Delete a VM (use with caution!)
AI agents call pve_delete_vm to permanently remove resources in Proxmox MCP Server — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
Deleting a VM irreversibly destroys compute infrastructure, including any attached storage, configurations, and running state. This cannot be undone and has severe blast radius if triggered erroneously by an AI agent—complete loss of virtual infrastructure. The explicit caution in the description confirms destructive intent.
From the tool's definition Tool name 'pve_delete_vm' and description 'Delete a VM (use with caution!)' both indicate permanent removal of virtual machine resources. The parenthetical warning reinforces the irreversible nature of this operation.
Attacks that exploit this kind of access
Delete a VM (use with caution!). It is categorised as a Destructive tool in the Proxmox MCP Server MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Proxmox MCP Server 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 MCP Server. 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 MCP server (mjrestivo16/mcp-proxmox). 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 →