This record as markdown: /tools/tjnull-ludus-fastmcp/destroy-vm.md
What destroy_vm does on Ludus FastMCP
AI agents call destroy_vm to permanently remove resources in Ludus FastMCP, typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
Why destroy_vm is rated Critical
This tool irreversibly removes a VM instance, which cannot be undone without restoration from backups. The action has significant blast radius in a cyber range environment—a compromised AI agent could destroy critical test infrastructure, disrupt research sessions, and cause loss of experimental data. While not financial, this is more severe than Execute or Write operations.
From the tool's definition The tool name 'destroy_vm' and description 'Destroy a specific VM' use explicit destructive terminology. The verb 'destroy' indicates irreversible deletion or termination of a virtual machine.
Attacks that exploit this kind of access
The rule that runs destroy_vm safely
PolicyLayer is an MCP gateway: it sits between your AI agents and Ludus FastMCP, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For destroy_vm, this is the rule to start with:
destroy_vm is removed from the agent's tool list entirely, so the agent never calls it. The rest of the server keeps working.
The button opens the PolicyLayer dashboard: create your workspace, connect Ludus FastMCP, apply this rule, and every destroy_vm call is checked against it from then on.
Questions about destroy_vm
Destroy a specific VM. It is categorised as a Destructive tool in the Ludus FastMCP MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Ludus Fast MCP server in PolicyLayer and add a rule for destroy_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 Ludus FastMCP. Nothing to install.
destroy_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 destroy_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 destroy_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.
destroy_vm is provided by the Ludus Fast MCP server (tjnull/ludus-fastmcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on Ludus Fast, and thousands of servers like it.
Across the catalogue