kube_executor · OCM MCP Server MCP: Risk & Policy

WHAT IT DOES

What kube_executor does on OCM MCP Server

AI agents invoke kube_executor to trigger actions in OCM 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 kube_executor needs a policy

kube_executor triggers real processes with real consequences. An agent gone sideways doesn't fire it once — it starts dozens of builds, sends mass notifications, or burns through compute before anyone looks up.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

kube_executor Rate-limited

kube_executor 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": {
    "kube_executor": {
      "limits": [
        {
          "counter": "kube_executor_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 OCM MCP Server, so you can run agents against it safely.

FAQ

Questions about kube_executor

What does the kube_executor tool do? +

Securely run a kubectl command or apply YAML. Provide either. It is categorised as a Execute tool in the OCM 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 kube_executor? +

Register the OCM MCP Server MCP server in PolicyLayer and add a rule for kube_executor: 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 OCM MCP Server. Nothing to install.

What risk level is kube_executor? +

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

Can I rate-limit kube_executor? +

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

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

kube_executor is provided by the OCM MCP Server MCP server (yanmxa/multicluster-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.