AI agents use modify_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.
Modifying VM settings changes the configuration of a running or stopped virtual machine (e.g., CPU, memory, network, storage). This is a Write operation since settings can typically be changed back. However, severity is high because misconfiguration could disrupt running workloads, affect network connectivity, or render VMs unbootable.
From the tool's definition 'Modify VM settings' — alters configuration of an existing virtual machine
Documented attack patterns abuse exactly the kind of access modify_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 modify_vm:
{
"version": "1",
"default": "deny",
"tools": {
"modify_vm": {
"limits": [
{
"counter": "modify_vm_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
}modify_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.
Modify VM settings. 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 modify_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.
modify_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 modify_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 modify_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.
modify_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.