Analyze, investigate, and act on your Datadog telemetry directly from Claude using natural language. Ask questions about your production applications. Identify, visualize, and remediate issues in your critical services. Run agentic loops to ensure you continue to maintain good observability and service management posture. You can use Datadog to: Investigate an incident: "Why is the checkout service throwing 500s? Pull the last hour of logs and traces and tell me what changed." Tune alerting: "Recommend a threshold for the p95 latency monitor on the payments API and draft the monitor definition." Track CI health: "Which tests have been flaky on main this week, and which PRs introduced them?" Debug LLM applications: "Find LLM Observability spans with errors in the support-bot app and summarize what is failing."

claude mcp add --transport http datadog "https://mcp.datadoghq.com/api/unstable/mcp-server/mcp?toolsets=all"