Enterprise-grade Model Context Protocol (MCP) Server for intelligent repository analysis and AI-powered development assistance.

Connect your development tools to comprehensive GitHub repository analysis with 11 streamlined tools, enhanced error handling, real-time monitoring, and production-ready deployment.

• 🔍 Comprehensive Repository Analysis - Deep insights into code structure, dependencies, and architecture
• 🤖 AI-Powered Code Review - Intelligent code analysis with OpenRouter integration (400+ models)
• 🚀 Production-Ready Deployment - Docker containers with security best practices
• 📊 Real-time Monitoring - Performance metrics, health checks, and observability
• 🛡️ Enterprise Security - Input validation, path traversal prevention, and secure processing
• ⚡ High Performance - Intelligent chunking, concurrent processing, and response optimization
• 🔧 Developer Experience - Comprehensive documentation, examples, and debugging tools

git clone https://github.com/TheAlchemist6/codecompass-mcp.git
cd codecompass-mcp

Expected output:

Cloning into 'codecompass-mcp'...
remote: Enumerating objects: 53, done.
remote: Total 53 (delta 0), reused 0 (delta 0), pack-reused 53
Receiving objects: 100% (53/53), 259.84 KiB | 1.85 MiB/s, done.

cp .env.example .env
# Edit .env with your real API keys
nano .env  # or use your preferred editor

Required in .env file:

GITHUB_TOKEN=ghp_your_actual_github_token_here
OPENROUTER_API_KEY=sk-or-v1-your_actual_openrouter_key_here

🔑 Where to get API keys:

• GitHub Token: github.com/settings/tokens → Generate new token (classic) → Select repo scope
• OpenRouter Key: openrouter.ai/keys → Create new API key

./scripts/docker-build.sh
./scripts/docker-run.sh --env-file .env

Expected output:

✅ Build successful
Image information:
REPOSITORY        TAG       IMAGE ID       CREATED         SIZE
codecompass-mcp   latest    a1b2c3d4e5f6   2 seconds ago   278MB

🚀 Starting CodeCompass MCP server...
✅ Server started successfully
Health check: healthy
API limits: 5000/hour remaining

# Test with health check
echo '{"jsonrpc": "2.0", "id": 1, "method": "tools/call", "params": {"name": "health_check"}}' | docker exec -i codecompass-mcp node build/index.js

• ✅ Linux (Ubuntu 18.04+, CentOS 7+)
• ✅ macOS (10.14+, Intel & Apple Silicon)
• ✅ Windows (10/11 with Docker Desktop)

# Install dependencies
npm install

# Set environment variables
export GITHUB_TOKEN=your_github_token
export OPENROUTER_API_KEY=your_openrouter_key

# Build and run
npm run build && npm run dev

npm install -g codecompass-mcp
codecompass-mcp --help

GITHUB_TOKEN=ghp_your_github_token_here        # GitHub API access
OPENROUTER_API_KEY=sk-or-v1-your_key_here     # OpenRouter API access

AI_MODEL=anthropic/claude-3.5-sonnet          # Default AI model
MAX_RESPONSE_TOKENS=25000                      # Response size limit
LOG_LEVEL=info                                 # Logging level
NODE_ENV=production                            # Environment mode

• get_repository_info - Repository metadata, statistics, and key information
• get_file_tree - Complete directory structure and file listing with filtering
• search_repository - Advanced search with regex patterns and filtering
• get_file_content - Batch file processing with security validation and metadata
• analyze_dependencies - Dependency graph analysis and vulnerability detection
• analyze_codebase - Comprehensive structure, architecture, and metrics analysis

• review_code - AI-powered code review with security, performance, and maintainability insights
• explain_code - Natural language code explanations and documentation generation
• suggest_improvements - Intelligent refactoring recommendations and modernization strategies

• transform_code - Code transformation, modernization, and migration assistance

• health_check - System health monitoring and performance metrics

# Build production image
./scripts/docker-build.sh

# Run with environment file
./scripts/docker-run.sh --env-file .env

# View logs
./scripts/docker-logs.sh -f --timestamps

version: '3.8'
services:
  codecompass-mcp:
    build: .
    container_name: codecompass-mcp
    restart: unless-stopped
    environment:
      - GITHUB_TOKEN=${GITHUB_TOKEN}
      - OPENROUTER_API_KEY=${OPENROUTER_API_KEY}
      - NODE_ENV=production
    healthcheck:
      test: ["CMD", "node", "-e", "console.log('Health check')"]
      interval: 30s
      timeout: 10s
      retries: 3

Add to your Claude Desktop configuration file:

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

{
  "mcpServers": {
    "codecompass": {
      "command": "docker",
      "args": [
        "exec", "-i", "codecompass-mcp", 
        "node", "build/index.js"
      ],
      "env": {
        "GITHUB_TOKEN": "your_github_token_here",
        "OPENROUTER_API_KEY": "your_openrouter_key_here"
      }
    }
  }
}

Then restart Claude Desktop and you'll see CodeCompass tools available in the UI.

