A Model Context Protocol (MCP) server designed to retrieve and analyze issues from Sentry.io. This server enables AI assistants to access detailed error reports, stack traces, and debugging information from your Sentry account.
The Sentry Integration MCP Server provides tools for inspecting and analyzing Sentry issues, making it easier to debug and resolve application errors. It integrates seamlessly with AI assistants like Claude and Zed, offering a streamlined workflow for error analysis.
issue_id_or_url
(string): Sentry issue ID or URL to analyze.issue_id_or_url
(string): Sentry issue ID or URL.npm install -g mcp-sentry
After installation, run the server:
mcp-sentry --auth-token YOUR_SENTRY_TOKEN
Or use the environment variable:
SENTRY_TOKEN=YOUR_SENTRY_TOKEN mcp-sentry
npx mcp-sentry --auth-token YOUR_SENTRY_TOKEN
mcp-sentry/
├── src/
│ ├── index.ts # Main entry point
│ ├── server.ts # MCP server implementation
│ ├── sentry-client.ts # Sentry API client
│ ├── models.ts # Data models
│ ├── utils.ts # Utility functions
│ └── types/ # Type definitions
├── build/ # Compiled JavaScript files
├── package.json
├── tsconfig.json
└── README.md
npm run build
npm run dev -- --auth-token YOUR_SENTRY_TOKEN
The server requires a Sentry authentication token, which can be provided via:
Command-line option:
shell
mcp-sentry --auth-token YOUR_SENTRY_TOKEN
Environment variable:
shell
SENTRY_TOKEN=YOUR_SENTRY_TOKEN mcp-sentry
Add this to your Claude Desktop configuration:
"mcpServers": {
"sentry": {
"command": "mcp-sentry",
"args": ["--auth-token", "YOUR_SENTRY_TOKEN"]
}
}
Add to your Zed settings.json:
"context_servers": [
"mcp-server-sentry": {
"command": {
"path": "mcp-sentry",
"args": ["--auth-token", "YOUR_SENTRY_TOKEN"]
}
}
],
Use the MCP inspector to debug the server:
npx @modelcontextprotocol/inspector mcp-sentry --auth-token YOUR_SENTRY_TOKEN
This project is licensed under the MIT License.
MCP server for interacting with Sentry.