MCP server directory

Terminal, filesystem, and background-job tools for Claude Desktop on Linux/macOS. Zero npm deps, pure Node.

Connect any bitcoin lightning wallet to your agent to send and receive instant payments globally.

Access the time in any timezone and get the current local time

Human-in-the-loop approval inbox for AI agents. An agent submits a proposed action (send email, post comment, run a command) via `impri_push_action`, a human approves, rejects, or edits it from a web, mobile, or Slack/Discord/Telegram inbox, and the agent only proceeds on an approved decision. The gate is a data dependency, not a prompt. Full audit trail, self-hostable (MIT, Docker Compose). `npx @impri/mcp`

Email inbox API MCP server for AI agents to receive, search, and send mail through hosted or local Sendmux Product MCP.

The TikTok MCP integrates TikTok access into Claude AI and other apps via TikNeuron.

Word search generator, crossword generator, and sudoku generator + solver in one local-first puzzle generator CLI — with printable PDF worksheets, starter word banks, verifiable LLM evals, and bundled agent skills. From the makers of puzzletide.com. Ask a language model to write a word search and you get a grid where half the words are broken; ask it for a sudoku and you usually get one with several solutions, or none. Grids are exactly the kind of output LLMs are bad at and deterministic code is good at.

6 tools · eval_generate, puzzle_crossword_generate

Check real-time operational status of 114+ cloud services and APIs (AWS, GitHub, Stripe, OpenAI, Vercel, etc.) directly from AI assistants. Published on npm.

Security MCP for vibe coding with 330 rules and 29 tools. Purpose-built for AI-generated code — scans Next.js, Supabase, Clerk, Stripe, Prisma, Hono, GraphQL, and 25+ modules. Cross-file taint analysis, host security audit, auto-fix, SARIF export, pre-commit hook, and CVE version detection. Zero config, runs locally.

AI agent marketplace with x402 micropayments. Discover, execute, and pay agents per-request via MCP with USDC on Base.

Accurate astronomical catalog data and observing session planner. 13,000+ deep-sky objects from OpenNGC with deterministic visibility, rise/transit/set, and alt/az calculations. `npx astronomy-oracle`

A Rust-based MCP server bridging Wazuh SIEM with AI assistants, providing real-time security alerts and event data for enhanced contextual understanding.

Unified GPU inference API with 30 AI services (LLM, image gen, video, TTS, whisper, embeddings, reranking, OCR) as MCP tools. Pay-per-use via x402 USDC or API key credits.

Teamfight Tactics champion, trait, item, and augment reference. 8 tools with full Set 16 data from CommunityDragon, including synergy lookups, item recipes, and rolling odds.

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.

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.

Institutional-grade crypto and US equity orderflow engine for real-time liquidity analysis and institutional alpha.

A universal MCP aggregator toolkit that connects AI agents to multiple MCP servers through a single unified configuration. Features ready-made templates, cross-repo prompt workflows, and an npm package for zero-config installation.universal MCP aggregator toolkit that connects AI agents to multiple MCP servers through a single unified configuration. Features ready-made templates, cross-repo prompt workflows, and an npm package for zero-config installation.

[Dida365](https://dida365.com/) (TickTick China) MCP server for AI-powered task management. 13 tools for projects, tasks, tags, and habits with OAuth 2.0 authentication. Compatible with OpenClaw, Claude Desktop, and any MCP client.

China's apparel supply chain data for AI agents. 1,000+ verified suppliers, 350+ lab-tested fabrics, 170+ industrial clusters with AATCC / ISO / GB lab-test verification.

Design-debugging context for AI agents from a real Chrome: which CSS rule WINS with file:line, blast radius (how many other elements that rule styles) + a scoped-fix selector, WordPress/Elementor origin attribution, interaction timelines, live CSS fix trials, and pixel/alignment/WCAG-contrast audits. No AI inside — deterministic CDP.

A ledger-cli integration for managing financial transactions and generating reports.

Generate diagrams from structured JSON across 18 types (architecture, ERD, sequence, flowchart, Gantt…) — native SVG/PNG, no headless browser. Built for LLMs and agents.

Official MCP client for Buildable - AI-powered development platform that makes any project buildable This package enables AI assistants (Claude, GPT, etc.) to work directly with Buildable projects using the Model Context Protocol (MCP). AI assistants can get project context, manage tasks, track progress, and communicate with human developers. Buildable (bldbl.dev) is an AI-powered development platform that makes any project buildable. It provides: - AI-Generated Build Plans: Comprehensive project roadmaps with implementation details - Smart Task Management: Automated task breakdown with dependencies and priorities - AI Assistant Integration: Direct integration with Claude, GPT, and other AI assistants - Real-time Collaboration: Seamless human-AI collaboration on complex projects - Progress Tracking: Live monitoring of development progress and blockers

6 tools · complete_task, create_discussion

Markdown-first Notion MCP server with 9 composite tools and 39 actions. ~77% token reduction via tiered docs. Auto-pagination and bulk operations.

One local gateway and manager for all your MCP servers, shared across every AI coding tool (Claude, Cursor, VS Code, Codex, and more). Set up and authenticate each server once; lazy discovery keeps each agent's context small, and keys stay in your OS keychain. No Docker, no cloud.

Multichain memecoin launchpad across 8 chains (Base, Arb, OP, Polygon, BSC, ETH, Avax, Solana). Tokenize yourself as an oMeme — earn 0.5% creator fee forever + 50% Uniswap V3 LP fees after graduation, from a single LP. $69 bounties. First 100 agents FREE for 60 days. 8 tools: trending tokens, search, quotes, bonding curves, trade simulation, chain info.

WhatsApp notifications for AI agents with zero setup — no Meta account, no templates, no dashboard: text "join", get an API key, send in 60 seconds (`uvx pingwa mcp` or remote at pingwa.dev/mcp). Two-way: `ask` with tap-to-answer buttons, `check_replies`. Official Meta Cloud API — won't ban your number.

Full Easypanel control from Claude Code and Cursor — 37 tools for deployments, services, env vars, logs, domains, databases and monitoring. Safety guards require explicit confirmation for all destructive actions.

An integration that allows LLMs to interact with Raindrop.io bookmarks using the Model Context Protocol (MCP).

Git-first memory for AI agents: Markdown files are truth, the index is disposable, and writes are reviewable commits. Ships 7 MCP tools (hybrid search, read_note, build_context, resolve, think, list_folders, and a scope-gated commit_note write) over a Streamable HTTP endpoint, plus a CLI and a read-only Obsidian companion.

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.

> Connect LLM clients and AI agents to HasData via the Model Context Protocol. The HasData MCP Server exposes HasData's scraping and search capabilities to any client that speaks the Model Context Protocol. Point your MCP-enabled client (Claude, Codex, Cursor, VS Code, Windsurf, custom agents, etc.) at the HasData endpoint and your model can scrape web pages, run Google searches, and pull structured data without writing API integration code. The server uses the streamable HTTP transport. Two ways to connect: sign in with your HasData account, or send an API key.

5 tools · amazon_product, apis

AI agent security scanner. Audits MCP servers for vulnerabilities, detects prompt injection, infinite loops, token bombing, and missing human oversight across 20+ frameworks. Maps findings to EU AI Act, OWASP LLM Top 10.