Sentry MCP Server
The Sentry MCP Server connects your AI to Sentry — query recent errors, inspect an issue's stack trace, analyze error trends — all in natural language.
For example, "what new errors appeared in the last 24 hours and which affects the most users" — the AI uses this server to pull Sentry data and attribute the cause.
What it does for you
Connects your AI to Sentry — pull production errors, read stack traces, and pinpoint which release introduced a bug, right in chat.
Capabilities
- Query errors and issues
- Read stack traces and frequency
- Correlate with releases / commits
Once installed, try asking your AI
Say this directly in Claude / Cursor or any client with this server connected
- ›“What are the top 3 most frequent errors in the last 24 hours?”
- ›“Which release did this error start appearing in?”
Install / Connect
claude mcp add mcp-server -- npx -y @sentry/mcp-serverFollow the official README; env and args vary per server.
Works with these clients
- Claude Desktopnpx
- Claude Codenpx
- Cursornpx
- VS Codenpx
- Windsurfnpx
Derived from the registry manifest (package type and transport) — we have not installed it ourselves. Check the official README before relying on it.
Why use it
Good for: developers and SREs who want AI to speed up production-error investigation and root-cause analysis.
Built by Sentry officially, so reliability is backed; its measured health data on this site is shown below.
Similar / alternative servers
io.github.sandeepbazar/ocm-mcp-server
Guardrailed fleet ops for AI agents: multi-cluster Kubernetes via OCM with polic
io.github.cyanheads/ntfy-mcp-server
Send, manage, and replay ntfy push notifications via MCP.
io.github.chrischall/gogcli-mcp-sheets
Extended Google Sheets for Claude via gogcli — auth + full Sheets support
io.github.chrischall/gogcli-mcp-slides
Google Slides via gogcli for Claude — deck and slide authoring
Frequently Asked Questions
What permissions does it need?
A Sentry auth token, scoped to the projects you want it to access.
Can it fix bugs automatically?
It brings error context to the AI; code fixes still need your codebase and judgment — don't apply blindly.