
FastMCP GitHub Automation Server
Provides a comprehensive API wrapper for GitHub operations through a FastMCP-based server, simplifying repository management, pull requests, issues, and other GitHub interactions with secure authentication.
README
GIT-Pilot
<div align="center"> <img src="images/logo.jpg" alt="GIT-Pilot Logo" width="200"/> </div>
GIT-Pilot is a powerful GitHub automation and management tool that provides a comprehensive API wrapper for GitHub operations. It simplifies GitHub interactions through a FastMCP-based server, making it easy to manage repositories, pull requests, issues, and more.
🌟 Features
🔐 Authentication & Security
- Secure token management with encryption using Fernet
- Token expiration and automatic cleanup
- Rate limit handling and automatic retries
- Configurable authentication timeouts
📦 Repository Management
- Create and manage repositories
- Handle branches and commits
- File operations (create, update, delete)
- Repository search and filtering
- Commit comparison and history
🔄 Pull Request Operations
- Create and manage pull requests
- Merge strategies (merge, squash, rebase)
- Status check validation
- Conflict detection and handling
- Draft PR support
📝 Issue Management
- Create and update issues
- Label management
- Assignee handling
- Comment management
- Issue search and filtering
🛠 Technical Features
- Thread-safe operations
- Resource management
- Comprehensive error handling
- Detailed logging
- Type safety
- Configuration management
- FastMCP server integration
🚀 Getting Started
Prerequisites
- Python 3.12 or higher
- GitHub account
- GitHub Personal Access Token
- FastMCP CLI (optional)
Installation
- Clone the repository:
git clone https://github.com/yourusername/GIT-Pilot.git
cd GIT-Pilot
- Install uv (if not already installed):
curl -LsSf https://astral.sh/uv/install.sh | sh
- Create and activate a virtual environment:
uv venv
source .venv/bin/activate # On Windows: .venv\Scripts\activate
- Install the package using uv:
uv pip install -e .
- Set up environment variables:
Create a
.env
file in the project root:
GITHUB_TOKEN=your_github_token_here
API Examples
# Create a repository
await call_tool("create_repository",
name="my-repo",
description="My awesome repository",
private=True,
has_issues=True,
has_wiki=True,
has_projects=True,
auto_init=True
)
# Create a pull request
await call_tool("create_pull_request",
repo_path="owner/repo",
title="New feature",
head="feature-branch",
base="main",
body="Description of changes",
draft=False
)
# List commits with filtering
await call_tool("list_commits",
repo_path="owner/repo",
branch="main",
author="username",
since="2024-01-01",
until="2024-04-21",
max_results=30
)
🔧 Configuration
The service can be configured through the Config
class:
@dataclass
class Config:
TOKEN_TTL_HOURS: int = 24
MAX_STORED_TOKENS: int = 1000
CLEANUP_INTERVAL_SECONDS: int = 3600
MAX_RETRIES: int = 3
RETRY_DELAY_SECONDS: int = 5
MAX_RESULTS_PER_PAGE: int = 100
ENCRYPTION_KEY: bytes = Fernet.generate_key()
🛡 Security
- Tokens are encrypted at rest using Fernet
- Automatic token expiration and cleanup
- Rate limit protection with retries
- Input validation
- Comprehensive error handling
- Secure token cleanup
🔄 Rate Limiting
The service includes built-in rate limit handling:
- Automatic retry on rate limit
- Configurable retry attempts
- Delay between retries
- Rate limit status logging
- Exponential backoff
🧪 Error Handling
Comprehensive error handling for:
- Authentication failures
- API errors
- Rate limits
- Invalid inputs
- Resource conflicts
- Network issues
- Token validation
- File operations
📈 Logging
Detailed logging with:
- Timestamp
- Log level
- Function name
- Line number
- Error details
- Stack traces
- Rate limit information
- Token operations
🤝 Contributing
We welcome contributions! Please follow these steps:
- Fork the repository
- Create a feature branch
- Commit your changes
- Push to the branch
- Create a Pull Request
📝 License
This project is licensed under the GNU General Public License v3.0 - see the LICENSE file for details.
🙏 Acknowledgments
- PyGithub for the GitHub API wrapper
- FastMCP for the server framework
- Fernet for secure token encryption
📞 Support
- GitHub Issues: Report a bug
- Documentation: Wiki
- Community: Discussions
🔄 Updates
Stay updated with the latest changes:
- Follow our release notes
- Subscribe to our newsletter
- Star the repository for updates
Made with ❤️ by the GIT-Pilot team
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.

E2B
Using MCP to run code via e2b.
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.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.