remote-capable server
The server can be hosted and run remotely because it primarily relies on remote services or has no dependency on the local environment.
Integrations
Leverages Cloudflare Workers for deployment of the MCP server, using Durable Objects for persistent state management and KV storage for token management
Integrates with GitHub's OAuth services for authentication, enabling secure access to the MCP server through GitHub credentials
Acts as a middleware to the upstream Sentry API provider, allowing AI agents to interact with Sentry's monitoring and error tracking capabilities
sentry-mcp
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.
Getting Started
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..
Stdio vs Remote
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 stdout
transport, you'll need to create an Personal API Token (PAT) in Sentry with the necessary scopes. As of writing this is:
Clone the repository and set it up as you normally would:
Launch the transport:
Note: You can also use environment variables:
MCP Inspector
MCP includes an Inspector, to easily test the service:
Enter https://[domain].workers.dev/sse
(TODO) and hit connect. Once you go through the authentication flow, you'll see the Tools working:
Access the remote MCP server from Claude Desktop
Open Claude Desktop and navigate to Settings, press ⌘ + ,
(comma) -> Developer -> Edit Config. This opens the configuration file that controls which MCP servers Claude can access.
Replace the content with the following configuration. Once you restart Claude Desktop, a browser window will open showing your OAuth login page. Complete the authentication flow to grant Claude access to your MCP server. After you grant access, the tools will become available for you to use.
Once the Tools (under 🔨) show up in the interface, you can ask Claude to use them. For example: "Could you use the math tool to add 23 and 19?". Claude should invoke the tool and show the result generated by the MCP server.
Local Development
If you'd like to iterate and test your MCP server, you can do so in local development. This will require you to create another OAuth App in Sentry (Settings => API => Applications):
- For the Homepage URL, specify
http://localhost:8788
- For the Authorized Redirect URIs, specify
http://localhost:8788/callback
- Note your Client ID and generate a Client secret.
- Create a
.dev.vars
file in your project root with:
Verify
Run the server locally to make it available at http://localhost:8788
To test the local server, enter http://localhost:8788/sse
into Inspector and hit connect. Once you follow the prompts, you'll be able to "List Tools".
Tests
There are two test suites included: basic unit tests, and some evaluations.
Unit tests can be run using:
Evals will require a .env
file with some config:
Once thats done you can run them using:
Notes
Using Claude and other MCP Clients
When using Claude to connect to your remote MCP server, you may see some error messages. This is because Claude Desktop doesn't yet support remote MCP servers, so it sometimes gets confused. To verify whether the MCP server is connected, hover over the 🔨 icon in the bottom right corner of Claude's interface. You should see your tools available there.
Using Cursor and other MCP Clients
To connect Cursor with your MCP server, choose Type
: "Command" and in the Command
field, combine the command and args fields into one (e.g. npx mcp-remote https://<your-worker-name>.<your-subdomain>.workers.dev/sse
).
Note that while Cursor supports HTTP+SSE servers, it doesn't support authentication, so you still need to use mcp-remote
(and to use a STDIO server, not an HTTP one).
You can connect your MCP server to other MCP clients like Windsurf by opening the client's configuration file, adding the same JSON that was used for the Claude setup, and restarting the MCP client.
You must be authenticated.
Tools
A remote Model Context Protocol server acting as middleware to the Sentry API, allowing AI assistants like Claude to access Sentry data and functionality through natural language interfaces.