Sentry MCP Server

Official

Investigate errors, analyze issues, and debug with AI using Sentry data

GitHub950
sentryerror-monitoringdebuggingofficialerrors

The official Sentry MCP server connects your AI assistant to your Sentry error monitoring account. Retrieve issues, read stack traces, understand error frequency, and get AI-assisted debugging suggestions — all from your AI client. Authenticated via a Sentry auth token. Particularly powerful when combined with your codebase context, letting the AI see both the error and the relevant code at the same time.

Install Config

Config file: ~/Library/Application Support/Claude/claude_desktop_config.json· Windows: %APPDATA%\Claude\claude_desktop_config.json

{
  "mcpServers": {
    "sentry": {
      "command": "npx",
      "args": [
        "-y",
        "@sentry/mcp-server"
      ],
      "env": {
        "SENTRY_AUTH_TOKEN": "your_auth_token",
        "SENTRY_ORG_SLUG": "your-org-slug"
      }
    }
  }
}

Required environment variables:

  • SENTRY_AUTH_TOKENSentry authentication token(e.g. sntrys_eyJia...)
  • SENTRY_ORG_SLUGYour Sentry organization slug(e.g. my-org)

Available Tools (4)

Tool nameDescription
get_sentry_issueGet details for a specific Sentry issue including stack trace
list_sentry_issuesList recent issues filtered by project, status, or query
get_sentry_eventGet a specific error event with full context
list_sentry_projectsList all Sentry projects in your organization

Example Prompts

  • Show me the top 5 unresolved errors in my project
  • What caused Sentry issue PROJ-1234?
  • Are there any new errors in production this week?
  • Get the full stack trace for the most recent error
  • List all issues tagged as 'performance'

Pros & Cons

Pros

  • Official Sentry server — maintained by Sentry's team
  • Read full stack traces and error context
  • Powerful when combined with codebase access

Cons

  • Requires a Sentry account and project
  • Read-only — cannot resolve or assign issues

Who Is This For?

  • ·Backend developers who use Sentry for error monitoring
  • ·On-call engineers who want AI assistance during incident response

When to use: Use when you're debugging production errors and want the AI to understand the full stack trace context alongside your code.

Supported Clients