About
Sentry's official MCP server lets coding assistants query errors, issues, traces and performance data in natural language, optimized for developer debugging workflows; built on Cloudflare's remote MCP approach with local stdio support too.
Our Verdict
Sentry MCP brings monitoring capabilities to the MCP ecosystem. Its GitHub popularity reflects community trust, and the standardized protocol ensures broad compatibility across AI clients.
Pricing
Use Cases
- Integrating monitoring capabilities into AI agent workflows
- Building custom AI-powered tools with Sentry MCP
- Enhancing AI agent functionality with standardized MCP access
Pros
- Sentry MCP provides standardized MCP protocol access
- Open source with 801 GitHub stars
- Active development and community support
Cons
- Requires MCP-compatible client (Claude, Cursor, etc.)
- Setup complexity varies by client
- Some features may depend on client capabilities
Installation
npx -y @sentry/mcp-serverFrequently Asked Questions
What is Sentry MCP mainly for?
It brings Sentry error monitoring into your coding assistant: ask "what caused this issue" or "show the latest error trace" right inside Cursor / Claude Code, and the assistant pulls Sentry data to help you locate and fix bugs without switching to the dashboard.
How do I install Sentry MCP and what scopes are needed?
The easy path is mcp.sentry.dev via OAuth; for local stdio use npx -y @sentry/mcp-server, which needs a Sentry User Auth Token with scopes like org:read, project:read/write and team:read.
Is Sentry MCP free?
The MCP server itself is open source and free, reading data from your own Sentry projects; Sentry has a free tier and charges beyond it as usual. Some AI-search tools require your own LLM provider key.