The full upstream README, mirrored here for reference. Install config, tool schemas, adoption signals, and an original overview live on the Sentry MCP listing page.
Sentry's MCP service is primarily designed for human-in-the-loop coding agents. Our tool selection and priorities are focused on developer workflows and debugging use cases, rather than providing a general-purpose MCP server for all Sentry functionality.
This remote MCP server acts as middleware to the upstream Sentry API, optimized for coding assistants like Cursor, Claude Code, and similar development tools. It's 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.
Install as a Claude Code plugin for automatic subagent delegation:
This provides a sentry-mcp subagent that Claude automatically delegates to when you ask about Sentry errors, issues, traces, or performance.
For forward-looking tool variants and features:
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.
Note: The AI-powered search tools (search_events, search_issues, etc.) require an LLM provider (OpenAI, Azure OpenAI, Anthropic, or OpenRouter). These tools use natural language processing to translate queries into Sentry's query syntax. Without a configured provider, these specific tools will be unavailable, but all other tools will function normally.
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:
Launch the transport:
Need to connect to a self-hosted deployment? Add --host (hostname
only, e.g. --host=sentry.example.com) when you run the command.
For isolated internal deployments that only expose plain HTTP, also add
--insecure-http.
Some features (like Seer) may not be available on self-hosted instances. You can disable specific skills to prevent unsupported tools from being exposed:
For self-hosted instances without TLS:
Remote clients that support custom HTTP headers can pass an upstream Sentry API token directly to the Cloudflare transport:
Sentry-Bearer is intentionally separate from Bearer: Bearer is reserved
for MCP OAuth access tokens. With Sentry-Bearer, the worker does not store,
validate, exchange, or refresh the upstream token. It forwards the token through
the same Sentry API calls used by OAuth-backed sessions, and the client or
upstream provider remains responsible for token lifetime and refresh.
Direct remote auth defaults to all active MCP skills. You can narrow the exposed
tools with ?skills=inspect,triage or ?disable-skills=seer.
Important: Always set EMBEDDED_AGENT_PROVIDER to explicitly specify your LLM provider. Auto-detection based on API keys alone is deprecated and will be removed in a future release. See docs/operations/embedded-agents.md for detailed configuration options.
If you leave the host variable unset, the CLI automatically targets the Sentry SaaS service. Only set the override when you operate self-hosted Sentry.
For self-hosted instances that don't support Seer:
MCP includes an Inspector, to easily test the service:
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, you'll need to set up your local environment:
Set up environment and agent skills:
This also runs npx @sentry/dotagents install to install shared skills from getsentry/skills into .agents/skills/ (symlinked into .claude/skills and .cursor/skills). If you need to update skills later, run it directly:
Create an OAuth App in Sentry (Settings => API => Applications):
http://localhost:5173http://localhost:5173/oauth/callbackConfigure your credentials:
.env in the root directory and add either OPENAI_API_KEY or OPENROUTER_API_KEYpackages/mcp-cloudflare/.env and add:
SENTRY_CLIENT_ID=your_development_sentry_client_idSENTRY_CLIENT_SECRET=your_development_sentry_client_secretCOOKIE_SECRET=my-super-secret-cookieStart the development server:
Run the server locally to make it available at http://localhost:5173
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 three test suites included: unit tests, evaluations, and manual testing.
Unit tests can be run using:
Evaluations require a .env file in the project root with some config:
Note: The root .env file provides defaults for all packages. Individual packages can have their own .env files to override these defaults during development.
Once that's done you can run them using:
Manual testing (preferred for testing MCP changes):
Note: The CLI defaults to http://localhost:5173. Override with --mcp-host or set MCP_URL environment variable.
Comprehensive testing playbooks:
docs/testing/stdio.md for complete guide on building, running, and testing the stdio implementation (IDEs, MCP Inspector)docs/testing/remote.md for complete guide on testing the remote server (OAuth, web UI, CLI client)This repository uses automated code review tools (like Cursor BugBot) to help identify potential issues in pull requests. These tools provide helpful feedback and suggestions, but we do not recommend making these checks required as the accuracy is still evolving and can produce false positives.
The automated reviews should be treated as:
When addressing automated feedback, focus on the underlying concerns rather than strictly following every suggestion.
Looking to contribute or explore the full documentation map? See CLAUDE.md (also available as AGENTS.md) for contributor workflows and the complete docs index. The docs/ folder contains the per-topic guides and tool-integrated .md files.