An MCP server for interacting with Sentry via LLMs.
This is a prototype of a remote MCP sever, acting as a middleware to the upstream Sentry API provider.
It is based on Cloudflare’s work towards remote MCPs.
You’ll find everything you need to know by visiting the deployed service in production:
If you’re looking to contribute, learn how it works, or to run this for self-hosted Sentry, continue below…
While this repository is focused on acting as an MCP service, we also support a stdio transport. This is still a work in progress, but is the easiest way to adapt run the MCP against a self-hosted Sentry install.
To utilize the stdio transport, you’ll need to create an User Auth Token in Sentry with the necessary scopes. As of writing this is:
org:read
project:read
project:write
team:read
team:write
event:read
Launch the transport:
npx @sentry/mcp-server@latest --access-token=sentry-user-token --host=sentry.example.com
Note: You can also use environment variables:
SENTRY_ACCESS_TOKEN=
SENTRY_HOST=
MCP includes an Inspector, to easily test the service:
pnpm inspector
Enter the MCP server URL (http://localhost:5173) and hit connect. This should trigger the authentication flow for you.
Note: If you have issues with your OAuth flow when accessing the inspector on 127.0.0.1, try using localhost instead by visiting http://localhost:6274.
To contribute changes against the server, you’ll need to set things up in in local development. This will require you to create another OAuth App in Sentry (Settings => API => Applications):
http://localhost:5173http://localhost:5173/callback.dev.vars file in packages/mcp-cloudflare/ root with:## packages/mcp-cloudflare/.dev.vars
SENTRY_CLIENT_ID=your_development_sentry_client_id
SENTRY_CLIENT_SECRET=your_development_sentry_client_secret
COOKIE_SECRET=my-super-secret-cookie
Run the server locally to make it available at http://localhost:5173
pnpm dev
To test the local server, enter http://localhost:5173/mcp into Inspector and hit connect. Once you follow the prompts, you’ll be able to “List Tools”.
There are two test suites included: basic unit tests, and some evaluations.
Unit tests can be run using:
pnpm test
Evals will require a .env file with some config:
OPENAI_API_KEY=
Once thats done you can run them using:
pnpm test
An MCP (Model Context Protocol) tool that provides real-time weather data, forecasts, and historical weather information using the OpenWeatherMap API, specifically designed for Claude Desktop.
Ragie Model Context Protocol Server
Model Context Protocol server for OpenStreetMap data
This Model Context Protocol (MCP) server enables LLMs like Claude to perform internet research using the Perplexity API. It provides real-time, up-to-date information with source citations.
