Set it up
- 1
Turn on Sentry in your AI
In Claude: open Settings → Connectors and add Sentry. In ChatGPT: Settings → Apps & Connectors.
- 2
Add it to your app once
Copy the short config below into your app. It just tells your AI where to find Sentry.
- 3
Just ask
Tell it what you want in plain words — no special commands.
For example, say
“Show me the top 3 unresolved errors in my Sentry project from the last 24 hours”
Need the exact config? Show it +
Add to your client
{
"mcpServers": {
"sentry": {
"command": "npx",
"args": ["-y", "mcp-remote", "https://mcp.sentry.dev/sse"]
}
}
}Paste into your client's MCP configuration file.
Get the skill
A ready-made skill that teaches your AI agent to use Sentry well. Sentry's official Claude Code plugin + skills for debugging.
/install-plugin sentry Quick skills
Copy one, paste it to your AI, watch it work.
Error Triage
“Show me the top 5 unresolved errors in the production project from the last 24 hours”
Stack Trace Analysis
“Look up Sentry issue PROD-1234 and explain what the stack trace suggests is wrong”
Trend Investigation
“Show me the trend of this error over the last 7 days — is it getting worse?”
In the wild
“I can investigate production errors without ever logging into Sentry. Get a notification, ask Claude to look into it, get a detailed analysis. The MCP handles authentication and API calls behind the scenes.”
Good to know
- · Sentry auth tokens should be scoped to the specific organization and project — avoid broad scopes
- · Issue IDs and slugs differ — some endpoints need one, some the other
- · High-frequency error projects can return huge result sets — use time ranges and filters
When to use
- ✓ You use Sentry for error tracking and want AI-assisted triage
- ✓ You need to investigate a specific error without opening the Sentry UI
- ✓ You want to summarize top errors across projects for a standup
- ✓ You're building workflows that auto-investigate new issues
When not to use
- × You use Rollbar, Datadog, or another error tracking service
- × You need real-time streaming of new errors as they happen
- × You only use Sentry for performance monitoring (not its focus)
About
Imagine asking your AI: 'What are our top 5 production errors from the last 24 hours?' or 'Summarize the stack trace of this issue' — and it pulls real data from Sentry. This server connects your AI to Sentry so it can query issues, read stack traces, and help you debug production errors through conversation.
The official Sentry MCP server connects AI assistants to your Sentry error monitoring data. Query issues, analyze error patterns, get stack traces, and let AI help you prioritize and fix bugs faster.
Maintained by Sentry with OAuth authentication support. One of the most useful devtools integrations for production debugging.
Workflows That Use Sentry MCP
An alert fires. In one prompt Claude reads the stack trace, pulls the code, judges severity, and writes the GitHub issue you'd have written by hand.
GitHub, Git, Docker, Kubernetes and Sentry in one chat — review, ship, and debug without tab-switching.
Works With
FAQ
What does Sentry MCP do? +
Imagine asking your AI: 'What are our top 5 production errors from the last 24 hours?' or 'Summarize the stack trace of this issue' — and it pulls real data from Sentry. This server connects your AI to Sentry so it can query issues, read stack traces, and help you debug production errors through conversation.
Do I need to know how to code? +
No. Turn it on in your AI's settings and ask in plain English — no terminal, no coding.
When should I use Sentry MCP? +
Reach for it when you need to: You use Sentry for error tracking and want AI-assisted triage; You need to investigate a specific error without opening the Sentry UI; You want to summarize top errors across projects for a standup; You're building workflows that auto-investigate new issues.
When should I avoid Sentry MCP? +
Skip it when: You use Rollbar, Datadog, or another error tracking service; You need real-time streaming of new errors as they happen; You only use Sentry for performance monitoring (not its focus).
How do I install Sentry MCP? +
In Claude Code, run: claude mcp add --transport sse sentry https://mcp.sentry.dev/sse. Copy-paste configs for Claude Desktop, Cursor, and Windsurf are at the top of this page.
