Delete the TODO from DB
AI agents call deleteTodo to permanently remove resources in Todo — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
An AI agent that decides to call deleteTodo doesn't hesitate, doesn't double-check, and doesn't stop at one. Whatever it removes from Todo is gone — there is no undo for destructive operations.
Attacks that exploit this kind of access
Delete the TODO from DB. It is categorised as a Destructive tool in the Todo MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Todo MCP server in PolicyLayer and add a rule for deleteTodo: 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 Todo. Nothing to install.
deleteTodo 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 deleteTodo 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 deleteTodo. 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.
deleteTodo is provided by the Todo MCP server (yusukebe/todo-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.