Navigation
MCP-Sentry: Centralized Error Tracking & Real-Time Collaboration - MCP Implementation

MCP-Sentry: Centralized Error Tracking & Real-Time Collaboration

MCP-Sentry: Streamline Sentry integration with a dedicated MCP server, enabling centralized error tracking and real-time collaboration to resolve issues faster.

Developer Tools
4.6(89 reviews)
133 saves
62 comments

Users create an average of 49 projects per month with this tool

About MCP-Sentry

What is MCP-Sentry: Centralized Error Tracking & Real-Time Collaboration?

MCP-Sentry is a Model Context Protocol (MCP) server designed to retrieve and analyze error data from Sentry.io. It enables AI assistants to access detailed error reports, including stack traces and event metadata, streamlining error analysis and collaboration across development teams. By integrating with existing workflows, it provides a centralized hub for tracking application issues and fostering real-time problem-solving.

How to Use MCP-Sentry: Centralized Error Tracking & Real-Time Collaboration?

Installation is straightforward via npm or npx. Users must first obtain a Sentry authentication token. Once installed, the server can be launched using either a command-line flag or an environment variable to specify the token. Configuration for platforms like Claude Desktop or Zed requires adding server details to their context settings. For example, in Zed, the configuration involves specifying the command path and authentication arguments in the settings.json file.

MCP-Sentry Features

Key Features of MCP-Sentry: Centralized Error Tracking & Real-Time Collaboration?

  • Error Analysis Tools: The get_sentry_issue tool retrieves full stack traces, timestamps, and event counts using issue IDs or URLs.
  • Context Integration: The sentry-issue prompt formats error details into conversation-ready context for AI-driven collaboration.
  • Authentication Flexibility: Supports both command-line options and environment variables for token management.
  • Development Readiness: Pre-built binaries and a clean project structure (including TypeScript sources) simplify deployment and customization.

Use Cases of MCP-Sentry: Centralized Error Tracking & Real-Time Collaboration?

Teams can leverage MCP-Sentry to:

  • Rapidly diagnose production errors by cross-referencing stack traces with AI insights.
  • Share real-time error data across development tools (e.g., Zed, Claude Desktop) for synchronized debugging sessions.
  • Automate error analysis workflows by embedding Sentry data into CI/CD pipelines through MCP integrations.
  • Centralize incident response by providing contextual error details to on-call engineers during outages.

MCP-Sentry FAQ

FAQ from MCP-Sentry: Centralized Error Tracking & Real-Time Collaboration?

Q: How do I generate a Sentry authentication token?
Sentry.io provides token generation instructions in its account settings under API authorization.

Q: Can I use MCP-Sentry without installing globally?
Yes, the npx mcp-sentry command allows execution without permanent installation, ideal for testing or CI environments.

Q: Does the server support Sentry On-Premises instances?
The server uses standard Sentry API endpoints, so it works with both cloud and self-hosted Sentry installations when configured correctly.

Q: What happens if my authentication token expires?
The server will return access errors. Update the token via the same command-line or environment variable methods to restore functionality.

Content

mcp-sentry: A Sentry MCP Server

A Model Context Protocol server for retrieving and analyzing issues from Sentry.io. This server provides tools to inspect error reports, stacktraces, and other debugging information from your Sentry account.

Overview

This MCP server allows AI assistants to access and analyze Sentry issues, providing detailed information about errors in your applications.

Tools

  1. get_sentry_issue

Retrieve and analyze a Sentry issue by ID or URL

Input:

* `issue_id_or_url` (string): Sentry issue ID or URL to analyze

Returns: Issue details including:

* Title
* Issue ID
* Status
* Level
* First seen timestamp
* Last seen timestamp
* Event count
* Full stacktrace

Prompts

  1. sentry-issue

Retrieve issue details from Sentry

Input:

* `issue_id_or_url` (string): Sentry issue ID or URL

Returns: Formatted issue details as conversation context

Installation

Prerequisites

  • Node.js 14 or later
  • A Sentry account with an authentication token

Using npm

npm install -g mcp-sentry

After installation, you can run it as a command:

mcp-sentry --auth-token YOUR_SENTRY_TOKEN

Or with the environment variable:

SENTRY_TOKEN=YOUR_SENTRY_TOKEN mcp-sentry

Using npx (without installation)

npx mcp-sentry --auth-token YOUR_SENTRY_TOKEN

Development

Project Structure

mcp-sentry/
├── src/
│   ├── index.ts           # Main entry point
│   ├── server.ts          # MCP server implementation
│   ├── sentry-client.ts   # Sentry API client
│   ├── models.ts          # Data models
│   ├── utils.ts           # Utility functions
│   └── types/             # Type definitions
├── build/                 # Compiled JavaScript files (included in the repository for direct npx execution)
├── package.json
├── tsconfig.json
└── README.md

Building

npm run build

Note: Unlike typical Node.js projects, the build directory is committed to this repository to support direct npx execution without requiring users to build the project themselves.

Running in Development Mode

npm run dev -- --auth-token YOUR_SENTRY_TOKEN

Authentication

This server requires a Sentry authentication token to access the Sentry API. You can provide this token in two ways:

  1. Using the --auth-token command-line option:

    mcp-sentry --auth-token YOUR_SENTRY_TOKEN

  2. Using the SENTRY_TOKEN environment variable:

    SENTRY_TOKEN=YOUR_SENTRY_TOKEN mcp-sentry

Usage with Claude Desktop

Add this to your Claude Desktop configuration:

"mcpServers": {
  "sentry": {
    "command": "mcp-sentry",
    "args": ["--auth-token", "YOUR_SENTRY_TOKEN"]
  }
}

Usage with Zed

Add to your Zed settings.json:

"context_servers": [
  "mcp-server-sentry": {
    "command": {
      "path": "mcp-sentry",
      "args": ["--auth-token", "YOUR_SENTRY_TOKEN"]
    }
  }
],

Debugging

You can use the MCP inspector to debug the server:

npx @modelcontextprotocol/inspector mcp-sentry --auth-token YOUR_SENTRY_TOKEN

License

This MCP server is licensed under the MIT License. This means you are free to use, modify, and distribute the software, subject to the terms and conditions of the MIT License.

Related MCP Servers & Clients