Hard-delete a machine. Cannot delete primary or machines with active tasks.
AI agents call machines_delete to permanently remove resources in Todos — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
This tool performs an irreversible deletion operation ('hard-delete') on machines, which constitutes permanent data/resource destruction that cannot be undone. While the tool has guards (cannot delete primary or machines with active tasks), the core action is destructive.
From the tool's definition Tool name is 'machines_delete' and description states 'Hard-delete a machine' with explicit caveat that certain machines cannot be deleted, indicating irreversible removal of infrastructure or compute resources.
Attacks that exploit this kind of access
Hard-delete a machine. Cannot delete primary or machines with active tasks. It is categorised as a Destructive tool in the Todos MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Todos MCP server in PolicyLayer and add a rule for machines_delete: 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 Todos. Nothing to install.
machines_delete 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 machines_delete 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 machines_delete. 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.
machines_delete is provided by the Todos MCP server (@hasna/todos). 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 →