Datadog's remote MCP server gives AI agents access to logs, metrics, APM traces and spans, monitors, dashboards, incidents, hosts and notebooks. It uses OAuth 2.0 by default (API/app keys also supported), has per-site endpoints, and lets users select toolsets via a query parameter. Users need mcp_read/mcp_write role permissions.
Also available as
Connect
- 1Connect it in ChatGPT
Turn on Developer mode in ChatGPT (Settings → Security and login), open Plugins, select + and paste https://mcp.datadoghq.com as the MCP server URL, then sign in with OAuth. Add it to a chat from the composer's tools menu.
- 2Or add it to Codex or the API
codex mcp add datadog --url https://mcp.datadoghq.com codex mcp login datadogThe login command opens a browser to finish OAuth.
Configs are generated from the publisher's documented endpoint. Check their docs for plan requirements and scopes. New to this? Read the step-by-step tutorial.
Tools 12
search_datadog_logsanalyze_datadog_logsget_datadog_metricsearch_datadog_monitorsget_datadog_tracesearch_datadog_spansaggregate_spanssearch_datadog_dashboardssearch_datadog_incidentssearch_datadog_hostssearch_datadog_eventsddsql_run_queryThings to ask
- “Show error logs for the checkout service in the last 30 minutes”
- “Which monitors are currently alerting?”
- “Fetch the trace for this trace ID and explain the latency”
- “List active incidents and their severity”