AI agents invoke proxmox_stop_vm to trigger actions in Homelab. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call — builds kicked off, notifications sent, workflows started.
This tool executes a command against infrastructure (Proxmox hypervisor) to change the state of a VM/container. While graceful shutdown is reversible (VMs can be restarted), the action itself is Execute-class because it runs an external operation whose impact depends on arguments. It is not Destructive because shutdown is not irreversible—containers and VMs can be restarted.
From the tool's definition The tool performs 'Stop (graceful shutdown) a VM or LXC container' — this is an operational action that triggers external system behavior (halting a running virtual machine), whose effects depend on which VMID argument is provided.
Attacks that exploit this kind of access
Stop (graceful shutdown) a VM or LXC container by its VMID. It is categorised as a Execute tool in the Homelab MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Homelab MCP server in PolicyLayer and add a rule for proxmox_stop_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 Homelab. Nothing to install.
proxmox_stop_vm is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.
Yes. Add a rate_limit block to the proxmox_stop_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 proxmox_stop_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.
proxmox_stop_vm is provided by the Homelab MCP server (nainounen/homelab-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 →