Delete a VM/container. Requires confirm=true.
AI agents call pve_delete_vm to permanently remove resources in Proxmox — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
Deleting a VM/container is an irreversible operation that destroys the entire compute resource and its state. Even though the tool requires confirm=true as a safety gate, the underlying action cannot be undone and represents maximal blast radius in infrastructure management. This falls squarely into the Destructive category with critical severity.
From the tool's definition Tool name explicitly states 'delete' and description confirms it 'Delete a VM/container', which irreversibly removes a virtual machine or container.
Attacks that exploit this kind of access
Delete a VM/container. Requires confirm=true. It is categorised as a Destructive tool in the Proxmox MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Proxmox MCP server in PolicyLayer and add a rule for pve_delete_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 Proxmox. Nothing to install.
pve_delete_vm is a Destructive tool with critical risk. Critical-risk tools should be blocked by default and only enabled with explicit human approval.
Yes. Add a rate_limit block to the pve_delete_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 pve_delete_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.
pve_delete_vm is provided by the Proxmox MCP server (plgonzalezrx8/proxmox-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 →