start_domain · Libvirt MCP: Risk & Policy

WHAT IT DOES

What start_domain does on Libvirt

AI agents invoke start_domain to trigger actions in Libvirt. 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_domain needs a policy

Starting a virtual machine is an Execute action: it launches a system whose behavior and side effects depend on what software runs inside it, what network it connects to, and what resources it accesses. While reversible (domain can be shut down), the tool initiates real computational effects outside the agent's direct control.

From the tool's definition Tool description states it will 'Start (boot) a defined domain that is currently shut off' — this triggers external VM boot operations whose effects are determined by the domain argument and the VM's configuration.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

start_domain Rate-limited

start_domain 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_domain": {
      "limits": [
        {
          "counter": "start_domain_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 Libvirt, so you can run agents against it safely.

FAQ

Questions about start_domain

What does the start_domain tool do? +

Start (boot) a defined domain that is currently shut off. It is categorised as a Execute tool in the Libvirt 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_domain? +

Register the Libvirt MCP server in PolicyLayer and add a rule for start_domain: 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 Libvirt. Nothing to install.

What risk level is start_domain? +

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

Can I rate-limit start_domain? +

Yes. Add a rate_limit block to the start_domain 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_domain completely? +

Set action: deny in the PolicyLayer policy for start_domain. 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_domain? +

start_domain is provided by the Libvirt MCP server (rzippert/libvirt-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.