://www.postman.com/postman/postman-public-workspace/)

**Log-stream tools for on-call / SRE agent workflows** — expose `rlg` (RustLogs) log files as MCP tools. Three tools: `tail_log` (last N events, filtered by level/target), `filter_log` (JSON-path-style predicates), `summarize_errors` (grouped error taxonomy). Speaks JSON-RPC 2.0 over stdio; near-lock-free structured logging engine underneath (65k-slot ring buffer, 14 output formats, `os_log`/`journald` sinks). Install `cargo install rlg-mcp` or `docker run -i ghcr.io/sebastienrousseau/rlg-mcp`. Dual-licensed MIT OR Apache-2.0.

Token-slimming AST code outliner, log compressor, and context budget analyzer cutting LLM context bills by up to 85%.

MCP server for the incident management platform [Rootly](https://rootly.com/).

Keyless local MCP server bringing ISTQB / OWASP / IEEE / ISO / EU AI Act QA standards into your AI client: standards-grounded retrieval, deterministic QA effort estimation, and automated QA document quality review (0-100 rubric) plus JUnit/CSV test-results flakiness analysis. `uvx qai-consultant-mcp`

AI-native CMS with 72 MCP tools for managing websites through natural language. Create and publish content, manage templates, assets, snippets, themes, collections, redirects, and multi-site forks — with full content versioning and semantic search.

Deep code indexing MCP server with SQLite FTS5, tree-sitter, and embeddings. 29 tools for symbol search, call graphs, git intelligence, and hybrid semantic search.

Local MCP server that shows AI agents which patterns your team actually uses, what files a change will affect, and when there is not enough context to trust an edit. 30+ languages, fully local.

Local MCP process broker that exposes one compact client entry while routing to many configured upstream MCP servers with profile gates, lifecycle ownership, and mutating-tool allowlists.

Run any command with `run_command` and `run_script` tools.

Publish HTML as live, shareable web pages from your AI coding agent. Instant URLs with access control (public, password-protected, email-restricted).

A lightweight MCP server for structured bug-fix analysis and project-local verified fix memory for AI agents.

An MCP server providing curated Swift and SwiftUI best practices from leading iOS developers, including patterns and real-world code examples from Swift by Sundell, SwiftLee, and other trusted sources.

A secure shell command execution server implementing the Model Context Protocol (MCP)

Free privacy-first URL shortener API with analytics and link management. No API key required.

Secure host-level telemetry gateway enabling sandboxed AI agents to dynamically fetch container logs and track kernel resource metrics.

Renders your frontend with Playwright and audits spacing, gaps, and element sizes against a design scale; returns structured fix hints for the agent loop. Tailwind-first, falls back to accessibility checks on other stacks.

The Underground Cultural District MCP server. 23 tools for AI agents: 13 free developer utilities (UUID, JSON formatter, Base64, hashing, JWT decoder, regex, cron, ETH converter), 7 paid creative tools, and a browsable marketplace of 218+ digital goods across 22 shops. npm: `@underground-cultural-district/mcp-server`

The IDE for agents: read code by symbol, edit against a known revision with compiler diagnostics in the response, validate with the project's own build and tests, and revert to a checkpoint. Tree-sitter plus real language servers for Go, Java, Scala, TypeScript, Python, Rust and Ruby. Official MCP Registry: `io.github.julianbei/jade`. `curl -fsSL https://raw.githubusercontent.com/julianbei/jade/main/install.sh | sh`

Run Python code in a secure sandbox via MCP tool calls

Code-quality gate for Bazel monorepos: runs lint, coverage and architecture checks off the build graph and returns a pass/fail verdict an agent can request before finishing a change.

Inspect, manage, and kill local dev servers. Lists what's listening on each port (pid, framework, project, uptime, memory, cpu), diagnoses port conflicts with free alternatives nearby, finds zombie processes, and kills by pid or port with a dry-run default.

Swiss-army-knife utility server for AI agents. 18 tools including JSON validation, base64, hashing, UUID generation, regex testing, markdown conversion, datetime conversion, cron parsing, CSV/JSON conversion, JWT decoding, and more. Streamable HTTP MCP + REST API with x402 micropayments.

MCP for semantic code search & navigation that reduces token waste

[gitmcp.io](https://gitmcp.io/) is a generic remote MCP server to connect to ANY [GitHub](https://www.github.com) repository or project for documentation

Justfile integration that enables LLMs to execute any CLI or script commands with parameters safely and easily, with environment variable support and comprehensive testing.

🐍 🏠 – A Python Runtime Interpreter MCP Server that executes user-submitted code in an isolated environment.

Deploy and operate multi-user web apps from an agent: one call returns a live app on its own URL with magic-link sign-in, a shared realtime database, per-role permissions, email notifications and file uploads, and the agent keeps read and write access to the app's data afterwards to keep changing it. Remote `https://homespun.dev/mcp` or `npx -y @homespunapps/mcp`.

Manage test cases in TestCollab directly from your AI coding assistant. List, create, and update test cases with filtering, sorting, and pagination support.

