delete_domain
AI agents call delete_domain to permanently remove resources in Libvirt — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
Deleting a virtual machine domain is irreversible and has severe consequences—the VM and potentially its associated data are permanently removed. This is a destructive action with high blast radius if an AI agent misuses it without proper authorization or context.
From the tool's definition Tool name is 'delete_domain' combined with server context describing KVM/QEMU virtual machine management. Sibling tools include 'force_destroy_domain' which confirms the server manages destructive VM operations.
Attacks that exploit this kind of access
delete_domain. It is categorised as a Destructive tool in the Libvirt MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Libvirt MCP server in PolicyLayer and add a rule for delete_domain: 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 Libvirt. Nothing to install.
delete_domain 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_domain 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_domain. 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_domain is provided by the Libvirt MCP server (rzippert/libvirt-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 →