Ref
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.
Ads
Overview
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.
Capabilities
- ref_search_documentation
Search for technical documentation — Ask your agent to find facts, code snippets, or API references across public docs, GitHub, or private resources using `ref_search_documentation`.
- ref_read_url
Read and convert any documentation page — Have your agent fetch a URL and get back clean markdown of the most relevant sections with `ref_read_url`.
- Refine searches without repeating results
The server automatically filters out previously seen results when you refine or repeat similar queries in the same session.
- Get token-efficient context
Relevant page sections are surfaced while less relevant parts are dropped, keeping context under 5k tokens per read.
Installation
npm install
Configuration
{
"mcpServers": {
"ref-tools-mcp": {
"command": "npx",
"args": [
"-y",
"io.github.ref-tools/ref-tools-mcp"
]
}
}
}Paste into ~/.cursor/mcp.json or .cursor/mcp.json
Tags
- documentation
- document
- development
Related MCP servers
Code Execution
Context7 MCP
LLMs rely on outdated or generic information about the libraries you use. You get: - ❌ Code examples are outdated and based on year-old training data - ❌ Hallucinated APIs that don't even exist - ❌ Generic answers for old package versions Context7 pulls up-to-date,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
Code Execution
Chrome DevTools MCP
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
Code Execution
Mastra/mcp
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
Code Execution
GitHub MCP Server
Connect your AI assistant to GitHub repositories, issues, pull requests, and search.
4 tools · create_issue, get_pull_request
Code Execution
Kubeshark
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
Code Execution
AWS Nova Canvas
Generate images using Amazon Nova Canvas with text prompts and color guidance.
Code Execution
Lingo.dev
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
Code Execution
Google MCP Servers
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