GitHubMcpServer

GitHubMcpServer

Exposes GitHub REST API operations as AI-ready tools for managing repositories, tracking push history, and updating settings. It enables LLM agents to perform tasks like creating repositories, retrieving metadata, and monitoring branch activity through a standardized interface.

Category
Visit Server

README

GitHubMcpServer

<div align="center">

Python FastMCP GitHub API License MCP

A Custom GitHub MCP (Model Context Protocol) Server that exposes GitHub API operations as AI-ready tools for LLM agents and applications.

OverviewFeaturesInstallationToolsConfigurationUsage

</div>


📖 Overview

GitHubMcpServer is a lightweight, high-performance MCP server built with FastMCP that bridges AI models and the GitHub REST API. It allows AI agents (such as Claude, GPT-4, etc.) to interact with GitHub repositories directly — fetching metadata, managing settings, tracking activity, listing and creating repositories — all through a standardized MCP interface over HTTP.

┌──────────────────────────┐        ┌───────────────────────────┐
│   AI Agent / LLM Client  │ ──────▶│   GitHubMcpServer         │
│  (Claude, GPT, etc.)     │◀────── │   FastMCP  •  Port 10000  │
└──────────────────────────┘        └──────────────┬────────────┘
                                                   │
                                       ┌───────────▼────────────┐
                                       │   GitHub REST API v3   │
                                       │   api.github.com       │
                                       └────────────────────────┘

✨ Features

Feature Description
🔍 Get Repository Info Fetch detailed metadata for any repository
✏️ Update Repository Settings Modify name, description, visibility, merge strategies & more
📊 Track Repository Activity Query push history, branch changes, merges with filtering
📂 List All Repositories Paginate and sort all user repositories
🆕 Create Repositories Spin up new repos with custom configuration
Async & Non-blocking Built with httpx and async/await for high performance
🌐 CORS Enabled Ready for browser-based or cross-origin MCP clients
🔒 Secure Auth Token-based authentication via .env file

📋 Prerequisites

  • Python 3.10+
  • A GitHub Personal Access Token (PAT) with required scopes
  • uv (recommended) or pip

Required GitHub Token Scopes

Scope Purpose
repo Full access to public & private repositories
read:user Read authenticated user profile data

💡 Generate your token at: GitHub → Settings → Developer Settings → Personal Access Tokens


🚀 Installation

1. Clone the Repository

git clone https://github.com/moksh555/GitHUbMcpServer.git
cd GitHUbMcpServer

2. Install Dependencies

Using uv (recommended):

uv sync

Using pip:

pip install "fastmcp>=3.1.1" httpx pydantic-settings

⚙️ Configuration

Create a .env file in the project root:

GITHUB_ACCESS_TOKEN=ghp_your_personal_access_token_here
OWNER_NAME=your_github_username
Variable Required Description
GITHUB_ACCESS_TOKEN Your GitHub Personal Access Token
OWNER_NAME Your GitHub username (repository owner)

⚠️ Never commit your .env file to version control. It is already listed in .gitignore.


▶️ Running the Server

uv run python gitHubMcpServer.py

The server starts on http://localhost:10000 using HTTP transport with CORS support.


🛠️ Available MCP Tools

getUserRepo

Retrieves detailed information for a specific GitHub repository.

Parameters:

Name Type Required Description
repoName string The name of the repository

Returns: ID, name, URL, privacy status, description, creation/update timestamps, primary language, open issues count.


updateRepo

Updates settings for an existing repository. Only provide fields you want to change.

Parameters:

Name Type Description
repoName string ✅ Current repository name
name string New repository name
description string New description
homepage string Homepage URL
private bool true for private, false for public
visibility string public or private
has_issues bool Enable/disable Issues tab
has_projects bool Enable/disable Projects tab
has_wiki bool Enable/disable Wiki tab
default_branch string Change default branch name
allow_squash_merge bool Allow squash merging
archived bool Archive the repository

getRepoActivity

Fetches a list of recent activities (pushes, merges, branch changes) for a repository.

Parameters:

Name Type Description
repoName string ✅ Repository name
direction string asc or desc
ref string Git reference (e.g. refs/heads/main)
actor string Filter by username
timePeriod string day, week, or month
activityType string push, force_push, branch_creation, etc.

Returns: Activity ID, user, type, branch, before/after SHA, timestamp.


geAllUserRepo

Lists all repositories for the authenticated user with pagination and sorting.

Parameters:

Name Type Description
per_page int Results per page (default: 30)
page int Page number for pagination
sort string Sort by: created, updated, pushed, full_name

createRepository

Creates a new GitHub repository under the authenticated user.

Parameters:

Name Type Description
name string ✅ Repository name
description string Short description
private bool true for private (default: false)
auto_init bool Initialize with a README

🔌 Connecting an AI Client

Claude Desktop (claude_desktop_config.json)

{
  "mcpServers": {
    "github": {
      "url": "http://localhost:10000/mcp",
      "transport": "http"
    }
  }
}

Python MCP Client

from mcp import ClientSession
from mcp.client.http import http_client

async with http_client("http://localhost:10000/mcp") as (read, write):
    async with ClientSession(read, write) as session:
        await session.initialize()
        result = await session.call_tool("getUserRepo", {"repoName": "my-repo"})
        print(result)

📁 Project Structure

GitHUbMcpServer/
├── gitHubMcpServer.py   # Main MCP server & all tool definitions
├── config.py            # Pydantic settings & .env loader
├── pyproject.toml       # Project metadata & dependencies
├── .python-version      # Python version pin
├── .gitignore           # Git ignore rules
├── uv.lock              # Locked dependency versions
└── README.md            # Project documentation

🤝 Contributing

Contributions, issues and feature requests are welcome!

  1. Fork the repository
  2. Create your feature branch: git checkout -b feature/amazing-feature
  3. Commit your changes: git commit -m "Add amazing feature"
  4. Push to the branch: git push origin feature/amazing-feature
  5. Open a Pull Request

👤 Author

moksh555 · GitHub Profile


<div align="center">

Built with ❤️ using <a href="https://github.com/jlowin/fastmcp">FastMCP</a> & Python

⭐ Star this repo if you find it helpful!

</div>

Recommended Servers

playwright-mcp

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.

Official
Featured
TypeScript
Magic Component Platform (MCP)

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.

Official
Featured
Local
TypeScript
Audiense Insights MCP Server

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.

Official
Featured
Local
TypeScript
VeyraX MCP

VeyraX MCP

Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.

Official
Featured
Local
graphlit-mcp-server

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.

Official
Featured
TypeScript
Kagi MCP Server

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.

Official
Featured
Python
E2B

E2B

Using MCP to run code via e2b.

Official
Featured
Neon Database

Neon Database

MCP server for interacting with Neon Management API and databases

Official
Featured
Exa Search

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.

Official
Featured
Qdrant Server

Qdrant Server

This repository is an example of how to create a MCP server for Qdrant, a vector search engine.

Official
Featured