compute_stop_instance · Google Cloud MCP: Risk & Policy

WHAT IT DOES

What compute_stop_instance does on Google Cloud

AI agents invoke compute_stop_instance to trigger actions in Google Cloud. 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 compute_stop_instance needs a policy

Stopping a Compute Engine instance is an external operation that changes system state and affects availability of services running on that instance. While not permanently destructive (the instance can be restarted), it is an Execute action—triggering external infrastructure operations whose effects depend on which instance is targeted.

From the tool's definition Tool name 'compute_stop_instance' and description 'Stop a Compute Engine instance' indicate the ability to stop (halt) a running cloud compute instance.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

compute_stop_instance Rate-limited

compute_stop_instance 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": {
    "compute_stop_instance": {
      "limits": [
        {
          "counter": "compute_stop_instance_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 Google Cloud, so you can run agents against it safely.

FAQ

Questions about compute_stop_instance

What does the compute_stop_instance tool do? +

Stop a Compute Engine instance. It is categorised as a Execute tool in the Google Cloud MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on compute_stop_instance? +

Register the Google Cloud MCP server in PolicyLayer and add a rule for compute_stop_instance: 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 Google Cloud. Nothing to install.

What risk level is compute_stop_instance? +

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

Can I rate-limit compute_stop_instance? +

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

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

compute_stop_instance is provided by the Google Cloud MCP server (lockon-n/google-cloud-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.