Ref provides token-efficient access to technical documentation for AI coding agents, enabling precise search and retrieval of API references, library guides, and service documentation. Unlike bulk documentation loaders, it uses intelligent search to deliver only the relevant context, reducing token consumption by 60-95%. Key capabilities: - Search across public documentation or index private GitHub repositories and PDFs for custom knowledge bases - Session-aware search that filters duplicate results and tracks query trajectories to refine results - Smart content extraction that surfaces only the most relevant sections of documentation pages - Optimized MCP implementation designed to minimize context rot while maximizing information retrieval accuracy

[](https://ref.tools) [](https://smithery.ai/server/@ref-tools/ref-tools-mcp) [](https://ref.tools) [](LICENSE) [](https://www.npmjs.com/package/ref-tools-mcp)

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 design 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

2. Fetching the part of the page that matters

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)

[](https://cursor.com/install-mcp?name=Ref&config=eyJjb21tYW5kIjoibnB4IiwiYXJncyI6WyIteSIsIm1jcC1yZW1vdGVAMC4xLjAtMCIsImh0dHBzOi8vYXBpLnJlZi50b29scy9tY3AiLCItLWhlYWRlcj14LXJlZi1hcGkta2V5OjxzaWduIHVwIHRvIGdldCBhbiBhcGkga2V5PiJdfQ==)

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

stdio

[](https://cursor.com/install-mcp?name=Ref&config=eyJjb21tYW5kIjoibnB4IiwiYXJncyI6WyJyZWYtdG9vbHMtbWNwIl0sImVudiI6eyJSRUZfQVBJX0tFWSI6IjxzaWduIHVwIHRvIGdldCBhbiBhcGkga2V5PiJ9fQ==)

``` "Ref": { "command": "npx", "args": ["ref-tools-mcp@latest"], "env": { "REF_API_KEY":