pve_start_vm · Proxmox MCP: Risk & Policy

WHAT IT DOES

What pve_start_vm does on Proxmox

AI agents invoke pve_start_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_start_vm needs a policy

Starting a VM/container is an Execute category action: it runs/triggers an external operation whose effects depend on which VM/container is targeted. The blast radius is high (service disruption, resource consumption, potential cascading effects in a cluster) but not critical because the operation is reversible (VMs can be stopped).

From the tool's definition 'Start a VM/container' is an external operation that triggers infrastructure state changes (VM boot). The tool requires confirm=true but this is a procedural gate, not a technical limit—an AI agent with confirmation capability can execute this.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

pve_start_vm Rate-limited

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

FAQ

Questions about pve_start_vm

What does the pve_start_vm tool do? +

Start 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_start_vm? +

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

What risk level is pve_start_vm? +

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

Can I rate-limit pve_start_vm? +

Yes. Add a rate_limit block to the pve_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 pve_start_vm completely? +

Set action: deny in the PolicyLayer policy for pve_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 pve_start_vm? +

pve_start_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.