Documcp

🚀 DocuMCP - Intelligent Documentation Deployment MCP Server

DocuMCP is an intelligent Model Context Protocol (MCP) server that brings a revolutionary change to the documentation deployment of open - source projects. It offers in - depth repository analysis, intelligent static site generator recommendations, and automated GitHub Pages deployment workflows.

🚀 Quick Start

Once configured with your MCP client, you can prompt DocuMCP using natural language. For example:

# Complete workflow
"analyze my repository and deploy documentation to GitHub Pages"

# Step by step
"analyze my repository for documentation needs"
"recommend the best static site generator for my project"
"set up documentation structure and deploy to GitHub Pages"

DocuMCP provides over 30 tools, including repository analysis, intelligent SSG recommendations, content generation, deployment automation with tracking, validation, user preference management, deployment analytics, and memory - enhanced insights. Refer to the complete documentation for detailed tool reference.

✨ Features

Core Capabilities

• 🔍 Repository Analysis: Conducts a deep multi - layered analysis of the project structure, dependencies, and documentation requirements.
• 🎯 SSG Recommendations: Offers data - driven recommendations for Jekyll, Hugo, Docusaurus, MkDocs, or Eleventy.
• 📚 Diataxis Framework: Automatically creates well - structured documentation based on proven principles.
• 🚀 GitHub Pages Deployment: Generates an automated workflow with SSG - specific optimizations.
• ✅ Deployment Verification: Performs comprehensive checks and troubleshooting to ensure successful deployments.

Intelligence & Learning (Phase 2)

• 🧠 Historical Intelligence: Learns from past deployments to improve recommendation accuracy.
• 👤 User Preferences: Provides personalized recommendations according to your preferences and usage patterns.
• 📊 Deployment Analytics: Offers comprehensive insights into deployment patterns and success rates.
• 🎯 Smart Scoring: Assigns intelligent SSG scores based on success rates from similar projects.
• 📈 Trend Analysis: Identifies deployment trends and provides health scores.

Documentation Maintenance (v0.5.2+)

• 📅 Freshness Tracking: Monitors documentation staleness with configurable thresholds.
• ✅ Freshness Validation: Automatically initializes and updates freshness metadata.
• 🗺️ Sitemap Management: Generates, validates, and manages sitemap.xml for SEO purposes.
• 🔗 Knowledge Graph Integration: Tracks freshness history for intelligent recommendations.

AI - Powered Semantic Analysis (v0.6.0+)

• 🤖 LLM Integration: Optionally integrates with DeepSeek, OpenAI, Anthropic, or Ollama.
• 🔍 Semantic Code Analysis: Detects behavioral changes beyond syntax using AI.
• 🧪 Example Validation: Simulates code execution to verify documentation examples.
• 🎯 Intelligent Fallback: Gracefully degrades to AST - only analysis when LLM is unavailable.
• 🔒 Privacy First: Works fully offline with AST analysis, and LLM is completely optional.

📦 Installation

# Clone the repository
git clone https://github.com/tosin2013/documcp.git
cd documcp

# Install dependencies
npm install

# Build the project
npm run build

💻 Usage Examples

MCP Client Setup

Claude Desktop

1. Locate Claude Desktop's configuration file:
   • macOS: ~/Library/Application Support/Claude/claude_desktop_config.json
   • Windows: %APPDATA%\Claude\claude_desktop_config.json
   • Linux: ~/.config/claude/claude_desktop_config.json
2. Add documcp server configuration:

   {
     "mcpServers": {
       "documcp": {
         "command": "npx",
         "args": ["documcp"]
       }
     }
   }
   

3. Restart Claude Desktop to load the configuration.

VS Code with GitHub Copilot

1. Install MCP extension for VS Code.
2. Configure in VS Code settings.json:

   {
     "mcp.servers": {
       "documcp": {
         "command": "npx",
         "args": ["documcp"]
       }
     }
   }
   

Cursor Editor

1. Configure in Cursor settings:

   {
     "mcpServers": {
       "documcp": {
         "command": "npx",
         "args": ["documcp"]
       }
     }
   }
   

Gemini Code Assist

1. Check Gemini documentation for MCP server configuration.
2. Add similar configuration as above.

Troubleshooting

• Ensure npx is available in your PATH.
• For global installations, use the full path:

  {
    "command": "node",
    "args": ["/usr/local/lib/node_modules/documcp/dist/index.js"]
  }
  

• Find installation path: npm list -g documcp

Key Tools

Analysis & Recommendations

• analyze_repository - Performs a deep analysis of the repository structure and dependencies.
• recommend_ssg - Offers intelligent SSG recommendations based on historical data and user preferences.
• detect_gaps - Identifies missing documentation sections.

Deployment & Tracking

• deploy_pages - Automates GitHub Pages deployment and tracks the outcome.
• verify_deployment - Conducts comprehensive deployment validation.
• analyze_deployments - Provides analytics and insights from deployment history.

User Preferences & Learning

• manage_preferences - Manages user preferences for personalized recommendations.
• View historical success rates and deployment patterns.
• Get recommendations based on the success of similar projects.

📚 Documentation

DocuMCP automatically creates documentation following the Diataxis framework:

• Tutorials: Learning - oriented guides for new users.
• How - To Guides: Task - oriented recipes for specific goals.
• Reference: Information - oriented technical descriptions.
• Explanation: Understanding - oriented conceptual discussions.

🔧 Technical Details

Requirements

• Node.js: 20.0.0 or higher
• npm: Latest stable version

Development

# Run in development mode
npm run dev

# Run tests
npm test

# Lint code
npm run lint

# Type check
npm run typecheck

Architecture

DocuMCP follows a modular, stateless architecture:

• TypeScript - based implementation using the official MCP SDK.
• Stateless operation for consistency and reliability.
• Modular design with clear separation of concerns.
• Progressive complexity allowing users to start simply.

📄 License

This project is under the MIT License. See LICENSE for details.

Contributing

We welcome contributions! Please refer to our Contributing Guide for more information.

First Time Contributors

Look for issues labeled "good first issue" to start contributing to the project. We welcome developers of all experience levels.

Reporting Issues

Please use our issue templates when reporting bugs or requesting features.

Code of Conduct

This project adheres to the Contributor Covenant Code of Conduct. By participating, you are expected to uphold this code.

Security

Please refer to our Security Policy for reporting vulnerabilities and security - related issues.

Acknowledgments

• Built on the Model Context Protocol.
• Follows the Diataxis Framework.
• Inspired by the need for better documentation in open - source projects.