kubectl_exec · Kubernetes MCP Server MCP: Risk & Policy

WHAT IT DOES

What kubectl_exec does on Kubernetes MCP Server

AI agents invoke kubectl_exec to trigger actions in Kubernetes MCP Server. 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 kubectl_exec needs a policy

This tool runs arbitrary commands inside a Kubernetes Pod, equivalent to remote code execution within the cluster. An AI agent could use this to exfiltrate secrets, modify running containers, pivot to other services, or cause widespread damage. The blast radius is critical as it provides direct shell-level access to live workloads.

From the tool's definition kubectl_exec - '在Pod中执行命令' means 'Execute commands in a Pod'

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

kubectl_exec Rate-limited

kubectl_exec 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": {
    "kubectl_exec": {
      "limits": [
        {
          "counter": "kubectl_exec_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 Kubernetes MCP Server, so you can run agents against it safely.

FAQ

Questions about kubectl_exec

What does the kubectl_exec tool do? +

在Pod中执行命令. It is categorised as a Execute tool in the Kubernetes MCP Server MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on kubectl_exec? +

Register the Kubernetes MCP Server MCP server in PolicyLayer and add a rule for kubectl_exec: 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 kubectl_exec? +

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

Can I rate-limit kubectl_exec? +

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

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

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