github-mcp
Enables AI assistants to interact with GitHub repositories, issues, pull requests, and content via the Model Context Protocol.
README
GitHub MCP Server

A Model Context Protocol (MCP) server that provides GitHub integration tools for AI assistants. This server implements a set of tools that allow AI models to interact with GitHub repositories, issues, pull requests, and content.
Features
- Repository Management
- List repositories
- Get repository details
- Issue Management
- List issues
- Create issues
- Pull Request Management
- List pull requests
- Create pull requests
- Content Management
- Get file content
- List directory contents
Installation
- Clone the repository:
git clone https://github.com/yourusername/github-mcp.git
cd github-mcp
- Install the package:
pip install -e .
Authentication
This server uses githubauthlib for secure GitHub authentication. The library retrieves GitHub tokens from your system's keychain:
- macOS: Uses Keychain Access
- Windows: Uses Credential Manager
- Linux: Uses libsecret
To set up authentication:
-
Install the required system dependencies:
-
macOS: No additional setup required
-
Windows: No additional setup required
-
Linux: Install libsecret
# Ubuntu/Debian sudo apt-get install libsecret-tools # Fedora sudo dnf install libsecret
-
-
Configure your GitHub credentials:
-
The server will automatically use your Git credentials from the system keychain
-
If no credentials are found, you'll need to configure Git with your GitHub credentials:
git config --global credential.helper store # Then perform a Git operation that requires authentication
-
Usage
- Start the server:
python -m github_mcp.server
The server will start on http://localhost:8000 by default.
- Configure Cursor IDE:
-
Open Cursor IDE settings
-
Add the following MCP server configuration:
{ "mcp": { "servers": [ { "name": "github-mcp", "url": "http://localhost:8000/sse" } ] } }
-
API Endpoints
GET /: Server information and available toolsPOST /tool: Synchronous tool callsGET /sse: Server-Sent Events endpoint for streaming responses
Available Tools
Repository Tools
list_repositories: List GitHub repositories- Parameters:
visibility(optional): "all", "public", or "private"sort(optional): "created", "updated", "pushed", or "full_name"
- Parameters:
get_repository: Get repository details- Parameters:
owner: Repository ownerrepo: Repository name
- Parameters:
Issue Tools
list_issues: List repository issues- Parameters:
owner: Repository ownerrepo: Repository namestate(optional): "open", "closed", or "all"labels(optional): List of label names
- Parameters:
create_issue: Create a new issue- Parameters:
owner: Repository ownerrepo: Repository nametitle: Issue titlebody(optional): Issue descriptionlabels(optional): List of label namesassignees(optional): List of assignee usernames
- Parameters:
Pull Request Tools
list_pull_requests: List repository pull requests- Parameters:
owner: Repository ownerrepo: Repository namestate(optional): "open", "closed", or "all"sort(optional): "created", "updated", "popularity", or "long-running"
- Parameters:
create_pull_request: Create a new pull request- Parameters:
owner: Repository ownerrepo: Repository nametitle: Pull request titlebody(optional): Pull request descriptionhead: Source branchbase(optional): Target branch (default: "main")draft(optional): Create as draft (default: false)
- Parameters:
Content Tools
get_file_content: Get file content- Parameters:
owner: Repository ownerrepo: Repository namepath: File pathref(optional): Branch/tag/commit reference
- Parameters:
list_directory: List directory contents- Parameters:
owner: Repository ownerrepo: Repository namepath(optional): Directory path (default: "")ref(optional): Branch/tag/commit reference
- Parameters:
Development
- Install development dependencies:
pip install -e ".[dev]"
- Run tests:
pytest
- Run linting:
ruff check .
License
This project is licensed under the MIT License - see the LICENSE file for details.
Contributing
- Fork the repository
- Create your feature branch (
git checkout -b feature/amazing-feature) - Commit your changes (
git commit -m 'Add amazing feature') - Push to the branch (
git push origin feature/amazing-feature) - Open a Pull Request
Acknowledgments
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
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.
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.