stop_instance · Gcp MCP: Risk & Policy

WHAT IT DOES

What stop_instance does on Gcp

AI agents invoke stop_instance to trigger actions in Gcp. 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 stop_instance needs a policy

This tool triggers a state-changing operation on cloud infrastructure. While not destructive (the instance data persists and can be restarted), it is an Execute action because it runs an external operation with side effects. The severity is high due to potential business impact from stopping production instances, though the blast radius is limited compared to destructive or financial operations.

From the tool's definition The tool 'stop_instance' performs an action that stops a running Compute Engine instance. The description explicitly states it performs an operation ('Stop a running Compute Engine instance') rather than simply retrieving data.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

stop_instance Rate-limited

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

FAQ

Questions about stop_instance

What does the stop_instance tool do? +

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

How do I enforce a policy on stop_instance? +

Register the Gcp MCP server in PolicyLayer and add a rule for 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 Gcp. Nothing to install.

What risk level is stop_instance? +

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

Can I rate-limit stop_instance? +

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

Set action: deny in the PolicyLayer policy for 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 stop_instance? +

stop_instance is provided by the Gcp MCP server (lokimcpuniverse/gcp-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.