cleanup · Kubernetes MCP: Risk & Policy

WHAT IT DOES

What cleanup does on Kubernetes

AI agents call cleanup to permanently remove resources in Kubernetes — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.

WHY IT NEEDS A POLICY

Why cleanup needs a policy

Cleaning up 'all managed resources' in a Kubernetes cluster is an irreversible bulk deletion operation. This could remove deployments, services, configmaps, and other cluster resources at scale, making it a critical destructive action with a very large blast radius if misused by an AI agent.

From the tool's definition 'Cleanup all managed resources' - deletes/removes all resources managed by this server

Attacks that exploit this kind of access

Questions about cleanup

What does the cleanup tool do? +

Cleanup all managed resources. It is categorised as a Destructive tool in the Kubernetes MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.

How do I enforce a policy on cleanup? +

Register the Kubernetes MCP server in PolicyLayer and add a rule for cleanup: allow, deny, rate-limit, or require approval. Point your MCP client at the PolicyLayer proxy URL and the rule is enforced on every call, before it reaches Kubernetes. Nothing to install.

What risk level is cleanup? +

cleanup is a Destructive tool with critical risk. Critical-risk tools should be blocked by default and only enabled with explicit human approval.

Can I rate-limit cleanup? +

Yes. Add a rate_limit block to the cleanup rule in your PolicyLayer policy. For example, setting max: 10 and window: 60 limits the tool to 10 calls per minute. Rate limits are tracked per agent session and reset automatically.

How do I block cleanup completely? +

Set action: deny in the PolicyLayer policy for cleanup. The AI agent will receive a policy violation error and cannot call the tool. You can also include a reason field to explain why the tool is blocked.

What MCP server provides cleanup? +

cleanup is provided by the Kubernetes MCP server (mcp-server-kubernetes). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.