Ref Tools Mcp

tools.refPublished by ref.toolsOfficial publisherv3.0.1Updated Oct 24, 2026

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

VerifiedStreamable HTTPWeb executableWeb Search & ScrapingKnowledge & MemoryDeveloper Tools

Overview

AI-generated overview

Remote MCP server that gives coding agents token-efficient search and reading of public and private technical documentation.

What you can do
  • Search technical documentation across public web, GitHub, private repos and PDFs using full-sentence queries
  • Read a documentation URL and convert it to markdown, trimmed to the sections most relevant to the session's searches
  • Avoid repeated results across similar searches in the same session
  • Expose the same capabilities under alternate tool names for OpenAI deep research clients
When to use it
Useful when a coding agent needs current API, library or service documentation and you want to keep context small instead of pulling whole pages. Suited to agents that search and then read a few sources in depth.
Requirements
A remote endpoint at api.ref.tools over streamable HTTP, or the legacy local stdio package run with npx. Requires an API key, supplied either as the X-Ref-Api-Key header or as a query parameter in the endpoint URL; the legacy stdio setup uses the REF_API_KEY environment variable. OAuth is declared as required authentication.
Before you install
An API key is required and, in the documented HTTP setup, is placed in the endpoint URL, so treat that URL as a secret. Searches and page reads are sent to a third-party service, and private repositories or PDFs you search are shared with it. The README notes token costs of documentation context, so usage may be billed.

Installation

In SourceWeft

  1. Open Ref Tools Mcp in the dashboard and add it to a workspace.
  2. Connect the required credentials. They are stored privately and never shown on public pages.
  3. Enable the server for the chats that should use its tools.

Web executable via Streamable HTTP. Remote servers run from the web runtime once configured in a workspace.

Use with an agent

Paste this prompt into Claude Code, Codex, Cursor or another agent — or into SourceWeft chat. The agent reads this server's install guide, shows you its publisher, endpoint and sign-in, and adds it to your client once you agree. Keys never go into a command.

Read https://sourceweft.com/mcp/tools.ref%2Fref-tools-mcp/install.md and connect the MCP server it describes to my client. Before changing any config, show me its publisher, endpoint and sign-in method and wait for my OK. Never put an API key in a command or in a file I would commit; ask me where it should come from.

Read the install guide the agent follows

Other MCP clients

Add this to your client's mcpServers config. The client completes OAuth sign-in on first connect.

{
  "mcpServers": {
    "ref-tools": {
      "type": "http",
      "url": "https://api.ref.tools/mcp"
    }
  }
}

README

[Documentation for your agent] [smithery badge] [Website] [License] [npm version]

Ref MCP

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)

For more complex situations, the LLM will try to refine it's prompt as it reads results. For example:

SEARCH 'n8n merge node vs Code node multiple inputs best practices' (126)READ https://docs.n8n.io/integrations/builtin/core-nodes/n8n-nodes-base.merge/#merge (4961)READ https://docs.n8n.io/flow-logic/merging/#merge-data-from-multiple-node-executions (138)SEARCH 'n8n Code node multiple inputs best practices when to use' (107)READ https://docs.n8n.io/code/code-node/#usage (80)SEARCH 'n8n Code node access multiple inputs from different nodes' (370)SEARCH 'n8n Code node $input access multiple node inputs' (372)READ https://docs.n8n.io/code/builtin/output-other-nodes/#output-of-other-nodes (2310)

Ref takes advantage of MCP sessions to track search trajectory and minimize context usage. There's a lot more ideas cooking but here's what we've implemented so far.

1. Filtering search results

For repeated similar searches in a session, Ref will never return repeated results. Traditionally, you dig farther in to search results by paging to the next result but this approach allows the agent to page AND adjust the prompt at the same time.

2. Fetching the part of the page that matters

When reading a page of documentation, Ref will use the agent's session search history to dropout less relevant sections and return the most relevant 5k tokens. This helps Ref avoid a big problem with standard fetch() web scraping which is when it hits a large documentation page you can easily end up pull in 20k+ tokens into context, most of which are irrelevant.

Why does minimizing tokens from documentation context matter?

1. More context makes models dumber

It's well documented that as of July 2025 that models get dumber as you put in more tokens. You might have heard about how models are great with long context now and that's kind of true but not the whole picture. For a quick primer on some research, checkout this video from the team at Chroma.

2. Tokens cost $$$

Imagine you are using Claude Opus as a background agent and you start by having the agent pull in documentation context and suppose it pulls in 10000 tokens of context with 4000 being relevant and 6000 being extra noise. At API pricing, that 6k tokens cost about $0.09 PER STEP. If one prompt ends up taking 11 steps with Opus, you've spent $1 for no reason.

Setup

There are two options for setting up Ref as an MCP server, either via the streamable-http server (recommended) or local stdio server (legacy).

This repo contains the legacy stdio server.

Streamable HTTP (recommended)

[Install Ref MCP in Cursor]

"Ref": {  "type": "http",  "url": "https://api.ref.tools/mcp?apiKey=YOUR_API_KEY"}

stdio

[Install Ref MCP in Cursor (stdio)]

"Ref": {  "command": "npx",  "args": ["ref-tools-mcp@latest"],  "env": {    "REF_API_KEY": <sign up to get an api key>  }}

Tools

Ref MCP server provides all the documentation related tools for your agent needs.

ref_search_documentation

A powerful search tool to check technical documentation. Great for finding facts or code snippets. Can be used to search for public documentation on the web or github as well from private resources like repos and pdfs.

Parameters:

  • query (required): Query to search for relevant documentation. This should be a full sentence or question.

ref_read_url

A tool that fetches content from a URL and converts it to markdown for easy reading with Ref. This is powerful when used in conjunction with the ref_search_documentation tool that returns urls of relevant content.

Parameters:

  • url (required): The URL of the webpage to read.

OpenAI deep research support

Ref can be used as a source for deep research. OpenAI requires specific tool definitions so when used with an OpenAI client, Ref will provide the same tools with slightly different naming.

ref_search_documentation(query) -> search(query)ref_read_url(url) -> fetch(id)

Development

npm installnpm run dev

Running with Inspector

For development and debugging purposes, you can use the MCP Inspector tool. The Inspector provides a visual interface for testing and monitoring MCP server interactions.

Visit the Inspector documentation for detailed setup instructions.

To test locally with Inspector:

npm run inspect

Or run both the watcher and inspector:

npm run dev

Local Development

  1. Clone the repository
  2. Install dependencies:
bash
npm install
  1. Build the project:
bash
npm run build
  1. For development with auto-rebuilding:
bash
npm run watch

License

MIT

Source: README.md at commit 83970a3

Tools

0
This server asks you to sign in, so SourceWeft could not read its tools without an account and has not indexed them. What a connected account sees can depend on that account and its permissions.

Version history

1
  1. v3.0.1LatestSep 16, 2026

Score

85% of the applicable checks met

How complete this listing is, computed from the registry entry, the endpoint and public sources. Not a rating of the server and not a statement that it is safe or working today: reachability is a dated check, and no installs or reviews go into the score.

  • Reached in the last 30 daysRequired25 pts
  • Auth declaredRequired10 pts
  • Tools listed15 pts

    Answer tools/list without a credential, or ship a package that starts in a sandbox without one.

  • DescriptionRequired15 pts
  • Logo10 pts
  • Documentation15 pts
  • License10 pts