Incident Response Debugger Agent
Performs deep root cause analysis through code path tracing, git bisect automation, dependency analysis, and systematic hypothesis testing for production bugs.
by Sentry
Sentry's official MCP server gives an AI agent direct access to your Sentry data: issues, errors, projects, and Seer's root-cause analysis. Sentry hosts it as a remote server (Streamable HTTP with OAuth) at mcp.sentry.dev, and also publishes a local stdio server, so an agent can pull real error context while you debug.
The Model Context Protocol (MCP).
Setup steps with copy-paste config. Sources are cited under each method.
Requires: An MCP host that supports remote servers · A Sentry account
Add the hosted endpoint
Point your host at Sentry's remote MCP endpoint and authorize over OAuth — nothing to install.
https://mcp.sentry.dev/mcpAuthorize
Complete the OAuth flow and grant access to the org/projects the agent should read.
Requires: Node.js · A Sentry auth token
Add to your MCP config
Run the local stdio server with a Sentry access token scoped to the projects you want to expose.
{
"mcpServers": {
"sentry": {
"command": "npx",
"args": ["-y", "@sentry/mcp-server@latest"],
"env": { "SENTRY_ACCESS_TOKEN": "<your-token>" }
}
}
}Copy-paste prompts written to exercise this plugin, with what to expect.
A new error spiked after a deploy.
Find the most frequent unresolved issue in my project from the last 24 hours, show its stack trace, and tell me the likely cause and which file to look at.
What to expect: The agent pulls the real issue and stack trace from Sentry and points you at the probable code path instead of guessing.
Real prompts from the IterPrompt library you can copy or run.
Performs deep root cause analysis through code path tracing, git bisect automation, dependency analysis, and systematic hypothesis testing for production bugs.
Analyzes error traces, logs, and observability data to identify error signatures, reproduction steps, user impact, and timeline context for production issues.
Create production-ready FastAPI projects with async patterns, dependency injection, and comprehensive error handling. Use when building new FastAPI applications or setting up backe
Build production-ready Node.js backend services with Express/Fastify, implementing middleware patterns, error handling, authentication, database integration, and API design best pr
Pulls recent production logs filtered for errors, warnings, and anomalies. Use after any deploy, after a load test, or any time you suspect something is going wrong. Treats logs as
Stop guessing at fixes — isolate the actual cause of a bug step by step.
No — the remote server at mcp.sentry.dev uses Streamable HTTP with OAuth, so you just add the URL and authorize. A local stdio server is available if you prefer.
The facts on this page and where they come from. Anything unverified is labeled — we'd rather say "unknown" than guess.
Install steps, pricing, and availability change often. Always confirm on the official page before relying on setup details.