Investigate Kubernetes health and processes with the Datadog MCP Server

Datadog has expanded its Model Context Protocol server to help AI assistants investigate Kubernetes and infrastructure issues using read-only access to observability data. New Kubernetes control plane tools provide one-call health assessments for the API server, scheduler, controller manager, and etcd, returning relevant metrics, statuses, and reusable Datadog queries for a selected cluster and time window. The Live Processes search tool supplies recent process-level evidence such as command lines, IDs, ownership, hosts, start times, and tags, while response token limits, pagination, tag controls, and secret redaction help manage large results safely. A new processes skill guides agents to the appropriate source among discovered processes, Live Processes, and per-process CPU and memory metrics, including how to interpret missing or truncated data. Datadog reports that access to Live Processes substantially improved answer accuracy in an internal evaluation, and the capabilities are available through supported AI clients such as Claude Code, Cursor, Codex, GitHub Copilot, and VS Code, subject to required telemetry collection and user permissions.

Use this post, company, and trend context to find content marketing opportunities, perform competitive analysis, or address product feature gaps via the Plushcap MCP server or the Plushcap API.