Delete a host.
AI agents call delete_host to permanently remove resources in Defined — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
This tool permanently removes a host from the Defined Networking infrastructure. Deletion of infrastructure is irreversible and has broad impact on network operations. An AI agent misusing this could inadvertently remove critical hosts, disrupting network connectivity and services.
From the tool's definition Tool name 'delete_host' with description 'Delete a host' indicates irreversible deletion of network infrastructure. The verb 'delete' combined with the network resource 'host' represents a destructive action that cannot be undone.
Attacks that exploit this kind of access
Delete a host. It is categorised as a Destructive tool in the Defined MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Defined MCP server in PolicyLayer and add a rule for delete_host: 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 Defined. Nothing to install.
delete_host 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_host 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_host. 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_host is provided by the Defined MCP server (quickvm/defined-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 →