MCP Server Sentry - TypeScript Implementation

This is a Model Context Protocol (MCP) server implemented in TypeScript for connecting to the Sentry error tracking service. This server allows AI models to query and analyze error reports and events on Sentry.

Features

1. get_sentry_issue Tool

   • Retrieves and analyzes Sentry issues 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
     • Complete stack trace

2. sentry-issue Prompt Template

   • Retrieves issue details from Sentry
   • Input:
     • issue_id_or_url (string): Sentry issue ID or URL
   • Returns: Formatted issue details as conversation context

Installation

# Install dependencies
npm install

# Build the project
npm run build

Configuration

The server is configured using environment variables. Create a .env file in the project root directory:

# Required: Sentry authentication token
SENTRY_AUTH_TOKEN=your_sentry_auth_token

# Optional: Sentry organization name
SENTRY_ORGANIZATION_SLUG=your_organization_slug

# Optional: Sentry project name
SENTRY_PROJECT_SLUG=your_project_slug

# Optional: Sentry base url
SENTRY_BASE_URL=https://sentry.com/api/0

Alternatively, you can set these environment variables at runtime.

Running

Run the server via standard IO:

node dist/index.js

Debug with MCP Inspector:

npx @modelcontextprotocol/inspector node dist/index.js

Environment Variables Description

• SENTRY_AUTH_TOKEN (required): Your Sentry API access token
• SENTRY_PROJECT_SLUG (optional): The slug of your Sentry project
• SENTRY_ORGANIZATION_SLUG (optional): The slug of your Sentry organization

The latter two variables can be omitted if project and organization information are provided in the URL.

License

This project is licensed under the MIT License.