Github Issues

🚀 GitHub MCP Server

An implementation of the Model Context Protocol (MCP) server that interacts with GitHub issues via Cline.

🚀 Quick Start

The GitHub MCP Server is an implementation of the Model Context Protocol (MCP) that enables interaction with GitHub issues through Cline. It provides a set of tools to list, create, and manage GitHub issues securely.

✨ Features

• List GitHub issues in a repository.
• Create new GitHub issues.
• Handle errors and perform validation.
• Implement secure authentication via environment variables.

📦 Installation

1. Clone the repository:

git clone https://github.com/timbuchinger/mcp-github.git
cd mcp-github

2. Install dependencies using uv:

pip install uv
uv venv
source .venv/bin/activate  # On Windows: .venv\Scripts\activate
uv pip install -r requirements.txt

3. Copy the environment variable template and configure your GitHub token:

cp .env.template .env

Edit the .env file and add your GitHub personal access token:

GITHUB_TOKEN=your_token_here

How to create a GitHub personal access token:

1. Go to GitHub Settings -> Developer settings -> Personal access tokens.
2. Generate a new token with the repo permission.
3. Copy the token and paste it into your .env file.

💻 Usage Examples

Basic Usage

Run the MCP server:

python -m src.mcp_github.server

The server exposes two tools to Cline:

get_issues

Get a list of issues from a GitHub repository:

{
  "repo": "owner/repo"
}

create_issue

Create a new issue in a GitHub repository:

{
  "repo": "owner/repo",
  "title": "Issue Title",
  "body": "Issue Description"
}

📚 Documentation

Error Handling

The server handles common errors:

• Missing GitHub token.
• Invalid repository name.
• Missing required parameters.
• GitHub API errors.

Error responses include descriptive messages to assist with troubleshooting.

🔧 Technical Details

Development

This project uses uv for dependency management. To set up the development environment:

# Install all dependencies (including development dependencies)
uv pip install -r requirements.txt

# Run tests
pytest

# Format code
black .

# Type check
mypy .