apply_manifest · K8s MCP: Risk & Policy

WHAT IT DOES

What apply_manifest does on K8s

AI agents use apply_manifest to create or update resources in K8s — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your K8s environment.

WHY IT NEEDS A POLICY

Why apply_manifest needs a policy

The tool creates or updates Kubernetes resources reversibly via YAML manifest application. This is a Write operation rather than Execute because it applies declarative configuration rather than running arbitrary code, and it is reversible (resources can be updated or deleted).

From the tool's definition Tool name 'apply_manifest' and description 'Apply a Kubernetes YAML manifest (create or update resources)' indicates creation or modification of Kubernetes resources through manifest application.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

apply_manifest Rate-limited

apply_manifest 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": {
    "apply_manifest": {
      "limits": [
        {
          "counter": "apply_manifest_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 K8s, so you can run agents against it safely.

FAQ

Questions about apply_manifest

What does the apply_manifest tool do? +

Apply a Kubernetes YAML manifest (create or update resources). It is categorised as a Write tool in the K8s MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

How do I enforce a policy on apply_manifest? +

Register the K8s MCP server in PolicyLayer and add a rule for apply_manifest: 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_manifest? +

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

Can I rate-limit apply_manifest? +

Yes. Add a rate_limit block to the apply_manifest 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_manifest completely? +

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

apply_manifest 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.