ref-tools-mcp

MCP serverSearch

Lets your coding agent search public and private documentation quickly.

Available today. Use it from your connected AI after setup.

Add ahel to your AI once: Claude, ChatGPT, Cursor, Claude Code or Codex. Then ask it to use this.

Then ask your AI: use ref-tools-mcp

About this server

Token-efficient search for coding agents over public and private documentation.

Install ref-tools-mcp

The server’s own address, for the clients that take one directly. Or connect ahel onceand every client you use reads it from one address, with the account kept on ahel rather than in each client’s config.

  • Claude Code

    claude mcp add --transport http --scope user ref-tools-mcp 'https://api.ref.tools/mcp'

    Run it once in your project, then open /mcp to approve any sign-in the server asks for.

  • Claude Desktop

    https://api.ref.tools/mcp

    Add a custom connector in Settings, paste this address, and approve the sign-in.

  • Cursor

    cursor://anysphere.cursor-deeplink/mcp/install?name=ref-tools-mcp&config=eyJ1cmwiOiJodHRwczovL2FwaS5yZWYudG9vbHMvbWNwIn0=

    Open the link and Cursor adds the server at that address.

  • ChatGPT

    https://api.ref.tools/mcp

    In Settings, enable Developer mode, create an MCP app, and paste this address. Your plan and workspace must allow custom apps.

  • Codex

    codex mcp add ref-tools-mcp --url 'https://api.ref.tools/mcp'

    Run it once, then sign in with codex mcp login ref-tools-mcp if the server asks for an account.

From the project's README

As published by ref-tools/ref-tools-mcp in README.md. This repository publishes several servers, so only the opening is shown here.

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.

For more see info ref.tools

Agentic search for exactly the right context

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.

For a simple query about Figma's Comment REST API it will make a couple calls to get exactly what it needs:

SEARCH 'Figma API post comment endpoint documentation' (54 tokens)
READ https://www.figma.com/developers/api#post-comments-endpoint (385 tokens)

Shortened here. Read the whole README on GitHub.

Signals

GitHub stars
1k
Forks
70
Last commit
Sep 2026
Advanced
Delivery
ref-tools-mcp MCP server → your ahel connector (mcp.ahel.ai) → your AI.
Item type
mcp-server
Key
tools-ref-ref-tools-mcp
Source
github.com/ref-tools/ref-tools-mcp
Hosted endpoint
https://api.ref.tools/mcp