AI agents call list_running_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 retrieves or queries information about running sandboxes—specifically, it likely enumerates active sandbox instances. Such operations have no side effects and fall under the Read category. Severity is low because listing running sandboxes poses minimal risk; it merely exposes existing state information that an agent would already have access to within the virtualization environment.
From the tool's definition Tool name 'list_running_sandboxes' indicates a query/listing operation. The verb 'list' is a standard read operation that retrieves state information without modification. No description provided, but the naming pattern is unambiguous.
Documented attack patterns abuse exactly the kind of access list_running_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_running_sandboxes:
{
"version": "1",
"default": "deny",
"tools": {
"list_running_sandboxes": {}
}
}list_running_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_running_sandboxes. 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_running_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_running_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_running_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_running_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_running_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.