Permanently delete a VM (power off if running, then destroy from disk).
AI agents call delete_vm to permanently remove resources in Vcenter — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
This tool irreversibly removes virtual machines and their associated storage from the infrastructure. The permanent nature of the deletion (destroy from disk) and the inability to undo the action makes this Destructive rather than Write.
From the tool's definition Tool description explicitly states 'Permanently delete a VM' and 'destroy from disk'. The name 'delete_vm' and keywords 'permanently delete' and 'destroy from disk' confirm irreversible data destruction.
Attacks that exploit this kind of access
Permanently delete a VM (power off if running, then destroy from disk). It is categorised as a Destructive tool in the Vcenter MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Vcenter MCP server in PolicyLayer and add a rule for 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 Vcenter. Nothing to install.
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 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 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.
delete_vm 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 →