Spark
Sign In
MCP Connector

Integrate Sentry for Error Monitoring

The Sentry MCP server lets Claude view Sentry.io issues, analyze error stack traces, and help debug production errors.

Connect
Works with sentry
VibeBaza
Own this? Claim it
78
Spark score
out of 100
Updated 7 months ago
Fresher alternatives ↓
Version 1.0.0
Models
universal
Add to Favorites

Why it matters

Connect your AI to Sentry.io to automatically view, analyze, and debug application errors. Streamline your DevOps workflow by gaining immediate insights into issues and their root causes.

Outcomes

What it gets done

01

List and retrieve details of Sentry issues.

02

Analyze error stack traces and event breadcrumbs.

03

Resolve issues directly through AI commands.

04

Monitor application health and error patterns.

Install

Add it to your toolbox

Run in your project directory:

curl -fsSL https://spark.entire.vc/get/vb-sentry | bash

Capabilities

Tools your agent gets

list_organizations

List all organizations you have access to.

list_projects

List projects in an organization.

list_issues

List issues for a project with optional query filtering.

get_issue

Get detailed information about a specific issue.

get_issue_events

Get events associated with an issue.

resolve_issue

Resolve an issue in Sentry.

Overview

Sentry MCP

The Sentry MCP server gives Claude tools to list organizations, projects, and issues, inspect stack traces and event details, and resolve issues directly against Sentry.io. Use it when debugging production errors, prioritizing fixes, or investigating a specific user-reported issue already captured in Sentry.

What it does

The Sentry MCP server integrates Claude with Sentry.io for error tracking and application monitoring. It exposes tools to list organizations and projects, list and inspect issues, retrieve the events associated with an issue, and resolve an issue directly - letting Claude view unresolved issues, analyze error stack traces, see error frequency and impact, and track issue status and assignments without leaving the conversation.

When to use - and when NOT to

Use this when debugging production errors, prioritizing bug fixes, understanding recurring error patterns, monitoring overall application health, or investigating a specific user-reported issue - any workflow where Sentry is already the source of truth for error data. It is not a replacement for Sentry's own alerting or performance-monitoring dashboards; it is a read-and-triage layer that surfaces and acts on issue data already captured by Sentry.

Inputs and outputs

Tools include list_organizations() returning an organization list, list_projects(organization_slug) returning a project list, list_issues(organization_slug, project_slug, query?) returning matching issues, get_issue(issue_id) returning issue details, get_issue_events(issue_id) returning the event list for that issue, and resolve_issue(issue_id) which marks an issue resolved and returns the result.

Integrations

Installed via uvx mcp-server-sentry (or pip install mcp-server-sentry) and configured with a SENTRY_AUTH_TOKEN created in Sentry under Settings > Auth Tokens, scoped to project:read, issue:read, event:read, and org:read. It is configured directly in Claude Code's MCP settings.

Who it's for

Developers and on-call engineers who want to triage and analyze Sentry issues conversationally with Claude - reviewing recent unresolved issues, digging into a specific stack trace, or resolving an issue once it is fixed.

uvx mcp-server-sentry
Source README

The Sentry MCP server provides integration with Sentry.io for error tracking and application monitoring. It enables Claude to view issues, analyze errors, and help with debugging.

Installation

Using uvx (recommended):

uvx mcp-server-sentry

Using pip:

pip install mcp-server-sentry

Configuration

Add to your Claude Code settings:

{
  "mcpServers": {
    "sentry": {
      "command": "uvx",
      "args": ["mcp-server-sentry"],
      "env": {
        "SENTRY_AUTH_TOKEN": "your_auth_token_here"
      }
    }
  }
}

Getting an Auth Token

  1. Log in to Sentry.io
  2. Go to Settings → Auth Tokens
  3. Create a new token with the following scopes:
    • project:read
    • issue:read
    • event:read
    • org:read

Available Tools

list_organizations

List all organizations you have access to.

list_organizations(): OrganizationList

list_projects

List projects in an organization.

list_projects(organization_slug: string): ProjectList

list_issues

List issues for a project.

list_issues(
  organization_slug: string,
  project_slug: string,
  query?: string
): IssueList

get_issue

Get detailed information about an issue.

get_issue(issue_id: string): IssueDetails

get_issue_events

Get events associated with an issue.

get_issue_events(issue_id: string): EventList

resolve_issue

Resolve an issue.

resolve_issue(issue_id: string): ResolveResult

Features

  • View unresolved issues
  • Analyze error stack traces
  • See error frequency and impact
  • Track issue status and assignments
  • Access event details and breadcrumbs

Usage Example

Claude, show me the most recent unresolved issues in our
production project and analyze the top error's stack trace.

Use Cases

  • Debugging production errors
  • Prioritizing bug fixes
  • Understanding error patterns
  • Monitoring application health
  • Investigating user-reported issues

FAQ

Common questions

Discussion

Questions & comments · 0

Sign In Sign in to leave a comment.