AI agents use create_vm to create or update resources in Virtualization — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Virtualization environment.
Based on the tool name and server context (VirtualBox/Hyper-V VM management), create_vm likely creates a new virtual machine, which is a Write operation (reversible creation). Severity is high because VMs consume significant system resources and could be misused for resource exhaustion. Confidence is reduced due to the empty description.
From the tool's definition Tool name is 'create_vm'; description is empty or uninformative. Server description mentions VM lifecycle management including creation.
Documented attack patterns abuse exactly the kind of access create_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 create_vm:
{
"version": "1",
"default": "deny",
"tools": {
"create_vm": {
"limits": [
{
"counter": "create_vm_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
}create_vm stays usable, but capped — an agent stuck in a loop can't make hundreds of changes a minute. Everything else on the server is denied unless you say otherwise.
Free to start. No card required.
create_vm. It is categorised as a Write tool in the Virtualization MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Virtualization MCP server in PolicyLayer and add a rule for create_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.
create_vm is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the create_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 create_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.
create_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.