apply_kustomize · K8s MCP: Risk & Policy

WHAT IT DOES

What apply_kustomize does on K8s

AI agents invoke apply_kustomize to trigger actions in K8s. 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 apply_kustomize needs a policy

Applying a Kustomize directory renders templates and deploys resources to a Kubernetes cluster. This triggers external operations with real cluster-side effects (creating, updating, or replacing resources). While it can also overwrite existing resources destructively, the primary action is executing a deployment operation whose effects depend on the directory contents.

From the tool's definition "Render and apply a Kustomize directory" — applies rendered Kubernetes manifests to a live cluster

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

apply_kustomize Rate-limited

apply_kustomize 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": {
    "apply_kustomize": {
      "limits": [
        {
          "counter": "apply_kustomize_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, so you can run agents against it safely.

FAQ

Questions about apply_kustomize

What does the apply_kustomize tool do? +

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

How do I enforce a policy on apply_kustomize? +

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

What risk level is apply_kustomize? +

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

Can I rate-limit apply_kustomize? +

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

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

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