The official Datadog MCP server gives AI agents access to your full observability stack — metrics, logs, distributed traces, and incidents — enabling autonomous debugging and root cause analysis.
Features:
- Query metrics with full PromQL/DQL expression support
- Search and tail logs in real time
- Inspect distributed traces and service maps
- View and manage monitors and alert policies
- Access incident timelines and postmortems
- Query APM service performance data
- Inspect infrastructure maps and host health
- Run synthetic test results analysis
- Create dashboards and widgets programmatically
Real-world workflow:
1. Deployment triggers an alert
2. Claude queries Datadog for the specific metric spike
3. Pulls correlated logs from the same time window
4. Identifies the root cause from trace data
5. Proposes a fix — all within the same conversation
The fastest path from "something is wrong" to "here's why and how to fix it."
datadog
monitoring
observability
metrics
logs
apm
tracing