exec_in_pod · K8s MCP: Risk & Policy

WHAT IT DOES

What exec_in_pod does on K8s MCP

AI agents invoke exec_in_pod to trigger actions in K8s MCP. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call — builds kicked off, notifications sent, workflows started.

WHY IT NEEDS A POLICY

Why exec_in_pod needs a policy

The name 'exec_in_pod' directly mirrors 'kubectl exec', which allows arbitrary command execution inside a running container. Despite the empty description, the name unambiguously indicates code/command execution within a pod.

From the tool's definition Tool name 'exec_in_pod' strongly implies executing commands inside a Kubernetes pod, a well-known and highly privileged operation.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

exec_in_pod Rate-limited

exec_in_pod stays usable, but rate-capped — a runaway agent can't fire it dozens of times a minute. Everything else on the server is denied unless you say otherwise.

View as policy code

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "exec_in_pod": {
      "limits": [
        {
          "counter": "exec_in_pod_rate",
          "window": "minute",
          "max": 10,
          "scope": "grant"
        }
      ]
    }
  }
}

RATE-LIMIT THIS TOOL →

Instant setup, no code required.

PolicyLayer is an MCP gateway: every tool call is checked against your rule before it reaches K8s MCP, so you can run agents against it safely.

FAQ

Questions about exec_in_pod

What does the exec_in_pod tool do? +

exec_in_pod. It is categorised as a Execute tool in the K8s MCP MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on exec_in_pod? +

Register the K8s MCP server in PolicyLayer and add a rule for exec_in_pod: 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 K8s MCP. Nothing to install.

What risk level is exec_in_pod? +

exec_in_pod is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.

Can I rate-limit exec_in_pod? +

Yes. Add a rate_limit block to the exec_in_pod 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 exec_in_pod completely? +

Set action: deny in the PolicyLayer policy for exec_in_pod. 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 exec_in_pod? +

exec_in_pod is provided by the K8s MCP server (rahul007-bit/k8s-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.