AI agents invoke stop_vm to trigger actions in Virtualization. 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.
This tool executes an operation that halts a running VM, affecting external systems and potentially interrupting services or workloads. While not destructive (data persists; the VM can be restarted), it is an Execute action because it triggers an external operation whose effects depend on which VM is targeted. The impact (taking systems offline) warrants 'high' severity.
From the tool's definition Tool name 'stop_vm' indicates it stops a running virtual machine. The server description confirms this is a VM lifecycle management tool that 'manage[s] virtual machines' through VirtualBox, Hyper-V, and Windows Sandbox.
Documented attack patterns abuse exactly the kind of access stop_vm gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Virtualization, and nothing reaches the server without passing your rules. This is the rule we recommend for stop_vm:
{
"version": "1",
"default": "deny",
"tools": {
"stop_vm": {
"limits": [
{
"counter": "stop_vm_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
}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.
Free to start. No card required.
stop_vm. It is categorised as a Execute tool in the Virtualization MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Virtualization MCP server in PolicyLayer and add a rule for 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 Virtualization. Nothing to install.
stop_vm is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.
Yes. Add a rate_limit block to the 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.
Set action: deny in the PolicyLayer policy for 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.
stop_vm is provided by the Virtualization MCP server (sandraschi/virtualization-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Virtualization, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
56 Virtualization tools catalogued and risk-classified — across an index of 43,000+ MCP servers.