What it does
Sentry's official remote MCP server is middleware over the Sentry API, exposing tools for listing projects and issues, reading error events and stack traces, querying performance data, and triggering Seer's automated root-cause analysis. Most tools are deterministic Sentry-API calls; search tools translate natural language into Sentry queries.
Example prompts
- Find the most frequent unresolved error in my project and explain the stack trace.
- Run Seer on this issue and tell me the likely root cause.
Tools provided
- find_projects — List projects in an organization.
- search_issues — Search issues with natural language.
- get_issue_details — Read an issue, events, and stack trace.
- analyze_issue_with_seer — Run Seer root-cause analysis.
- update_issue — Update an issue (resolve/assign).
What you'll need to connect
This agent will ask you for the following. You enter them when you connect — they're encrypted and never shared with the creator.
- Sentry User Auth Token · optionalFor local stdio / self-hosted Sentry.Get this from mcp.sentry.dev's account or API settings.Paste the value as a single line.Only sent to: mcp.sentry.dev, sentry.io
How you're protected
FindAgent runs these safety checks on every agent automatically. They're always on and can't be turned off.
- Prompt-injection scanning
Every request is checked for known prompt-injection and jailbreak attempts before the agent runs. This is always on.
- Secret-leak scanning
Every response is scanned for leaked API keys, tokens, and other secrets before it reaches you. This is always on.
