Sentry Mcp

What is Sentry Mcp?

Sentry Mcp delivers a remote MCP service that sits between AI coding assistants and the Sentry API. It translates natural‑language requests from tools like Cursor or Claude Code into Sentry queries and actions, allowing developers to debug and explore incidents without leaving their editor.

How to Use Sentry Mcp?

• Remote mode (default): Run the package with npx @sentry/mcp-server@latest. Supply a Sentry access token and, if you need AI‑powered search tools, configure an LLM provider via environment variables.
• Stdio transport: Useful for self‑hosted setups. Execute the same command with --access-token (and optionally --host for a non‑SaaS Sentry instance). Example: npx @sentry/mcp-server@latest --access-token=YOUR_TOKEN --host=sentry.example.com.
• Inspector: Run pnpm inspector and point the UI at http://localhost:5173 to test the server interactively.
• Configuration: Set SENTRY_ACCESS_TOKEN, EMBEDDED_AGENT_PROVIDER (openai or anthropic), and the corresponding API key (OPENAI_API_KEY or ANTHROPIC_API_KEY). Optional overrides include SENTRY_HOST and MCP_DISABLE_SKILLS.

Key Features

• Remote MCP server that proxies all Sentry endpoints needed by coding assistants.
• Built‑in stdio transport for quick self‑hosted usage.
• AI‑powered search tools (search_events, search_issues, etc.) that translate natural language into Sentry query syntax.
• Ability to disable unsupported skills (e.g., Seer) via flags or environment variables.
• Inspector UI for easy testing of the MCP endpoint.
• Comprehensive local development workflow with OAuth app setup, environment handling, and automated test suites.

Use Cases

• AI‑driven debugging: Ask an assistant "Show me the last 5 errors in project X" and receive structured data from Sentry.
• Incident triage automation: Let a coding assistant create or update issues based on log patterns.
• Self‑hosted Sentry environments: Run the MCP server against on‑prem Sentry installations for internal tooling.
• Custom tooling: Build plugins for IDEs that need direct, authenticated access to Sentry without exposing raw tokens.

FAQ

• Which LLM providers are supported? OpenAI and Anthropic. Set EMBEDDED_AGENT_PROVIDER to openai or anthropic and provide the appropriate API key.
• Do I need a provider for all tools? Only the AI‑powered search tools require an LLM provider. Other tools work with just the Sentry token.
• What scopes does the Sentry access token need? org:read, project:read, project:write, team:read, team:write, event:write.
• How can I disable a skill that my Sentry instance doesn't support? Use the --disable-skills=skill1,skill2 flag or set MCP_DISABLE_SKILLS in the environment.
• Can I run the server locally for development? Yes. Follow the pnpm dev workflow after configuring .env files and an OAuth app.
• What host does the CLI target by default? It targets the Sentry SaaS service. Set SENTRY_HOST or use --host to point to a self‑hosted instance.

sentry-mcp

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.

Getting Started

You'll find everything you need to know by visiting the deployed service in production:

https://mcp.sentry.dev

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.

Note: The AI-powered search tools (search_events, search_issues, etc.) require an LLM provider (OpenAI or Anthropic). 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:

org:read
project:read
project:write
team:read
team:write
event:write

Launch the transport:

npx @sentry/mcp-server@latest --access-token=sentry-user-token

Need to connect to a self-hosted deployment? Add --host (hostname only, e.g. --host=sentry.example.com) when you run the command.

Some features (like Seer) may not be available on self-hosted instances. You can disable specific skills to prevent unsupported tools from being exposed:

npx @sentry/mcp-server@latest --access-token=TOKEN --host=sentry.example.com --disable-skills=seer

Environment Variables

SENTRY_ACCESS_TOKEN=         # Required: Your Sentry auth token

# LLM Provider Configuration (required for AI-powered search tools)
EMBEDDED_AGENT_PROVIDER=     # Required: 'openai' or 'anthropic'
OPENAI_API_KEY=              # Required if using OpenAI
ANTHROPIC_API_KEY=           # Required if using Anthropic

# Optional overrides
SENTRY_HOST=                 # For self-hosted deployments
MCP_DISABLE_SKILLS=          # Disable specific skills (comma-separated, e.g. '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/embedded-agents.md for detailed configuration options.

Example MCP Configuration

{
  "mcpServers": {
    "sentry": {
      "command": "npx",
      "args": ["@sentry/mcp-server"],
      "env": {
        "SENTRY_ACCESS_TOKEN": "your-token",
        "EMBEDDED_AGENT_PROVIDER": "openai",
        "OPENAI_API_KEY": "sk-..."
      }
    }
  }
}

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:

{
  "mcpServers": {
    "sentry": {
      "command": "npx",
      "args": ["@sentry/mcp-server"],
      "env": {
        "SENTRY_ACCESS_TOKEN": "your-token",
        "SENTRY_HOST": "sentry.example.com",
        "MCP_DISABLE_SKILLS": "seer"
      }
    }
  }
}

MCP Inspector

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.

Local Development

To contribute changes, you'll need to set up your local environment:

1. Set up environment files:

   make setup-env  # Creates both .env files from examples
   

2. Create an OAuth App in Sentry (Settings => API => Applications):

   • Homepage URL: http://localhost:5173
   • Authorized Redirect URIs: http://localhost:5173/oauth/callback
   • Note your Client ID and generate a Client secret

3. Configure your credentials:

   • Edit .env in the root directory and add your OPENAI_API_KEY
   • Edit packages/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

4. Start the development server:

   pnpm dev
   

Verify

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".

Tests

There are three test suites included: unit tests, evaluations, and manual testing.

Unit tests can be run using:

pnpm test

Evaluations require a .env file in the project root with some config:

# .env (in project root)
OPENAI_API_KEY=  # Also required for AI-powered search tools in production

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:

pnpm eval

Manual testing (preferred for testing MCP changes):

# Test with local dev server (default: http://localhost:5173)
pnpm -w run cli "who am I?"

# Test agent mode (use_sentry tool only)
pnpm -w run cli --agent "who am I?"

# Test against production
pnpm -w run cli --mcp-host=https://mcp.sentry.dev "query"

# Test with local stdio mode (requires SENTRY_ACCESS_TOKEN)
pnpm -w run cli --access-token=TOKEN "query"

Note: The CLI defaults to http://localhost:5173. Override with --mcp-host or set MCP_URL environment variable.

Comprehensive testing playbooks:

• Stdio testing: See docs/testing-stdio.md for complete guide on building, running, and testing the stdio implementation (IDEs, MCP Inspector)
• Remote testing: See docs/testing-remote.md for complete guide on testing the remote server (OAuth, web UI, CLI client)

Development Notes

Automated Code Review

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:

• ✅ Helpful suggestions to consider during code review
• ✅ Starting points for discussion and improvement
• ❌ Not blocking requirements for merging PRs
• ❌ Not replacements for human code review

When addressing automated feedback, focus on the underlying concerns rather than strictly following every suggestion.

Contributor Documentation

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.