MCP server for cryptocurrency tipping through AI interfaces using x402 payment protocol and CDP Wallet.

SSH & Kubernetes access broker where the model never touches a credential: a separate signer mints per-operation ephemeral SSH certificates and bound ServiceAccount tokens, with a per-command allow/deny/approval firewall (POSIX-sh AST), dry-run, human-in-the-loop approvals, session recording and an Ed25519-chained audit log. Self-hosted Go binaries, GPLv3.

Apple Documentation MCP Server. Search Apple developer docs, Swift Evolution proposals, and 600+ sample code projects with full-text search.

Official MCP server for CodeLogic, providing access to code dependency analytics, architectural risk analysis, and impact assessment tools.

Web Validator by DigestSEO validates HTML and CSS, audits technical SEO and accessibility signals, checks JSON-LD and bounded public links, and captures responsive screenshots. Install locally with `npx -y mcp-web-validator`; no API keys required.

A single-binary MCP server that converts source code into AST, regardless of language.

Local-first task bus for CLI-based AI agents. Route work, persist state in SQLite, and let Codex, Claude Code, and other agents collaborate through a shared MCP server.

Grounding / hallucination guard: verify a claim against evidence (Supported/Refuted/Not Enough Evidence) with a confidence + abstain flag, for RAG and agents. `npx -y eleata-verify-mcp`.

AI-powered developer assistant that enables advanced research, analysis and discovery across GitHub and NPM realms in realtime.

Unified MCP server for GitLab and Jira: manage projects, merge requests, files, releases and tickets with AI agents.

A zero-cost MCP server that forces AI to self-correct generation messages using prompt injection, independent self-audition and context isolation.

Comprehensive DevOps and networking MCP server providing standardized access to essential infrastructure tools. Features network monitoring, system diagnostics, automation workflows, and infrastructure management with AI-powered operational insights.

Structured `.aide` spec files that give AI agents progressive disclosure into your codebase architecture via MCP.

Local-first stdio MCP server and Agent Skill for TraeCN desktop automation on macOS, exposing exactly 20 focused tools through a durable local gateway.

Local-first live context engine and MCP server. Pre-resolves git, services, tests, and memory into a ready context briefing at session start (compile-before-context). MIT, PyPI: perseus-ctx.

Connect Claude Code with E2B cloud sandboxes — 29 tools for creating isolated Linux VMs, cloning repos, running commands, managing files, and performing git operations without touching the local machine.

MCP server for Apple's Icon Composer: programmatically create .icon bundles with Liquid Glass effects (iOS 26+). 12 tools for icon creation, glass effect tuning, dark mode appearances, and App Store export.

Web scraping — extract clean markdown, links, and metadata from any URL. Free Firecrawl alternative.

A MCP server to interact with Neovim

23-in-1 developer utility MCP server: web search, exchange rates, crypto prices, QR codes, JSON formatter, UUID, URL tools, domain check, RSS feeds, and more. 6 paid APIs via x402 micropayments ($0.003 USDC on Base). `npx myclaw-toolkit`

Implementation of HTTP 402 (payment required http code) relying on Solana

Deterministic documentation-drift detection for AI agents. Validates a project's canonical docs against its actual code — no LLM guessing; every finding has a stable code and a suggested fix. Five read-only tools over stdio: guard, score, explain, verify-claims, diagnose. `npx -y docguard-cli mcp`

An MCP server (and command-line tool) to provide a dynamic map of chat-related files from the repository with their function prototypes and related files in order of relevance. Based on the "Repo Map" functionality in Aider.chat

MCP server for microservices.sh: inspect verified Cloudflare-native modules/templates, generate app plans/projects, run checks, and trigger confirmation-gated preview deploys. Install via `npx -y @microservices-sh/mcp`.

📇 🏠 🍎 A MCP server implementation for iOS Simulator control.

Capstone of the Grand Line MCP set: a "collect them all" server that unlocks once the other tools are installed. `pip install laugh-tale-mcp`

Behavioral verification intelligence for autonomous coding agents. Builds a behavioral graph of any TS/JS repo, clusters into 25 semantic workflows (Auth, Payments, Webhooks, Caching, Queue, etc.), detects drift, generates concrete adversarial probes (idempotency, retry storm, cache stampede, replay), emits per-workflow risk + confidence. 17 MCP tools. Local SQLite state. Zero cloud. MIT.

A MCP server for interacting with [Bruno API Client](https://www.usebruno.com/).

Universal tmux driver: sessions, windows, panes, keystrokes, and pane capture — local or remote over SSH. Curated tools plus a raw `tmux_command` passthrough; works against tmux 1.8+. Shared, visible sessions for pair-programming with the agent. `uvx mcp-tmux`.

Official MCP Server for [OpsLevel](https://www.opslevel.com)

What Chrome DevTools MCP is for the browser, tui-mcp is for the terminal. Launch, screenshot, and interact with any TUI app.

CLI-first API testing tool with structured JSON failures (`failure_category`, `error_code`, `hints`) so AI agents can branch on the taxonomy without parsing stderr. MCP tools: `tarn_run`, `tarn_validate`, `tarn_fix_plan`, `tarn_inspect`, `tarn_rerun_failed`, and more. Tests are `.tarn.yaml`. Single static binary (musl), MIT.