# Add MCP server to Claude Code
claude mcp add codecompass-docker -s user -- \
  docker exec -i codecompass-mcp node build/index.js

• Cline (VS Code): Add to MCP configuration
• Continue (VS Code/JetBrains): Configure as MCP provider
• Custom clients: Use stdio transport with node build/index.js

# Test the connection
echo '{"jsonrpc": "2.0", "id": 1, "method": "tools/list"}' | docker exec -i codecompass-mcp node build/index.js

# Should return list of 11 tools

# Interactive monitoring dashboard
./scripts/monitor.js --watch

# Export metrics
./scripts/monitor.js --export > metrics.json

# Health check
curl -X POST http://localhost:3000/health

• Response Times: <100ms for health checks, 2-10s for repository analysis
• Memory Usage: 50-200MB depending on repository size
• Concurrent Processing: Configurable limits with automatic scaling
• Error Tracking: Comprehensive error monitoring with contextual suggestions

{
  "name": "health_check",
  "arguments": {
    "checks": ["api-limits", "monitoring", "configuration"],
    "options": {
      "include_metrics": true,
      "include_insights": true
    }
  }
}

{
  "name": "fetch_repository_data",
  "arguments": {
    "url": "https://github.com/microsoft/typescript",
    "options": {
      "include_structure": true,
      "include_dependencies": true,
      "max_files": 100,
      "chunk_mode": true
    }
  }
}

{
  "name": "ai_code_review",
  "arguments": {
    "url": "https://github.com/your-org/your-repo",
    "file_paths": ["src/main.ts", "src/utils/"],
    "review_focus": ["security", "performance", "maintainability"],
    "options": {
      "ai_model": "anthropic/claude-3.5-sonnet",
      "severity_threshold": "medium"
    }
  }
}

{
  "name": "get_file_content",
  "arguments": {
    "url": "https://github.com/your-org/your-repo",
    "file_paths": ["src/", "docs/", "tests/"],
    "options": {
      "max_concurrent": 10,
      "include_metadata": true,
      "continue_on_error": true
    }
  }
}

MCP Client → MCP Server → Service Layer → External APIs
            ↓
         Monitoring & Logging

• MCP Server: JSON-RPC protocol handling with 11 streamlined tools
• Service Layer: GitHub API, OpenRouter integration, and business logic
• Configuration: Centralized, type-safe configuration with Zod validation
• Monitoring: Real-time performance tracking and health monitoring
• Security: Input validation, path traversal prevention, and secure processing

• Zod Schema Validation: Type-safe input validation for all tools
• Path Traversal Prevention: Comprehensive file path security checks
• Rate Limiting: Configurable request rate limiting and throttling
• API Key Management: Secure environment variable handling

• Non-root Execution: All containers run as unprivileged users
• Read-only Filesystems: Security-focused container configuration
• Resource Limits: Memory and CPU constraints for stability
• Health Checks: Automated health monitoring and recovery

• Chunking: Large responses split into manageable chunks
• Truncation: Smart truncation preserving data structure
• Concurrent Processing: Parallel file processing with configurable limits
• Caching: Intelligent caching strategies for frequently accessed data

• Memory Efficiency: Optimized memory usage with automatic cleanup
• Request Tracking: Correlation IDs for distributed tracing
• Performance Insights: Automated performance analysis and recommendations
• Scalability: Horizontal scaling ready with Docker containers

• Setup Guide - Installation and configuration instructions
• API Reference - Complete tool documentation with examples
• Docker Guide - Container deployment and management
• Monitoring Guide - Observability and performance monitoring
• Architecture Guide - Technical architecture and patterns

• Usage Examples - Real-world usage patterns and templates
• Integration Examples - MCP client integration examples
• Configuration Templates - Production-ready configuration examples

We welcome contributions! Please see our Contributing Guide for details on:

• Development setup and workflow
• Code style and testing requirements
• Pull request process and guidelines
• Bug reporting and feature requests

# Clone and setup
git clone https://github.com/your-org/codecompass-mcp.git
cd codecompass-mcp

# Install dependencies
npm install

# Run tests
npm test

# Start development server
npm run dev:watch

• ✅ 11 streamlined, atomic tools with clear responsibilities
• ✅ Production-ready Docker deployment
• ✅ Real-time monitoring and observability
• ✅ Enterprise security features
• ✅ Complete documentation suite

• 🔮 Conversational Context Management - Session state and conversation history
• 🔮 Advanced Caching - Redis-based caching with intelligent invalidation
• 🔮 Plugin System - Extensible architecture for custom tools
• 🔮 Multi-language Support - Expanded language support beyond TypeScript/JavaScript
• 🔮 Kubernetes Integration - Native Kubernetes deployment with Helm charts

This project is licensed under the MIT License - see the LICENSE file for details.

• OpenRouter MCP - Architecture patterns and best practices inspiration
• MCP Protocol - Foundation for tool integration and communication
• Anthropic - Claude AI integration and development support
• GitHub - Repository analysis and API integration
• Docker - Containerization and deployment infrastructure

• Documentation: Check our comprehensive documentation in the docs/ directory
• Issues: Report bugs and request features on GitHub Issues
• Discussions: Join community discussions on GitHub Discussions

• API Key Setup: See Setup Guide
• Docker Issues: Check Docker Guide
• Performance: Review Monitoring Guide

• TypeScript - Type-safe JavaScript development
• Node.js - JavaScript runtime environment
• Docker - Containerization platform
• Zod - TypeScript-first schema validation
• MCP SDK - Model Context Protocol implementation

Made with 💜 by Myron Labs

Transform your development workflow with intelligent repository analysis and AI-powered code insights.