Sentry MCP Server is a middleware service designed for human-in-the-loop coding agents, optimizing the connection between development tools like Cursor and Claude Code to Sentry's API. It focuses specifically on developer workflows and debugging use cases, making it easier to integrate AI coding assistants with Sentry functionality.
The easiest way to use Sentry MCP is through the deployed production service:
For self-hosted Sentry installations, you can use the stdio transport:
Create a User Auth Token in your Sentry instance with these scopes:
Launch the transport using npx:
npx @sentry/mcp-server@latest --access-token=sentry-user-token --host=sentry.example.com
Alternatively, use environment variables:
SENTRY_ACCESS_TOKEN=your-token-here
SENTRY_HOST=sentry.example.com
OPENAI_API_KEY=your-openai-key # Required only for AI-powered search tools
Note: The AI-powered search tools (search_events
and search_issues
) require an OpenAI API key for natural language processing to translate queries into Sentry's query syntax.
To test the service easily, use the built-in Inspector tool:
pnpm inspector
Connect to your MCP server by entering the URL (e.g., http://localhost:5173
for local development) and follow the authentication flow.
Tip: If you encounter OAuth flow issues with 127.0.0.1
, try using localhost
instead (http://localhost:6274
).
To run the server locally:
make setup-env
Create an OAuth App in your Sentry instance:
http://localhost:5173
http://localhost:5173/oauth/callback
Configure your credentials:
OPENAI_API_KEY
to the root .env
filepackages/mcp-cloudflare/.env
and add:
SENTRY_CLIENT_ID=your_development_sentry_client_id
SENTRY_CLIENT_SECRET=your_development_sentry_client_secret
COOKIE_SECRET=my-super-secret-cookie
Start the development server:
pnpm dev
The server will be available at http://localhost:5173
. To verify it's working:
http://localhost:5173/mcp
To run the unit test suite:
pnpm test
To run the evaluation tests:
.env
file in the project root with your OpenAI API key:OPENAI_API_KEY=your-openai-api-key
pnpm eval
To add this MCP server to Claude Code, run this command in your terminal:
claude mcp add-json "sentry-mcp" '{"command":"npx","args":["@sentry/mcp-server@latest"]}'
See the official Claude Code MCP documentation for more details.
There are two ways to add an MCP server to Cursor. The most common way is to add the server globally in the ~/.cursor/mcp.json
file so that it is available in all of your projects.
If you only need the server in a single project, you can add it to the project instead by creating or adding it to the .cursor/mcp.json
file.
To add a global MCP server go to Cursor Settings > Tools & Integrations and click "New MCP Server".
When you click that button the ~/.cursor/mcp.json
file will be opened and you can add your server like this:
{
"mcpServers": {
"sentry-mcp": {
"command": "npx",
"args": [
"@sentry/mcp-server@latest"
]
}
}
}
To add an MCP server to a project you can create a new .cursor/mcp.json
file or add it to the existing one. This will look exactly the same as the global MCP server example above.
Once the server is installed, you might need to head back to Settings > MCP and click the refresh button.
The Cursor agent will then be able to see the available tools the added MCP server has available and will call them when it needs to.
You can also explicitly ask the agent to use the tool by mentioning the tool name and describing what the function does.
To add this MCP server to Claude Desktop:
1. Find your configuration file:
~/Library/Application Support/Claude/claude_desktop_config.json
%APPDATA%\Claude\claude_desktop_config.json
~/.config/Claude/claude_desktop_config.json
2. Add this to your configuration file:
{
"mcpServers": {
"sentry-mcp": {
"command": "npx",
"args": [
"@sentry/mcp-server@latest"
]
}
}
}
3. Restart Claude Desktop for the changes to take effect