compute_create_instance · Google Cloud MCP: Risk & Policy

WHAT IT DOES

What compute_create_instance does on Google Cloud

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

WHY IT NEEDS A POLICY

Why compute_create_instance needs a policy

This tool creates new Compute Engine VM instances, which is a Write operation that modifies cloud infrastructure state. The severity is high because creating instances can incur financial costs, consume quota, and potentially enable further attacks via the created instance. However, it is not classified as Financial (no direct money movement) or Destructive (the action is reversible via compute_delete_instance).

From the tool's definition Tool name 'compute_create_instance' and description 'Create a new Compute Engine instance' indicate creation of cloud infrastructure resources.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

compute_create_instance Rate-limited

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

FAQ

Questions about compute_create_instance

What does the compute_create_instance tool do? +

Create a new Compute Engine instance. It is categorised as a Write tool in the Google Cloud MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

How do I enforce a policy on compute_create_instance? +

Register the Google Cloud MCP server in PolicyLayer and add a rule for compute_create_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_create_instance? +

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

Can I rate-limit compute_create_instance? +

Yes. Add a rate_limit block to the compute_create_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_create_instance completely? +

Set action: deny in the PolicyLayer policy for compute_create_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_create_instance? +

compute_create_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.