get-pod-metrics · Kubernetes MCP Server MCP: Risk & Policy

WHAT IT DOES

What get-pod-metrics does on Kubernetes MCP Server

AI agents call get-pod-metrics to retrieve information from Kubernetes MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.

WHY IT NEEDS A POLICY

Why get-pod-metrics needs a policy

This tool queries and retrieves existing metrics data from a Kubernetes cluster. It performs no mutations, executions, or destructive operations. While metrics access could theoretically inform operational decisions, the tool itself only reads and returns data. Severity is low because metric retrieval has no blast radius—it cannot modify cluster state, execute workloads, delete resources, or cause financial impact.

From the tool's definition Tool name 'get-pod-metrics' and description 'Get detailed metrics for a pod' indicate retrieval of monitoring/observability data without modification or side effects.

Attacks that exploit this kind of access

Questions about get-pod-metrics

What does the get-pod-metrics tool do? +

Get detailed metrics for a pod. It is categorised as a Read tool in the Kubernetes MCP Server MCP Server, which means it retrieves data without modifying state.

How do I enforce a policy on get-pod-metrics? +

Register the Kubernetes MCP Server MCP server in PolicyLayer and add a rule for get-pod-metrics: 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 MCP Server. Nothing to install.

What risk level is get-pod-metrics? +

get-pod-metrics is a Read tool with low risk. Read-only tools are generally safe to allow by default.

Can I rate-limit get-pod-metrics? +

Yes. Add a rate_limit block to the get-pod-metrics 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 get-pod-metrics completely? +

Set action: deny in the PolicyLayer policy for get-pod-metrics. 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 get-pod-metrics? +

get-pod-metrics is provided by the Kubernetes MCP Server MCP server (thekaranpargaie/kube-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.