Documentation Assistant

A comprehensive MCP (Model Context Protocol) server that automatically analyzes Python codebases and generates professional documentation.

Features

• Repository Scanning: Automatically discovers and analyzes Python files

• Documentation Generation: Creates README, API docs, and setup guides

• Interactive Help: Explains specific functions and classes

• Dependency Tracking: Identifies all imports and packages

• MCP Integration: Works seamlessly with Claude Desktop

Related MCP server: Documentation MCP Server

Quick Start

Installation

1. Clone the repository:

git clone https://github.com/YOUR_USERNAME/documentation-assistant.git
cd documentation-assistant

2. Create virtual environment:

python -m venv venv

# On Windows:
venv\Scripts\activate

# On Mac/Linux:
source venv/bin/activate

3. Install dependencies:

pip install -r requirements.txt

Configuration

Add to your Claude Desktop config file:

macOS: ~/Library/Application Support/Claude/claude_desktop_config.json Windows: %APPDATA%\Claude\claude_desktop_config.json

{
  "mcpServers": {
    "documentation-assistant": {
      "command": "python",
      "args": ["/absolute/path/to/doc_assistant_mcp.py"]
    }
  }
}

Available Tools

• scan_repository - Analyze Python files in a directory

• generate_readme - Create comprehensive README

• generate_api_docs - Generate API documentation

• generate_setup_guide - Create setup instructions

• explain_code - Explain specific functions/classes

• list_dependencies - Show all project dependencies

Documentation

• Integration Guide - Complete setup instructions

• API Documentation - Generated example docs

• Setup Guide - Installation and configuration

• Conversation Logs - Usage examples

• Project Summary - Technical details

Testing

Run the test suite:

python test_client.py

Requirements

• Python 3.8+

• MCP SDK

• Dependencies listed in requirements.txt

License

MIT License

Contributing

Contributions welcome! Please read the contributing guidelines first.

Support

For issues or questions, please open an issue on GitHub.

Author

Lubaina - lubainahumayoun@gmail.com

Acknowledgments

• Built with MCP (Model Context Protocol)

• Uses Python AST for code analysis