MCPgee
MCPgee
MCPgeeMCPgee

Docmole

v1.0.0•Knowledge & Memory•stable

Dig through any documentation with AI - MCP server for Claude, Cursor, and other AI assistants

aianthropicbunclaudeclaude-code
Share:
18
Stars
0
Downloads
0
Weekly
0/5
View on GitHub

What is Docmole?

Docmole is a Model Context Protocol (MCP) server that allows AI assistants like Claude, Cursor, and VS Code to dig through any documentation with ai - mcp server for claude, cursor, and other ai assistants

Dig through any documentation with AI - MCP server for Claude, Cursor, and other AI assistants

This server falls under the Knowledge & Memory category on MCPgee, the world's largest MCP server directory with 33,000+ servers.

Features

  • Dig through any documentation with AI - MCP server for Claud

Use Cases

Documentation search and analysis
AI-powered doc navigation
Vigtu

Maintainer

LicenseMIT
Languagetypescript
Versionv1.0.0
UpdatedApr 17, 2026
Statushealthy
Maintenanceactive

Works with

ClaudeOpenAIwindowsmacoslinux
View SourceBrowse All Servers

Installation

Manual Installation

npx docmole

Configuration

Configuration Details

Config File

claude_desktop_config.json

Performance

Response Metrics

Response Time< 200ms
ThroughputMedium

Resource Usage

Memory UsageLow
CPU UsageLow

How to Set Up and Use Docmole

Docmole is an MCP server that lets AI assistants dig through any documentation site using vector-based semantic search and hybrid keyword retrieval. It supports two modes: a zero-setup Mintlify proxy for compatible documentation platforms, and a self-hosted local RAG mode powered by LanceDB and OpenAI embeddings for any documentation URL. Teams use it to give Claude, Cursor, and other AI assistants deep, accurate answers about third-party libraries and internal docs without copy-pasting content manually.

Prerequisites

  • Bun runtime installed (https://bun.sh) — Docmole's CLI is built with Bun
  • An OpenAI API key if using local RAG mode (not required for Mintlify proxy mode)
  • A documentation URL or Mintlify project identifier for the docs you want to index
  • An MCP-compatible client such as Claude Desktop or Cursor
1

Install Docmole globally via Bun

Install the Docmole CLI globally using Bun so it is available as a command for the MCP server process.

bun install -g docmole
2

Choose your mode: Mintlify proxy or local RAG

For Mintlify-hosted docs, use the project ID directly (no API key needed). For any other documentation URL, set your OPENAI_API_KEY environment variable to enable local embedding and vector search.

# For Mintlify proxy mode (no API key required):
bunx docmole -p agno-v2

# For local RAG mode, set your key first:
export OPENAI_API_KEY=sk-...
3

Set up a project for local RAG mode

Run the setup command to crawl and index your target documentation URL. Docmole will scrape the site and build a local LanceDB vector store in the DOCMOLE_DATA_DIR directory (default: ~/.docmole).

bunx docmole setup --url https://docs.example.com --id my-docs
4

Serve the MCP server for your indexed project

Start the Docmole MCP server for the project you just indexed. This process exposes the documentation search tools via the MCP protocol for your AI client to consume.

bunx docmole serve --project my-docs
5

Add Docmole to your MCP client configuration

Register the server in your client's config file. Use the serve command as the MCP process so the client launches it automatically.

{
  "mcpServers": {
    "my-docs": {
      "command": "bunx",
      "args": ["docmole", "serve", "--project", "my-docs"],
      "env": {
        "OPENAI_API_KEY": "sk-YOUR_KEY_HERE",
        "DOCMOLE_DATA_DIR": "~/.docmole"
      }
    }
  }
}

Docmole Examples

Client configuration

Example claude_desktop_config.json entry for a Docmole server serving a locally indexed documentation project.

{
  "mcpServers": {
    "my-docs": {
      "command": "bunx",
      "args": ["docmole", "serve", "--project", "my-docs"],
      "env": {
        "OPENAI_API_KEY": "sk-YOUR_OPENAI_API_KEY",
        "DOCMOLE_DATA_DIR": "/Users/yourname/.docmole"
      }
    }
  }
}

Prompts to try

Example prompts to send to your AI assistant after connecting Docmole.

