start_instance · Gcp MCP: Risk & Policy

WHAT IT DOES

What start_instance does on Gcp

AI agents invoke start_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 start_instance needs a policy

This tool executes a command that changes infrastructure state by starting a cloud compute resource. While not destructive (the instance isn't deleted or data overwritten), it is Execute-category because it triggers an external operation with real-world effects.

From the tool's definition 'Start a stopped Compute Engine instance' — this tool triggers external operations (VM startup) whose effects are real and depend on which instance argument is provided.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

start_instance Rate-limited

start_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": {
    "start_instance": {
      "limits": [
        {
          "counter": "start_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 start_instance

What does the start_instance tool do? +

Start a stopped 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 start_instance? +

Register the Gcp MCP server in PolicyLayer and add a rule for start_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 start_instance? +

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

Can I rate-limit start_instance? +

Yes. Add a rate_limit block to the start_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 start_instance completely? +

Set action: deny in the PolicyLayer policy for start_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 start_instance? +

start_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.