Skillget

docmole

mcp
Security Audit
Warn
Health Pass
  • License — License: MIT
  • Description — Repository has a description
  • Active repo — Last push 0 days ago
  • Community trust — 18 GitHub stars
Code Warn
  • network request — Outbound network request in src/backends/agno.ts
  • process.env — Environment variable access in src/backends/embedded/config.ts
  • process.env — Environment variable access in src/backends/embedded/providers.ts
  • network request — Outbound network request in src/backends/embedded/providers.ts
Permissions Pass
  • Permissions — No dangerous permissions requested
Purpose
This tool is an MCP server that allows AI assistants like Claude or Cursor to query, index, and dig through external documentation sites using local vector storage and embeddings.

Security Assessment
Overall risk: Medium. The tool does not request dangerous system permissions, but it makes outbound network requests to fetch documentation pages and communicate with external APIs. It relies on environment variables (specifically requiring `OPENAI_API_KEY`) for its core functionality. While there are no hardcoded secrets, users should be aware that this tool inherently processes and sends data over the internet to embedding providers and target documentation websites. No arbitrary shell command execution was detected.

Quality Assessment
The project is actively maintained, with its last push occurring today. It uses the permissive and standard MIT license. However, it is a very new or niche tool with minimal community trust indicators, currently sitting at only 18 GitHub stars. The code is written in TypeScript and relies on the Bun runtime.

Verdict
Use with caution — the tool is actively maintained and open-source, but its young community footprint and inherent requirement to send data to external APIs warrant a careful review of the documentation sites you choose to index.
SUMMARY

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

README.md

docmole

Docmole

Dig through any documentation with AI

npm version
License
Bun
MCP

Docmole is an MCP server that lets you query any documentation site from AI assistants like Claude, Cursor, or any MCP-compatible client. The mole digs through docs so you don't have to.

Features

  • 🔍 Universal docs support — works with any documentation site
  • 🏠 Self-hosted RAG — LanceDB vectors + OpenAI embeddings, no Python needed
  • ⚡ Zero-setup mode — instant access to Mintlify-powered sites
  • 🧠 Multi-turn conversations — remembers context across questions
  • 🔗 WebFetch compatible — links converted to absolute URLs
  • 🔌 MCP native — works with Claude, Cursor, and any MCP client

Coming soon

  • 🦙 Ollama support — fully local mode, no API keys needed
  • 📄 Generic HTML extraction — support for non-Mintlify documentation sites
  • 🔄 Incremental updates — only re-index changed pages

Installation

To use Docmole, run it directly with bunx (no install needed):

bunx docmole --help

Or install globally:

bun install -g docmole

Works on macOS, Linux and Windows. Requires Bun runtime.

Getting started

Local RAG Mode (any docs site)

Index and query any documentation site. Requires OPENAI_API_KEY.

# One-time setup — discovers pages and builds vector index
bunx docmole setup --url https://docs.example.com --id my-docs

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

Add to your MCP client:

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

Mintlify Mode (zero setup)

For sites with Mintlify AI Assistant — no API key needed:

bunx docmole -p agno-v2

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

CLI

Docmole has a built-in CLI for all operations:

# Mintlify mode (proxy to Mintlify API)
docmole -p <project-id>

# Local RAG mode
docmole setup --url <docs-url> --id <project-id>
docmole serve --project <project-id>
docmole list
docmole stop --project <project-id>

Run docmole --help for all options.

How it works

┌─────────────┐     ┌─────────────┐     ┌──────────────────────┐
│ MCP Client  │────▶│   Docmole   │────▶│ Embedded: LanceDB    │
│ (Claude,    │◀────│ MCP Server  │◀────│ Mintlify: API proxy  │
│  Cursor...) │     └─────────────┘     └──────────────────────┘
└─────────────┘

Local RAG Mode: Crawls documentation, generates embeddings with OpenAI, stores in LanceDB. Hybrid search combines semantic and keyword matching.

Mintlify Mode: Proxies requests to Mintlify's AI Assistant API. Zero setup, instant results.

Known Mintlify Project IDs

Documentation Project ID
Agno agno-v2
Resend resend
Mintlify mintlify
Vercel vercel
Upstash upstash
Plain plain

Find more: Open DevTools → Network tab → use the AI assistant → look for leaves.mintlify.com/api/assistant/{project-id}/message

Configuration

Environment Variable Default Description
OPENAI_API_KEY — Required for local RAG mode
DOCMOLE_DATA_DIR ~/.docmole Data directory for projects

Project structure

~/.docmole/
├── projects/
│   └── <project-id>/
│       ├── config.yaml      # Project configuration
│       └── lancedb/         # Vector database
└── global.yaml              # Global settings

Documentation

See AGENT.md for detailed documentation including:

  • Architecture details
  • Backend implementations
  • Enterprise deployment guides

Contributing

PRs welcome! See the contributing guide for details.

Acknowledgments

License

The Docmole codebase is under MIT license.

Reviews (0)

No results found