- "Search the docs for how to configure authentication middleware"
- "What are all the configuration options for the cache module?"
- "Find examples of pagination in the API documentation"
- "Explain the difference between sync and async modes based on the docs"
- "What does the docs say about rate limiting and retry strategies?"

Troubleshooting Docmole

Setup fails with an embedding error or OpenAI authentication error

Ensure OPENAI_API_KEY is exported in your shell environment before running the setup command. The local RAG mode requires a valid OpenAI key to generate embeddings. Mintlify proxy mode does not require it.

Documentation search returns irrelevant results

Re-run 'bunx docmole setup' with the same project ID to re-crawl and re-index the documentation. If the docs site uses JavaScript rendering, some pages may not have been captured; check the crawl output for skipped URLs.

Docmole MCP tools do not appear in the AI client

Verify Bun is installed and in PATH by running 'bun --version'. Confirm the project name in the serve command matches the ID used during setup. Fully restart the MCP client after editing the configuration file.

Frequently Asked Questions about Docmole

What is Docmole?

Docmole is a Model Context Protocol (MCP) server that dig through any documentation with ai - mcp server for claude, cursor, and other ai assistants It connects AI assistants to external tools and data sources through a standardized interface.

How do I install Docmole?

Follow the installation instructions on the Docmole GitHub repository. Clone the repo, install dependencies, and add the server config to your AI client.

Which AI clients work with Docmole?

Docmole works with all major MCP-compatible AI clients including Claude Desktop, Claude Code, Cursor, VS Code (GitHub Copilot), Windsurf, and Cline.

Is Docmole free to use?

Yes, Docmole is open source and available under the MIT license. You can use it freely in both personal and commercial projects.

Learn More About MCP Servers

Getting Started with MCP

Set up your first MCP server in minutes

MCP Setup Guide

Configure MCP in Claude, Cursor & VS Code

All MCP Tutorials

18+ hands-on guides for developers

MCP FAQ

40+ answers about Model Context Protocol

Docmole Alternatives — Similar Knowledge & Memory Servers

Looking for alternatives to Docmole? Here are other popular knowledge & memory servers you can use with Claude, Cursor, and VS Code.

MemPalace

★ 52.6k

A local AI memory system that stores all conversations verbatim and organizes them into navigable structures. It provides 19 MCP tools for AI assistants to search and retrieve past decisions, debugging sessions, and architecture debates automatically

Kratos

★ 25.7k

🏛️ Memory System for AI Coding Tools - Never explain your codebase again. MCP server with perfect project isolation, 95.8% context accuracy, and the Four Pillars Framework.

Context Mode

★ 15.4k

An MCP server that preserves LLM context by intercepting large data outputs and returning only concise summaries or relevant sections. It enables efficient sandboxed code execution, file processing, and documentation indexing across multiple programm

Memu

★ 13.7k

Memory for 24/7 proactive agents like OpenClaw.

MemOS

★ 9.3k

MemOS (Memory Operating System) is a memory management operating system designed for AI applications. Its goal is: to enable your AI system to have long-term memory like a human, not only remembering what users have said but also actively invoking, u

Everos

★ 5.4k

Build, evaluate, and integrate long-term memory for self-evolving agents.

Browse More Knowledge & Memory MCP Servers

Explore all knowledge & memory servers available in the MCPgee directory. Each server includes setup guides for Claude, Cursor, and VS Code.

Knowledge & MemoryBrowse All Servers

Quick Config Preview

{ "mcpServers": { "docmole": { "command": "npx", "args": ["-y", "docmole"] } } }

Add this to your claude_desktop_config.json or .cursor/mcp.json

Read the full setup guide →

Ready to use Docmole?

Browse our complete directory of 33,000+ MCP servers, read setup guides for your editor, and start building with the Model Context Protocol.

33,000+ ServersFree & Open SourceStep-by-Step Guides
Explore All ServersRead Our Guides