docmole

Overview

Docmole is a versatile MCP server designed to enable AI assistants to search and query documentation sites. It operates in two modes: local RAG mode which crawls documentation sites, generates embeddings with OpenAI, and stores them in LanceDB; and Mintlify mode which proxies requests to Mintlify's AI Assistant API with zero setup. The server supports multi-turn conversations, web fetch compatibility, and works with Claude, Cursor, and other MCP clients.

Try asking AI

After installing, here are 5 things you can ask your AI assistant:

• query_docs

  Query documentation across indexed sites

  Try:How do I set up authentication in Resend?Try:What are the deployment options for Vercel?Try:Explain how to use vector databases with LanceDB

Note: Inferred from the documentation that this is an MCP server for querying documentation, though the exact tool names aren't explicitly documented. The 'query_docs' name represents the core functionality described in the README.

Comparable tools

Installation

bunx docmole --help

bun install -g docmole

# One-time setup
bunx docmole setup --url https://docs.example.com --id my-docs

# Start the MCP server
bunx docmole serve --project my-docs

bunx docmole -p agno-v2

{
  "mcpServers": {
    "my-docs": {
      "command": "bunx",
      "args": ["docmole", "serve", "--project", "my-docs"]
    },
    "mintlify-docs": {
      "command": "bunx",
      "args": ["docmole", "-p", "agno-v2"]
    }
  }
}

FAQ

What documentation sites does Docmole support?

Docmole supports any documentation site through its local RAG mode. It also has zero-setup support for specific Mintlify-powered sites like Agno, Resend, Vercel, and others.

Do I need an OpenAI API key?

An OpenAI API key is only required for local RAG mode. For Mintlify-powered sites, no API key is needed as it proxies requests to Mintlify's API.

Compare docmole with