start_vm · Cloud VM MCP: Risk & Policy

WHAT IT DOES

What start_vm does on Cloud VM MCP

AI agents invoke start_vm to trigger actions in Cloud VM MCP. 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_vm needs a policy

Starting a VM is an Execute action because it performs an irreversible operational change on cloud infrastructure. While not destructive in the sense of deleting data, it modifies system state and has real-world consequences (resource allocation, costs, service availability).

From the tool's definition Tool name 'start_vm' and description 'Start a virtual machine' indicate the tool triggers an external operation (VM startup) whose effects depend on which VM is targeted.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

start_vm Rate-limited

start_vm 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_vm": {
      "limits": [
        {
          "counter": "start_vm_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 Cloud VM MCP, so you can run agents against it safely.

FAQ

Questions about start_vm

What does the start_vm tool do? +

Start a virtual machine. It is categorised as a Execute tool in the Cloud VM MCP 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_vm? +

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

What risk level is start_vm? +

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

Can I rate-limit start_vm? +

Yes. Add a rate_limit block to the start_vm 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_vm completely? +

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

start_vm is provided by the Cloud VM MCP server (sondt2709/cloud-vm-mcp-py). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.