This project provides a middleware communication protocol (MCP) server for interacting with the Sentry API, designed to facilitate AI-driven analysis and automation. It targets developers and researchers who need to integrate Sentry data with large language models (LLMs) for tasks like automated code review and issue analysis. The primary benefit is enabling natural language queries and commands against Sentry data.

How It Works

The MCP server acts as a bridge between LLMs and the Sentry API. It leverages Cloudflare's MCP work, allowing for both remote and stdio transports. AI-powered search tools translate natural language queries into Sentry's query syntax, enhancing data exploration. This approach simplifies complex API interactions and enables advanced AI capabilities for Sentry users.

Quick Start & Requirements

• Install/Run: npx @sentry/mcp-server@latest --access-token=sentry-user-token --host=sentry.example.com
• Prerequisites: Sentry User Auth Token with org:read, project:read, project:write, team:read, team:write, event:write scopes. OpenAI API key is required for AI-powered search tools (search_events, search_issues).
• Links: Deployed Service

Highlighted Details

• Supports both remote and stdio transports for flexibility.
• Includes an MCP Inspector for easy service testing and authentication flow verification.
• AI-powered search tools enable natural language querying of Sentry events and issues.
• Local development setup is detailed for contributors, requiring a Sentry OAuth App.

Maintenance & Community

The project is part of the Sentry ecosystem. Further community and contribution details are available via the deployed service link.

Licensing & Compatibility

The README does not explicitly state the license. Compatibility for commercial use or closed-source linking is not specified.

Limitations & Caveats

AI-powered search tools are dependent on an OpenAI API key. The stdio transport is noted as a work in progress. Automated code review tools are provided as suggestions, not mandatory checks.