mcpField
@
@ragrabbit/mcp

@ragrabbit/mcp

Local
ragrabbit.comSearch136Updated 83w ago
RepositoryVisit website

About @ragrabbit/mcp

@ragrabbit/mcp is an MCP server for searching documentation indexed by a RagRabbit instance. It is open source and self-hosted, and suits teams that want AI clients to query their own website documentation.

Key features

  1. 01Semantic search using natural language queries
  2. 02search_docs tool for documentation lookup
  3. 03llms.txt resource with LLM-related documentation
  4. 04Setup instructions for Claude Desktop and Cursor

Use cases

  1. 01Adding an AI-accessible search entry point to product documentation
  2. 02Letting a coding assistant in Cursor query project docs
  3. 03Retrieving product usage guides from Claude Desktop

MCP support

This project is an MCP server that exposes a search_docs tool for documentation search and an llms.txt resource describing LLM documentation to MCP clients.

Configuration

Local server config is the same for every client. Copy it into your client’s MCP config file.

mcp.json · Universal config
{
  "mcpServers": {
    "madarco": {
      "command": "npx",
      "args": [
        "-y",
        "@ragrabbit/mcp"
      ]
    }
  }
}
Run commandnpx -y @ragrabbit/mcp

Local servers need a runtime on your machine (e.g. Node.js 18+). Config file locations differ by client; see your client’s docs.

Packages
npm@ragrabbit/mcp

Tools

1

Saved tool list · updated 3w ago

ParameterTypeRequiredDescription
querystringYesThe search query to find relevant documents

Details

From the project README

MCP Server for RagRabbit Documentation Search

This server implements the Model Context Protocol (MCP) to provide AI models with access to any documentation indexed with an instance of RagRabbit.

Overview

The MCP Server acts as a bridge between AI clients and RagRabbit's hosted documentation:

  • Semantic search across documentation using natural language queries
  • Access to LLM-specific documentation
  • Standardized communication through the Model Context Protocol

Installation

Claude Desktop

Add a custom mcp server with the name of your product, so that Claude AI can use it when looking for info about it.

in claude_desktop_config.json (Claude -> Settings -> Developer -> Edit Config)

{
  "mcpServers": {
    "<name_of_your_documentation_no_spaces>": {
      "command": "npx",
      "args": ["@ragrabbit/mcp", "http://<RagRabbit install>/", "<name of your documentation>"]
    }
  }
}
In Cursor IDE

Go to Cursor -> Settings -> Cursor Settings -> MCP

And add a new MCP of type command with the command:

npx @ragrabbit/mcp", "http://<RagRabbit install>/", "<name of your documentation>"

Arguments:

  • ragrabbit-url: (Required) The base URL of your RagRabbit instance, eg https://my-ragrabbit.vercel.com/
  • name: (Required) Custom name for the documentation search service (defaults to "RagRabbit") so that AI will know to use it when looking for info

Exposed Tools by this MCP

search_docs

Performs semantic search across the documentation.

Parameters:

  • query: String - The search query to find relevant documents

Example:

{
  "name": "search_docs",
  "arguments": {
    "query": "How to implement authentication?"
  }
}

Available Resources

LLMs Documentation
  • URI: llms.txt
  • Description: Documentation about LLMs and their capabilities
  • MIME Type: text/plain

License

MIT

Comments

Markdown supported

New to MCP?

From what the protocol is to installing your first server, these answers cover most first questions.

An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.