Sentry

Name: Sentry
Author: javaDer

@javaDer

Repository

About Sentry

No overview available yet

#mcp-sentry #sentry-server #error-analysis

Basic information

Config

Add this server to your MCP-compatible client using the configuration below.

{
  "mcpServers": {
    "sentry": {
      "command": "uvx",
      "args": [
        "mcp-sentry-custom",
        "--auth-token",
        "YOUR_SENTRY_TOKEN",
        "--project-slug",
        "YOUR_PROJECT_SLUG",
        "--organization-slug",
        "YOUR_ORGANIZATION_SLUG",
        "--sentry-url",
        "YOUR_SENTRY_URL"
      ]
    }
  }
}

Tools

Retrieve and analyze a Sentry issue by ID or URL. Use this tool when you need to: - Investigate production errors and crashes - Access detailed stacktraces from Sentry - Analyze error patterns and frequencies - Get information about when issues first/last occurred - Review error counts and status

Retrieve and analyze Sentry issues by project slug. Use this tool when you need to: - Investigate production errors and crashes - Access detailed stacktraces from Sentry - Analyze error patterns and frequencies - Get information about when issues first/last occurred - Review error counts and status

Overview

What is Sentry?

Sentry is an MCP server that retrieves and analyzes issues from Sentry.io or self-hosted Sentry instances. It provides tools to inspect error reports, stack traces, and other debugging information directly from your Sentry account.

How to use Sentry?

Install the server via Smithery, uv, pip, or Docker. Configure it with your Sentry authentication token, project slug, organization slug, and Sentry URL. Use it with Claude Desktop or Zed by adding the appropriate configuration to claude_desktop_config.json or Zed's settings.json.

Key features of Sentry

Retrieve a specific Sentry issue by ID or URL
List all issues for a given project and organization
Detailed issue information including stack trace and event count
Formatted issue details via a prompt for conversation context
Supports both Sentry.io and self‑hosted Sentry instances
Compatible with multiple MCP clients (Claude Desktop, Zed)

Use cases of Sentry

Debug an application error by fetching its full stack trace from Sentry
Quickly review recent issues in a project during a development session
Integrate Sentry issue details into an AI assistant’s conversation context
Automate issue triage by pulling structured data into an MCP‑enabled tool

FAQ from Sentry

What does Sentry require to run?

You need a Sentry authentication token, a project slug, an organization slug, and the URL of your Sentry instance (either Sentry.io or self‑hosted). The server can be run via uvx, pip, or Docker.

How do I install Sentry?

Install via Smithery (npx -y @smithery/cli install @javaDer/mcp-sentry-custom), run directly with uvx, install via pip, or use a Docker container. All methods are documented in the README.

Where does Sentry store my data?

Sentry does not store any data locally; it retrieves issue information directly from your Sentry account (Sentry.io or self‑hosted) each time you use it.

What transport or authentication does Sentry use?

Sentry uses standard MCP transport (stdio). Authentication is handled via the provided --auth-token parameter. No OAuth or additional auth flows are documented.

Are there any known limits or restrictions?

The README does not mention any specific limits. It is a fork of the official sentry server from the modelcontextprotocol/servers repository.

Comments

More Developer Tools MCP servers

FastAPI-MCP

tadata-org

Expose your FastAPI endpoints as Model Context Protocol (MCP) tools, with Auth!

11.9K

Golf

golf-mcp

Production-Ready MCP Server Framework • Build, deploy & scale secure AI agent infrastructure • Includes Auth, Observability, Debugger, Telemetry & Runtime • Run real-world MCPs powering AI Agents

834