AI agents call list_sandboxes to retrieve information from Virtualization without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool performs a read-only operation that enumerates running sandbox instances. It has no side effects, does not execute code, and does not modify any system state. The blast radius of misuse is minimal—an AI agent could only enumerate existing sandboxes, which provides information but cannot cause destructive or financial harm.
From the tool's definition 'List all running Windows Sandbox instances' - the tool queries and retrieves information about existing sandboxes without modifying or executing any operations.
Documented attack patterns abuse exactly the kind of access list_sandboxes 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 list_sandboxes:
{
"version": "1",
"default": "deny",
"tools": {
"list_sandboxes": {}
}
}list_sandboxes is read-only, so it stays allowed — but everything else on the server is denied unless you say otherwise.
Free to start. No card required.
List all running Windows Sandbox instances. It is categorised as a Read tool in the Virtualization MCP Server, which means it retrieves data without modifying state.
Register the Virtualization MCP server in PolicyLayer and add a rule for list_sandboxes: 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.
list_sandboxes is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the list_sandboxes 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 list_sandboxes. 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.
list_sandboxes 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.