GitHub MCP Tools
A Multi-Claude Program for interacting with GitHub APIs through Claude Desktop, allowing users to search repositories, manage issues, pull requests, repository settings, workflows, and collaborators.
README
GitHub MCP Tools
A Multi-Claude Program (MCP) for interacting with GitHub APIs through Claude Desktop.
Features
- Search GitHub repositories and issues
- Create, update, and manage GitHub issues and pull requests
- Manage repository settings and configurations
- Handle repository workflows and actions
- Search for users and organizations
- Manage repository collaborators and teams
Installation
-
Clone this repository:
git clone https://github.com/yourusername/github-mcp.git cd github-mcp -
Create and activate a virtual environment:
# On macOS/Linux python -m venv venv source venv/bin/activate # On Windows python -m venv venv .\venv\Scripts\activate -
Install dependencies:
pip install -r requirements.txt -
Create a
.envfile in the project root:touch .env -
Add your GitHub credentials to the
.envfile:GITHUB_TOKEN=your_personal_access_token_here GITHUB_USERNAME=your_github_username -
Test the installation:
# Run all tests python -m pytest # Run a specific test file python -m pytest tests/test_search_repos.py -
Start the MCP server:
python run.py
Environment Setup
GitHub Personal Access Token
You'll need a fine-grained personal access token to authenticate with GitHub:
- Log in to your GitHub account
- Go to Settings > Developer settings > Personal access tokens > Fine-grained tokens
- Click "Generate new token"
- Configure the token:
- Token name: "Claude Desktop Integration"
- Description: "Token for Claude Desktop GitHub integration"
- Expiration: Choose an appropriate expiration date
- Repository access: Select "All repositories" or specific repositories
- Permissions:
- Repository permissions:
- Actions: Read and write
- Contents: Read and write
- Issues: Read and write
- Pull requests: Read and write
- Repository hooks: Read and write
- Repository settings: Read and write
- Organization permissions (if working with organization repositories):
- Members: Read-only
- Teams: Read-only
- Repository permissions:
- Click "Generate token" and save the generated token securely
Tools
Search Repositories
Search for GitHub repositories using various criteria.
Parameters:
- query: Search query string
- sort: Sort field (stars, forks, updated, etc.)
- order: Sort order (asc or desc)
- max_results: Maximum number of results to return (default: 10)
Create Issue
Create a new GitHub issue in a specified repository.
Parameters:
- owner: Repository owner
- repo: Repository name
- title: Issue title
- body: Issue description
- labels: List of labels to apply
- assignees: List of assignee usernames
Create Pull Request
Create a new pull request.
Parameters:
- owner: Repository owner
- repo: Repository name
- title: PR title
- body: PR description
- head: Source branch
- base: Target branch
- draft: Whether to create as draft PR
Manage Repository Settings
Update repository settings and configurations.
Parameters:
- owner: Repository owner
- repo: Repository name
- settings: Dictionary of settings to update
Search Issues
Search for issues across repositories.
Parameters:
- query: Search query string
- state: Issue state (open, closed, all)
- sort: Sort field
- order: Sort order
- max_results: Maximum number of results
Manage Workflows
Manage GitHub Actions workflows.
Parameters:
- owner: Repository owner
- repo: Repository name
- workflow_file: Workflow file path
- action: Action to perform (enable, disable, trigger)
Manage Collaborators
Manage repository collaborators.
Parameters:
- owner: Repository owner
- repo: Repository name
- username: Collaborator username
- permission: Permission level (pull, push, admin, maintain, triage)
Example Usage
# Search for repositories
search_repos(query="python web framework", sort="stars", max_results=5)
# Create a new issue
create_issue(
owner="username",
repo="repository",
title="Bug: Login not working",
body="Users cannot log in using the login button",
labels=["bug", "high-priority"]
)
# Create a pull request
create_pull_request(
owner="username",
repo="repository",
title="Feature: Add user authentication",
body="Implements JWT-based authentication",
head="feature/auth",
base="main"
)
# Search for issues
search_issues(query="is:open is:issue author:username", max_results=10)
# Manage repository settings
manage_repo_settings(
owner="username",
repo="repository",
settings={
"has_issues": True,
"has_projects": True,
"has_wiki": True
}
)
Development
Running Tests
# Run all tests
python -m pytest
# Run with coverage
python -m pytest --cov=src tests/
# Run specific test file
python -m pytest tests/test_search_repos.py
Adding New Tools
- Create a new file in
src/tools/ - Implement your tool function
- Register the tool in
src/main.py - Add tests in
tests/ - Update documentation in README.md
Contributing
- Fork the repository
- Create a feature branch
- Make your changes
- Run tests
- Submit a pull request
License
MIT License
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.