IntegrationsDatadog integration
Your Datadog alerts.The story behind them.
Connect Datadog to Claude Code, Codex, Cursor or any MCP agent through CoreSpeed. Your agent searches monitors, logs, traces and incidents, and turns an alert into a timeline with its likely cause. CoreSpeed proxies Datadog's own MCP server for US1 accounts; access follows your Datadog role, and changing a monitor or dashboard is a separate call.
From an alertto what happened.
Requests you can make once Datadog is connected. The data is fictional.
- DatadogMonitors · env:prod
- M-1042checkout p95 latency above 2 sAlert
- M-0987email-worker queue depthWarn
- M-0911API error rateOK
See what is alerting
From the monitors you can see
- DatadogLogs · service:checkout
status:error, last 20 minutes
- 412 × connection pool exhausted (db-primary).
- 38 × upstream timeout calling payments.
- First error at 14:03, after deploy v2.41.
Read the logs around it
Read, not changed
- Claude CodeAnswer
Incident timeline
Checkout latency, 14:03 to 14:20.
- 14:03 deploy v2.41 lowers the pool size.
- 14:05 p95 latency passes 2 s; the monitor alerts.
- 14:20 rollback; latency recovers.
Write the incident timeline
A draft for the postmortem
Know what fired.Know why.
Ask your agent which monitors are alerting, what the logs say around them, and what changed first.
Reads fromDatadog
All connectors →Which production monitors are alerting right now? For the worst one, read the error logs from the last 20 minutes and tell me the likely cause. Do not change any monitor.
datadog__search_datadog_monitorsok
1 alerting: checkout p95 latency
Keep your agent.Bring your work.
One CoreSpeed account, across compatible agents.
- 1
Set up CoreSpeed
Give your agent the setup line. It adds CoreSpeed and signs you in.
- 2
Connect Datadog
Authorize the account and the content you need.
- 3
Start with one task
Ask for a summary, a brief, or a draft. Review the answer.
Setup guidesClaude CodeCodexCursor