pve_stop_vm · Proxmox MCP: Risk & Policy

WHAT IT DOES

What pve_stop_vm does on Proxmox

AI agents invoke pve_stop_vm to trigger actions in Proxmox. 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 pve_stop_vm needs a policy

Hard stopping a VM/container is an execute action that triggers an external operation on Proxmox infrastructure. While the confirmation gate (confirm=true) provides some protection, the action itself is not reversible in the sense that running processes are forcibly terminated, potentially causing data loss or corruption.

From the tool's definition Tool description states 'Hard stop a VM/container' with a confirmation gate (requires confirm=true). This triggers an external operation with immediate effects on running infrastructure.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

pve_stop_vm Rate-limited

pve_stop_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": {
    "pve_stop_vm": {
      "limits": [
        {
          "counter": "pve_stop_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 Proxmox, so you can run agents against it safely.

FAQ

Questions about pve_stop_vm

What does the pve_stop_vm tool do? +

Hard stop a VM/container. Requires confirm=true. It is categorised as a Execute tool in the Proxmox MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on pve_stop_vm? +

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

What risk level is pve_stop_vm? +

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

Can I rate-limit pve_stop_vm? +

Yes. Add a rate_limit block to the pve_stop_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 pve_stop_vm completely? +

Set action: deny in the PolicyLayer policy for pve_stop_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 pve_stop_vm? +

pve_stop_vm is provided by the Proxmox MCP server (plgonzalezrx8/proxmox-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.