AI agents call get_vm_ip to retrieve information from Mcp Utm without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves network information from a running virtual machine using ARP (Address Resolution Protocol), a standard query mechanism. It does not create, modify, delete, execute code, or commit financial obligations. It is purely a read operation that queries existing VM state without any capability to alter system state or trigger external operations.
From the tool's definition Tool name is 'get_vm_ip' and description states it 'Discover the IP address of a running VM via ARP.' The verb 'discover' and the mechanism (ARP query) indicate passive information retrieval with no side effects.
Attacks that exploit this kind of access
Discover the IP address of a running VM via ARP. It is categorised as a Read tool in the Mcp Utm MCP Server, which means it retrieves data without modifying state.
Register the Mcp Utm MCP server in PolicyLayer and add a rule for get_vm_ip: 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 Mcp Utm. Nothing to install.
get_vm_ip 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 get_vm_ip 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 get_vm_ip. 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.
get_vm_ip is provided by the Mcp Utm MCP server (neverprepared/mcp-utm). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
get_vm_ip is one line of Mcp Utm's registry record.
The record carries the whole server: verified identity, auth posture, risk grade, every tool classified, recommended policy — re-checked continuously.
Teams ship this data inside their own products. See what a licence covers →