LLM-based code review MCP server with AST-powered smart context extraction. Supports Claude, GPT, Gemini, and 20+ models via OpenRouter.

Agency-grade MCP server for WordPress Elementor — multi-site management for 120+ WordPress sites with safe edits (backup + auto-rollback + post-write verification), template export/import, global widget detection, CSS flush, WP-CLI escape hatch, headless Chrome screenshots. 34 tools across pages, widgets, templates, bulk find/replace, and fleet operations.

The merge gate for AI-written code: deterministic checks veto placeholder/mock implementations, tests that cannot fail and unsupported "it's done" claims, then a model review checks for calls to APIs that do not exist, grades what remains and returns a fix plan. Remote server, no signup needed to start.

Local code-graph engine for AI coding workflows: static analysis of Rust, Cangjie, ArkTS, TypeScript/JavaScript, C/C++, Python, and Shell projects into symbols, imports, call graphs, and quality gates, with pre-commit change review, impact analysis, and a 6-tool AI facade (50 tools in full mode). Read-only by design — never executes build scripts or uploads code. Install from release tarball or build from source.

Universal deployment tracker for AI assistants with live status badges and deployment monitoring

Translates design tokens between platforms — extract from Tailwind, CSS, Figma, or W3C DTCG, then generate Material 3 (Kotlin), SwiftUI, Tailwind config, and CSS Variables with WCAG contrast validation.

Translates a lockfile diff (npm, PyPI) into a human-readable upgrade plan. Point it at a Dependabot PR and get back semver classification, breaking changes from GitHub release notes, CVEs fixed in range, migration links, and a per-package recommendation. Bulk tool ranks up to 50 changes by risk (security > caution > review > likely-safe > safe). Install via `npx -y @digicatalyst/dep-diff-mcp`.

Structural memory for coding agents. Indexes TypeScript/JavaScript repos and exposes callers, callees, blast-radius impact, and symbol locations over MCP — with file:line@sha evidence anchors and branch-aware differential impact — so agents answer "who calls X?" / "what breaks if I change X?" without re-reading files. Local-only, zero telemetry, Apache-2.0. `npx @graphpilot-oss/graphpilot mcp`

📇 🏠 – Offline Garmin Connect IQ SDK documentation with comprehensive search and API examples

iOS leak hunting and performance investigation. Reads `.memgraph` (`leaks(1)`) and `.trace` (`xctrace`) files, classifies retain cycles against a 34-pattern catalog (SwiftUI, Combine, Swift Concurrency, UIKit, Core Animation, Core Data, SwiftData, RxSwift, Realm), surfaces a Swift `fixTemplate` snippet for each match, and bridges to source via SourceKit-LSP. Single-call build+boot+launch fixes the macOS 26.x `leaks --outputGraph` regression; `replayScenario` + `captureScenarioState` close the verify-fix loop. 31 MCP tools, 34 catalog resources, 5 investigation prompts. CI-gateable via `verifyFix` and `compareTracesByPattern`. Apache 2.0.

Structural code context server for AI agents — compressed symbol indexes, dependency graphs, and git diffs via TypeScript AST analysis. Zero external dependencies, no vector database or embedding API required.

Flag features directly from chat in your IDE with [Reflag](https://reflag.com).

App Store Connect control plane: 41 job-shaped tools that edit version metadata (with Apple's character limits validated), upload screenshots, build/sign/upload the binary, drive TestFlight, create IAPs and subscriptions with territory availability, run a release preflight audit, submit and release. Flags the steps Apple only allows on its website (privacy label, EU trader, first IAPs) instead of failing on them. Six tools need no license, three of those no Apple credentials either.

Deterministic validation of AI-generated artifacts before acting on them: JSON Schema conformance, OpenAPI response conformance, SQL syntax per dialect. Typed verdicts with per-error fix hints. Hosted free tier with remote MCP endpoint; MIT, self-hostable.

Comprehensive developer tools for file editing, shell command execution, and screen capture capabilities

Self-evolving MCP server that generates and improves its own tools at runtime. Built on FastMCP, Janee uses LLM-driven tool generation to dynamically create, test, and refine MCP tools from natural language descriptions — enabling AI agents to extend their own capabilities on the fly.

MCP server for ROS2 enabling AI-driven robotics applications and services.

Playwright for the entire OS. Gives AI agents the ability to see, find, and interact with UI elements in any desktop application.

A JetBrains IDE plugin that exposes an MCP server, enabling AI coding assistants to leverage the IDE's indexing and refactoring capabilities (rename, safe delete, find references, call hierarchy, type hierarchy, diagnostics and more).

Atlassian Jira Cloud integration. Enables AI systems to interact with Jira projects, issues, comments, and related development information in real time.

Prose linter + AI-slop detector: weasel words, passive voice, hedging, and 190+ research-cited AI tells. Remote server at wsc.theserverless.dev/mcp or `npx wsc-mcp`.