GitHub MCP Control Plane
Provides secure, controlled access to GitHub operations through the Model Context Protocol with enterprise-grade security features including secret detection, vulnerability scanning, rate limiting, and full audit trails. Supports repository management, file operations, branch creation, commits, and GitHub Actions workflows.
README
GitHub MCP Control Plane
A production-ready, enterprise-grade GitHub MCP (Model Context Protocol) server deployed on Cloudflare Workers with zero-idle cost, comprehensive security validation, and full audit trails.
Overview
This MCP server provides secure, controlled access to GitHub operations through the Model Context Protocol. It implements a stateless request/response model with enterprise-grade security features including:
- Multi-layer Security: Secret detection, vulnerability scanning, RBAC, and policy enforcement
- Full Audit Trail: Every action logged with correlation IDs for complete traceability
- Rate Limiting: Distributed rate limiting using Cloudflare KV
- Batch Operations: Handle 100+ files in a single commit
- Delegation: Heavy tasks delegated to GitHub Actions for optimal performance
- Idempotent Operations: Built-in retry logic with exponential backoff
Architecture
┌─────────────┐
│ Client │
└──────┬──────┘
│ MCP Request
▼
┌─────────────────────────────────────┐
│ Cloudflare Worker (Stateless) │
│ ┌───────────────────────────────┐ │
│ │ Entry Point & Routing │ │
│ └──────────────┬────────────────┘ │
│ ▼ │
│ ┌───────────────────────────────┐ │
│ │ Authentication & Authorization│ │
│ └──────────────┬────────────────┘ │
│ ▼ │
│ ┌───────────────────────────────┐ │
│ │ Validation Pipeline │ │
│ │ • Schema Validation │ │
│ │ • Security Scanning │ │
│ │ • Policy Enforcement │ │
│ │ • Dependency Checking │ │
│ └──────────────┬────────────────┘ │
│ ▼ │
│ ┌───────────────────────────────┐ │
│ │ Tool Execution │ │
│ │ • Read-Only Tools │ │
│ │ • Write-Controlled Tools │ │
│ │ • Workflow Tools │ │
│ └──────────────┬────────────────┘ │
│ ▼ │
│ ┌───────────────────────────────┐ │
│ │ Audit Logging & Response │ │
│ └──────────────┬────────────────┘ │
└─────────────────┼────────────────────┘
│
┌─────────┴─────────┐
▼ ▼
┌───────────────┐ ┌──────────────┐
│ GitHub API │ │ GitHub │
│ │ │ Actions │
└───────────────┘ └──────────────┘
Quick Start
Prerequisites
- Node.js 18+
- Wrangler CLI
- GitHub Personal Access Token with appropriate permissions
- Cloudflare account with Workers and KV enabled
Installation
# Install dependencies
npm install
# Configure Wrangler
wrangler login
# Set required secrets
wrangler secret put GITHUB_TOKEN
wrangler secret put GITHUB_WEBHOOK_SECRET
wrangler secret put JWT_SECRET
wrangler secret put ENCRYPTION_KEY
# Validate configuration
npm run validate-config
# Deploy to production
npm run deploy
Local Development
# Start local development server
npm run dev
# The worker will be available at http://localhost:8787
Configuration
Environment Variables
See .env.example for all available configuration options.
Tool Manifest
Configure available tools in src/config/tools-manifest.json:
{
"tools": [
{
"name": "list_repositories",
"category": "read-only",
"description": "List repositories accessible to the authenticated user",
"requiredPermissions": ["read:org", "repo"]
}
]
}
Policy Rules
Define authorization policies in src/config/policy-rules.json:
{
"policies": [
{
"name": "write-restrictions",
"tools": ["create_branch", "create_commit"],
"conditions": {
"repository": {
"allowedPatterns": ["*"],
"blockedPatterns": ["protected-*"]
},
"branch": {
"blockedPatterns": ["main", "master", "production"]
}
}
}
]
}
Security Features
1. Authentication
- JWT token validation
- GitHub permission verification
- Token expiration handling
2. Authorization
- RBAC with fine-grained permissions
- Repository-level access control
- Branch protection rules
3. Validation
- JSON schema validation for all requests
- Secret detection (regex + entropy analysis)
- Dependency vulnerability checking via OSV.dev
- Code policy enforcement
4. Rate Limiting
- Distributed rate limiting with Cloudflare KV
- Configurable windows and thresholds
- Per-client rate tracking
5. Audit Trail
- Every action logged with correlation ID
- Structured JSON logging
- Configurable retention period
Available Tools
Read-Only Tools
list_repositories- List accessible repositoriesfetch_file- Fetch file contents from a repositorylist_files- List files in a directoryget_repository_info- Get repository metadata
Write-Controlled Tools
create_branch- Create a new branchcreate_commit- Create commits with file changesbatch_create_commits- Handle 100+ files in batch operations
Workflow Tools
trigger_workflow- Trigger GitHub Actions workflowsget_workflow_status- Check workflow execution statusget_workflow_logs- Fetch workflow execution logs
API Reference
See docs/API.md for detailed API documentation.
Deployment
Production Deployment
# Deploy to production
npm run deploy
# Deploy to staging
wrangler deploy --env staging
GitHub Actions Integration
For long-running tasks, the worker delegates to GitHub Actions. Configure:
- Add workflow file to your repository (
.github/workflows/execution-handler.yml) - Set
GITHUB_WEBHOOK_SECRETin your repository settings - Configure the worker URL in workflow dispatch
See docs/DEPLOYMENT.md for complete deployment guide.
Monitoring
Health Check
curl https://your-worker-url.workers.dev/health
Expected response:
{
"status": "healthy",
"timestamp": "2024-01-01T00:00:00Z",
"version": "1.0.0"
}
Logs
All logs are emitted in structured JSON format:
{
"level": "info",
"message": "Request received",
"correlationId": "abc-123",
"tool": "list_repositories",
"userId": "user-123",
"timestamp": "2024-01-01T00:00:00Z"
}
Testing
# Run all tests
npm test
# Run tests with coverage
npm run test:coverage
# Run specific test file
npx vitest tests/unit/auth.test.js
Error Handling
All errors follow a consistent format:
{
"error": {
"code": "VALIDATION_ERROR",
"message": "Invalid request payload",
"details": [
{
"field": "repository",
"message": "Repository name is required"
}
],
"correlationId": "abc-123"
}
}
Security Considerations
- Never commit secrets - Use Wrangler secrets for all sensitive data
- Use principle of least privilege - GitHub tokens should have minimal required permissions
- Enable audit logging - Track all operations for compliance
- Regular secret rotation - Rotate JWT and encryption keys regularly
- Monitor rate limits - Set appropriate thresholds to prevent abuse
Troubleshooting
Common Issues
Worker returns 401 Unauthorized
- Check GITHUB_TOKEN is set correctly
- Verify token has required permissions
- Check token hasn't expired
Rate limit errors
- Review rate limiting configuration
- Check KV namespace is properly configured
- Monitor usage patterns
Validation failures
- Review validation logs for specific errors
- Check schema definitions in tools-manifest.json
- Verify secret patterns in secret-patterns.json
Contributing
Contributions are welcome! Please ensure:
- All tests pass
- Code follows existing patterns and style
- New features include tests
- Documentation is updated
License
MIT License - see LICENSE file for details
Support
For issues and questions:
- GitHub Issues: [repository-url]/issues
- Documentation: docs/
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
E2B
Using MCP to run code via e2b.