Sentry MCP Server 🔍
A TypeScript implementation of a Sentry MCP (Modern Context Protocol) tool that allows AI agents to access and analyze Sentry error data. 🤖
✨ Features
- 🎯 Retrieve and analyze Sentry issues
- 📊 Get formatted issue details and metadata
- 🔬 View detailed stacktraces
- 🛠️ Support for both tool and prompt interfaces
- 🛡️ Robust error handling
- 🔄 Real-time communication
📦 Installation
🔧 Configuration
Create a .env file in the root directory with your Sentry auth token:
SENTRY_AUTH_TOKEN=your_sentry_auth_token
SENTRY_API_BASE=https://sentry.io/api/0/ # Optional, defaults to this value
📚 Usage
Starting the Server 🚀
The server will start on port 1337 by default.
Using with MCP 🛠️
The server provides two MCP interfaces:
- Tool Interface:
get_sentry_issue{
"issue_id_or_url": "12345"
}
- Prompt Interface:
sentry-issue{
"issue_id_or_url": "https://sentry.io/organizations/your-org/issues/12345/"
}
💡 Integrating with Cursor IDE
The Sentry MCP Server can be integrated with Cursor IDE for enhanced development experience:
- 🚀 Start the MCP server locally using
pnpm start - 🔧 Configure Cursor to use the local MCP server:
- 🎉 Enjoy seamless Sentry issue analysis directly in your IDE!
🤝 Contributing
- 🔀 Fork the repository
- 🌿 Create your feature branch
- 💾 Commit your changes
- 🚀 Push to the branch
- 📬 Create a new Pull Request