Sentry MCP Server

Sentry's MCP server allows AI agents to query application error traces, inspect stack traces, monitor release health, and manage unresolved software exceptions. It equips agents to diagnose production crashes, analyze root causes of unhandled errors, review performance bottlenecks, and prioritize urgent bug fixes for developer teams.

Start for free

Sentry MCP Server

Benefits with Ory + Sentry MCP Server

Sentry's MCP server lets your agents search errors and issues, read stack traces and event details, and look into releases and performance data in your Sentry organization. It can also update issues and change project setup. Ory Agent Security lets debugging agents investigate production errors while changes stay with the agents you approve, and every tool call is tied to the user behind it.

View documentation

Use Cases

— 01 use case

Agent IAM

Debuggers read at Read, triage agents work issues at Write, keys and alert rules stay at Admin, and Block shuts out agents with no Sentry work.

Explore Agent IAM

Core Functionality

— 04 capabilities

Read, write, admin, or no access
Ory Agent Security classifies every tool on the Sentry MCP server as read, write, or admin, so you can give each user, team, or agent type only the level it needs: read for debugging agents, write for triage agents, admin for platform owners' agents, and no access for agents with no role in error handling.
Enforced before execution
Ory Agent Security checks each tool call against the user, the agent acting for them, and any sub-agent inside the agent harness, so a denied project change stops before it reaches Sentry, with nothing to roll back and no gateway to deploy.
Observe, then enforce
Observe mode shows which agents query or update Sentry and for whom without blocking anything, so you can apply Ory's pre-built policy for the Sentry MCP server and enforce it on your own schedule.
Complete audit trail
Every allow and deny decision on the Sentry MCP server streams to your SIEM through OpenTelemetry with the user, agent, and action attached, so you can show which agent resolved an issue or changed alerting, and on whose behalf.