Sentry MCP Server

@getsentry

Repository

Basic information

About Sentry MCP Server

Model Context Protocol (MCP) server for Sentry

#sentry #mcp #server#sentry-api

Sentry MCP Server config

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

{
  "mcpServers": {
    "sentry": {
      "command": "npx",
      "args": [
        "ts-node",
        "/Users/<your-user-directory>/sentry-mcp-ts/index.ts"
      ],
      "env": {
        "SENTRY_AUTH": "<YOUR_AUTH_TOKEN>"
      }
    }
  }
}

Sentry MCP Server tools

Tool list not available yet

This listing does not currently have a tool list to display. This does not mean the server has no tools; check its documentation for supported capabilities.

Fetch the live tool list by running this server in a temporary sandbox using the button above.

Overview

What is Sentry MCP Server?

A standalone Model Context Protocol (MCP) server that provides tools for AI assistants to interact with the Sentry API. It enables retrieving and analyzing error data, managing projects, and monitoring application performance. This server is largely superseded by the Sentry Remote-MCP Server and exists primarily for educational purposes.

How to use Sentry MCP Server?

Install dependencies with npm install, then run the server with npx ts-node index.ts. Set the SENTRY_AUTH environment variable to your Sentry authentication token before starting. Configuration for Claude Desktop requires adding a JSON block to your Claude settings with the command and token.

Key features of Sentry MCP Server

Lists all accessible Sentry projects for an organization.
Resolves issue details using a short ID (e.g., PROJECT-123).
Retrieves and analyzes specific Sentry events from an issue.
Creates new projects in Sentry and returns client keys.
Lists issues and events from a Sentry project or issue.
Lists replays from a Sentry organization with filters.
Supports summary or detailed views and plain or markdown output.

Use cases of Sentry MCP Server

Retrieve error details from a Sentry issue during debugging.
Create a new Sentry project programmatically from an AI assistant.
List and analyze recent error events for a specific project.
Monitor application performance by listing issues and replays.

Frequently asked questions

What authentication is required?

A Sentry authentication token with appropriate API permissions. Generate it in Sentry account settings under Settings → User Settings → Auth Tokens.

What are the runtime requirements?

Node.js v14 or higher, npm or yarn, and a Sentry account with API access.

Which IDEs or tools are verified to work with this server?

Cursor, Codeium Windsurf, and Claude Desktop.

Is there a newer version of this server?

Yes, it has been largely superseded by the Sentry Remote-MCP Server at `https://github.com/getsentry/sentry-mcp` and live at `https://mcp.sentry.dev`.

What tools does the server expose?

It exposes nine tools: `list_projects`, `resolve_short_id`, `get_sentry_event`, `list_error_events_in_project`, `create_project`, `list_project_issues`, `list_issue_events`, `get_sentry_issue`, and `list_organization_replays`.

Comments

More Developer Tools MCP servers

LocalCan

Gives AI agents public URLs (tunnels) for localhost, live HTTP traffic inspection, snapshot publishing, and access control. Part of LocalCan, the ngrok alternative for Mac, Windows and Linux. Free plan.

FARPY

mangomunchr

Verified distributed compute for humans, applications, and agents. Submit Blender, Octane, and video workloads, route them across qualified GPUs, track asynchronous execution, download finished artifacts, and verify FARP

Termany

thinkany-ai

Agent-Native Terminal

174

Reelier

Maxime Houle

Agents make claims. Reelier writes receipts — record an agent's tool-call workflow once, replay it deterministically at 0 tokens, and diff runs to catch drift.