Incident Response
Detect an outage, gather logs, notify the team, and create an incident ticket
Example Prompt
We have a production outage in the payments service. Gather logs, notify the team on Slack, and open an incident ticket.
About
Coordinates a rapid incident response workflow by checking error tracking for active issues, pulling container logs for affected services, notifying the on-call team via Slack, and creating a GitHub issue to track the incident through resolution.
Workflow Steps
Check Sentry for unresolved critical errors across services
🚨 List IssuesPull recent container logs from the affected service for diagnosis
📜 Container LogsSend an incident alert to the team Slack channel with initial findings
📨 Send MessageCreate a GitHub issue to formally track the incident and remediation steps
➕ Create IssuePost a follow-up Slack message with the incident ticket link
📨 Send MessageTools Used
Container Logs
Retrieve log output from a running or stopped Docker container
Create Issue
Create a new issue in a GitHub repository with title, body, labels, and assignees
List Issues
Retrieve unresolved error issues from a Sentry project, sorted by frequency or last seen
Send Message
Send a message to a Slack channel or direct message conversation
Required MCP Servers
Docker
Manage containers, images, volumes, and networks via the Docker daemon
GitHub
Access GitHub repos, issues, PRs, and code search via the official MCP server
Sentry
Query error reports, performance data, and release health from Sentry
Slack
Send messages, read channels, and manage Slack workspace interactions