AI agents call list_vms to retrieve information from Vcenter without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
list_vms retrieves or queries VM inventory with no side effects. Although the tool description is empty, the name alone strongly suggests a read operation. The severity is low because listing VMs exposes metadata but carries minimal blast radius if misused by an agent.
From the tool's definition Tool name is 'list_vms' and sibling tools on the server include create_vm, delete_vm, power_off_vm, power_on_vm. The name pattern and context (listing VMs alongside destructive operations) indicate this retrieves/enumerates VMs without modification.
Attacks that exploit this kind of access
list_vms. It is categorised as a Read tool in the Vcenter MCP Server, which means it retrieves data without modifying state.
Register the Vcenter MCP server in PolicyLayer and add a rule for list_vms: 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 Vcenter. Nothing to install.
list_vms 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_vms 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_vms. 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_vms is provided by the Vcenter MCP server (michaelrice/vcenter-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →