Kubernetes context for agents
Provides cluster context over MCP, bringing ranked issues, a change timeline, logs, and owners into one view.
Loading page…
Coding / product dossier
Open-source Kubernetes context via MCP for AI agents, with read-only root-cause investigations.
Product brief
Your agent knows Kubernetes. It doesn't know your cluster. Radar (open-source) gives it context over MCP: ranked issues, a change timeline, logs and owners in one view. New: click Investigate on a failing workload. Claude Code, Codex or Cursor finds the root cause, read-only, with evidence for each claim. In our benchmark of 50 live faults across six tools, Radar found the most root causes. Radar Cloud investigates every alert and posts findings to Slack.
Why we selected it
Radar gives coding agents concrete Kubernetes context rather than offering another general-purpose assistant. Open-source availability, read-only investigations, and evidence-backed findings make it a substantive tool to
Product preview saved with our daily selection
Capability scan
Only capabilities supported by the product information we collected are listed here.
Provides cluster context over MCP, bringing ranked issues, a change timeline, logs, and owners into one view.
An Investigate action on a failing workload lets Claude Code, Codex, or Cursor investigate root causes read-only, with evidence for each claim.
Radar Cloud investigates every alert and posts findings to Slack.
Best-fit use cases
FAQ
Radar provides ranked Kubernetes issues, a change timeline, logs, and owners over MCP.
The description names Claude Code, Codex, and Cursor. Clicking Investigate on a failing workload starts a read-only investigation with evidence for each claim.
The described Investigate workflow is read-only.
Radar is described as open source. The description also identifies Radar Cloud as an offering that investigates alerts and posts findings to Slack.