power_off_vm · Vcenter MCP: Risk & Policy

WHAT IT DOES

What power_off_vm does on Vcenter

AI agents invoke power_off_vm to trigger actions in Vcenter. 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 power_off_vm needs a policy

Powering off a VM is a disruptive external operation that immediately halts all workloads running on the VM. While not permanently destructive (the VM still exists and can be powered back on), it is not a simple write and can cause data loss or service outages for any services running on the VM. It falls under Execute as it triggers a significant external operational effect.

From the tool's definition 'Hard power off a VM by display name or moref ID' — forcibly terminates a running virtual machine

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

power_off_vm Rate-limited

power_off_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": {
    "power_off_vm": {
      "limits": [
        {
          "counter": "power_off_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 Vcenter, so you can run agents against it safely.

FAQ

Questions about power_off_vm

What does the power_off_vm tool do? +

Hard power off a VM by display name or moref ID (e.g. 'vm-42'). It is categorised as a Execute tool in the Vcenter MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on power_off_vm? +

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

What risk level is power_off_vm? +

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

Can I rate-limit power_off_vm? +

Yes. Add a rate_limit block to the power_off_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 power_off_vm completely? +

Set action: deny in the PolicyLayer policy for power_off_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 power_off_vm? +

power_off_vm is provided by the Vcenter MCP server (michaelrice/vcenter-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.