YannickTM

DocuMCP

Community YannickTM
Updated

DocuMCP

๐Ÿค– An MCP server for intelligent code documentation generation with RAG capabilities

DocuMCP enables Claude to generate, search, and manage documentation for your codebase using vector embeddings and semantic search. It provides tools for creating user guides, technical documentation, code explanations, and architectural diagrams.

โœจ Features

  • ๐Ÿ“š Generate and update documentation based on your codebase
  • ๐Ÿ” Semantic search across code, documentation, and diagrams
  • ๐Ÿ“Š Create and merge architectural diagrams
  • ๐Ÿ“ Generate user guides
  • ๐Ÿ’พ Support for multiple vector databases (LanceDB, ChromaDB, Qdrant)
  • ๐Ÿง  Flexible embedding providers (built-in or Ollama)

๐Ÿš€ Quick Start

Installation via NPX (Recommended)

The easiest way to use DocuMCP is to configure Claude Desktop with the published npm package:

Add the following to your Claude Desktop configuration:

  • MacOS: ~/Library/Application Support/Claude/claude_desktop_config.json
  • Windows: %APPDATA%/Claude/claude_desktop_config.json
{
  "mcpServers": {
    "docu-mcp": {
      "command": "npx",
      "args": ["@myjungle/docu-mcp-server"]
    }
  }
}

That's it! Restart Claude Desktop and DocuMCP will be available.

Alternative Installation Methods

Using Smithery CLI

Install the server via Smithery CLI:

# Install Smithery CLI if you don't have it
npm install -g @smithery/cli

# Then install the Docu MCP server
npx -y @smithery/cli@latest install @YannickTM/docu-mcp --client claude

๐Ÿš€ Manual Start

1. Clone and Install

git clone https://github.com/YannickTM/docu-mcp
cd docu-mcp
npm install

2. Build the MCP Server

cd mcp
npm run build
cd ..

3. Advanced Configuration

Add the following to your Claude Desktop configuration:

  • MacOS: ~/Library/Application Support/Claude/claude_desktop_config.json
  • Windows: %APPDATA%/Claude/claude_desktop_config.json
{
  "mcpServers": {
    "docuassistant": {
      "command": "node",
      "env": {
        "VECTOR_DB_PROVIDER": "qdrant",
        "QDRANT_URL": "http://localhost:6333",
        "EMBEDDING_PROVIDER": "ollama",
        "EMBEDDING_MODEL": "bge-m3:latest",
        "EMBEDDING_DIMENSION": "1024",
        "OLLAMA_URL": "http://localhost:11434"
      },
      "args": ["/absolute/path/to/DocuMCP/mcp/dist/index.js"]
    }
  }
}

4. Start Required Services (if using external providers)

For Qdrant:
cd qdrant
npm run start
For ChromaDB:
cd chromadb
npm run start

5. Restart Claude Desktop

Restart Claude Desktop to load the new configuration.

๐Ÿ› ๏ธ Configuration Options

Vector Database Providers

Provider Description Configuration
LanceDB File-based local database (default) VECTOR_DB_PROVIDER=lanceLANCE_PATH=~/lanceDB
ChromaDB Simple vector database with web UI VECTOR_DB_PROVIDER=chromaCHROMA_URL=http://localhost:8000
Qdrant Production-grade vector database VECTOR_DB_PROVIDER=qdrantQDRANT_URL=http://localhost:6333

Embedding Providers

Provider Description Configuration
Built-in Uses all-MiniLM-L6-v2 model (default) EMBEDDING_PROVIDER=buildinEMBEDDING_MODEL=all-MiniLM-L6-v2EMBEDDING_DIMENSION=384
Ollama Use any Ollama model EMBEDDING_PROVIDER=ollamaEMBEDDING_MODEL=bge-m3:latestEMBEDDING_DIMENSION=1024OLLAMA_URL=http://localhost:11434

๐Ÿ”ง Available Tools

DocuMCP provides the following tools to Claude:

  • ๐Ÿ“ File Operations: read_file, write_file, create_directory, read_directory
  • ๐Ÿ”Ž Search Tools: search_codebase, search_documentation, search_diagram, search_user_guide
  • ๐Ÿ“š Documentation: generate_documentation, generate_user_guide, explain_code
  • ๐Ÿ“Š Diagrams: generate_diagram, merge_diagram
  • ๐Ÿ—ƒ๏ธ Indexing: index_file, index_directory
  • ๐Ÿ”€ Merging: merge_documentation

๐Ÿ“‹ Requirements

  • Node.js 20.11.24+
  • Claude Desktop
  • (Optional) Docker for running external vector databases

๐Ÿค Contributing

Contributions are welcome! Please feel free to submit a Pull Request.

Made with โค๏ธ

MCP Server ยท Populars

MCP Server ยท New

    ajitpratap0

    GoSQLX

    High-performance SQL parser, formatter, linter & security scanner for Go - 1.5M+ ops/sec, multi-dialect, zero-copy, race-free

    Community ajitpratap0
    smart-mcp-proxy

    MCPProxy โ€“ Smart Proxy for AI Agents

    Supercharge AI Agents, Safely

    Community smart-mcp-proxy
    wowyuarm

    File Ops

    A local file operations skill for AI agents: convert, inspect, archive, and extract text

    Community wowyuarm
    cyanheads

    @cyanheads/mcp-ts-core

    TypeScript template for building Model Context Protocol (MCP) servers. Ships with declarative tools/resources, pluggable auth, multi-backend storage, OpenTelemetry observability, and first-class support for both local and edge (Cloudflare Workers) runtimes.

    Community cyanheads
    bitbonsai

    MCP-Vault

    A lightweight Model Context Protocol (MCP) server for safe Obsidian vault access

    Community bitbonsai