getsentry/sentry-mcp

An MCP server for interacting with Sentry via LLMs.

What it solves

This project provides a Model Context Protocol (MCP) server that allows AI coding assistants (like Cursor or Claude Code) to interact directly with Sentry. It bridges the gap between an AI agent's code editor and the error tracking and performance monitoring data in Sentry, enabling developers to debug and resolve issues more efficiently within their AI-powered workflow.

How it works

It acts as middleware between the AI agent and the Sentry API. It can be deployed as a remote server (via Cloudflare) or run locally using a stdio transport. The server exposes a set of tools that the AI agent can use to fetch errors, issues, and traces. For AI-powered search tools, it integrates with LLM providers like OpenAI, Anthropic, or OpenRouter to translate natural language queries into Sentry's specific query syntax.

Who it’s for

Developers using AI coding assistants who want to integrate Sentry's debugging data directly into their agent's context, as well as developers managing self-hosted Sentry instances.

Highlights

  • Coding Agent Optimization: Specifically designed for human-in-the-loop coding agents and developer workflows.
  • Flexible Deployment: Supports both remote MCP server deployments and local stdio transport for self-hosted environments.
  • AI-Powered Search: Uses LLMs to translate natural language into Sentry query syntax for easier issue discovery.
  • Claude Code Integration: Provides a dedicated plugin for automatic subagent delegation in Claude Code.
  • Customizable Skills: Allows users to disable specific skills (like Seer) if they are not supported by their Sentry instance.

Related

  • Project
    ergut/mcp-logseq

    An MCP server that connects AI assistants to LogSeq, enabling them to read, write, and search a knowledge base using both keyword and semantic search.

  • Project
    SonarSource/sonarqube-mcp-server

    An MCP server that integrates SonarQube's code quality and security analysis into AI agents, enabling them to analyze code snippets and project health.

  • Project
    makenotion/notion-mcp-server

    An MCP server that enables AI agents to read, search, and edit Notion workspaces using token-efficient Markdown tools.

  • Project
    postmanlabs/postman-mcp-server

    An MCP server that connects AI agents and coding assistants to Postman workspaces, collections, and specifications to automate API testing and client code generation.

  • Project
    dbt-labs/dbt-mcp

    An MCP server that provides AI agents with tools to interact with dbt Core, Fusion, and Platform, enabling them to query data, manage lineage, and execute dbt workflows.