Connect Sentry to ChatGPT
Search, read and write Sentry from ChatGPT. Arlet links the two through one MCP connection and takes care of keys and authentication.
Arlet makes Sentry's official MCP server available from the AI client you already use. Signing in completes the connection, and the consent screen lets you choose which permission sets (inspect, Seer, triage, project management) to grant.
The AI can search issues and events, read stack traces and traces, run Seer root-cause analysis, and update or comment on issues. The available tools are those provided by Sentry's official server.
How to connect Sentry to ChatGPT
- 1
In the Arlet dashboard, open Integrations β Add an integration and choose Sentry. Sign in with Link Sentry, name the connection and click Create.
- 2
In ChatGPT, open Settings β Plugins β Browse plugins and click + at the top right.
- 3
In the New Plugin form, enter "Arlet" as the Name, choose Server URL for Connection and enter https://mcp.arlet.dev/mcp/, pick OAuth for Authentication, check the risk acknowledgement and click Create.
- 4
Open the Arlet plugin you created, click Sign in with Arlet, sign in with Google and click Allow. The connection is complete.
If the Plugins screen is not shown, turn on Developer mode under Settings β Security and login.
What you can do
Sentry tools that ChatGPT can call.
search_issuesSearch issues with natural-language conditions.
search_eventsSearch events and replays, with counts and trends.
get_issue_detailsGet an issue's details, impact and stack trace.
get_event_stacktraceGet an event's stack trace.
get_trace_detailsGet a trace's spans and timings.
analyze_issue_with_seerRun Seer root-cause analysis with fix suggestions.
update_issueChange an issue's status or assignee.
add_issue_noteComment on an issue.
find_releasesSearch releases.
get_release_detailsGet a release's details.
find_alert_rulesList alert rules.
find_monitorsList cron monitors.
find_dashboardsSearch dashboards.
find_projectsList projects.
search_docsSearch Sentry's documentation.
The tool list follows what Sentry's official MCP server provides and may change.
Example uses
First-response investigation
Find issues that spiked in the last 24 hours and summarize stack traces and impact for the team.
Root-cause analysis
Analyze an issue with Seer and turn the explanation and suggested fix into a review-ready note.
Triage
Rank open issues by severity, assign owners and leave notes.
Release health
List issues new to the latest release to decide whether to roll back.
Prompts you can use as-is
- List issues whose event count spiked in the last 24 hours, sorted by affected users
- Analyze issue PROJ-1234 with Seer and explain the cause and the fix
- Rank open issues by severity and assign the top five to me
- List the issues that first appeared in release 2.14.0
