A Model Context Protocol (MCP) server that enables AI assistants like Claude to interact with GitHub repositories, issues, and pull requests.

• Repository Search: Find GitHub repositories based on search queries
• Issue Management: Get, create, and comment on issues
• Pull Request Handling: View and manage pull requests
• Repository Analysis: Get statistics and insights about repositories

• Python 3.8+
• GitHub API token

1. Clone this repository:

   git clone https://github.com/yourusername/github-mcp-server.git
   cd github-mcp-server

2. Install dependencies:

   pip install -r requirements.txt

3. Set up your GitHub token as an environment variable:

   export GITHUB_TOKEN=your_github_token_here

4. Run the server:

   python server.py

The server will start running on http://localhost:5000.

The MCP server provides the following endpoints:

• GET /mcp/discover: Returns available operations and their parameters
• POST /mcp/execute: Executes operations based on provided parameters

curl -X GET http://localhost:5000/mcp/discover

curl -X POST http://localhost:5000/mcp/execute \
  -H "Content-Type: application/json" \
  -d '{
    "endpoint": "search_repositories",
    "parameters": {
      "query": "machine learning"
    }
  }'

curl -X POST http://localhost:5000/mcp/execute \
  -H "Content-Type: application/json" \
  -d '{
    "endpoint": "get_repo_issues",
    "parameters": {
      "owner": "openai",
      "repo": "whisper"
    }
  }'

The server follows the Model Context Protocol specification to allow AI assistants to:

1. Discover available operations
2. Execute operations with appropriate parameters
3. Process and return results in a structured format

You can extend this server by:

1. Adding new endpoints in the discover() function
2. Implementing corresponding handler functions
3. Updating the routing in the execute() function

• The server uses an API token for authentication with GitHub
• Implement rate limiting to prevent abuse
• Add input validation for all parameters
• Consider implementing OAuth for more secure token management

See the demo video for a walkthrough of the server's capabilities.

MIT License

For questions or support, please open an issue on this repository.