patch_resource · Kubernetes MCP: Risk & Policy

WHAT IT DOES

What patch_resource does on Kubernetes MCP

AI agents use patch_resource to create or update resources in Kubernetes MCP — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Kubernetes MCP environment.

WHY IT NEEDS A POLICY

Why patch_resource needs a policy

The patch_resource tool modifies Kubernetes resources, which falls squarely into the Write category. While the description is empty, the tool name combined with the server's stated capability to 'patch Kubernetes resources' provides strong evidence. Severity is high because Kubernetes resource patches can affect cluster behavior, networking, security policies, and workload configurations.

From the tool's definition Tool name 'patch_resource' indicates modification of Kubernetes resources. Server description states it allows users to 'patch Kubernetes resources.' Patching is a reversible modification operation that updates resource configurations.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

patch_resource Rate-limited

patch_resource stays usable, but capped — an agent stuck in a loop can't make hundreds of changes a minute. Everything else on the server is denied unless you say otherwise.

View as policy code

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "patch_resource": {
      "limits": [
        {
          "counter": "patch_resource_rate",
          "window": "minute",
          "max": 30,
          "scope": "grant"
        }
      ]
    }
  }
}

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, so you can run agents against it safely.

FAQ

Questions about patch_resource

What does the patch_resource tool do? +

patch_resource. It is categorised as a Write tool in the Kubernetes MCP MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

How do I enforce a policy on patch_resource? +

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

What risk level is patch_resource? +

patch_resource is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.

Can I rate-limit patch_resource? +

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

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

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