Delete a TODO item
AI agents call delete_todo to permanently remove resources in Agent Todo — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
This tool irreversibly removes a TODO item from the system. Deletion cannot be undone, making it a Destructive action rather than Write (which is reversible). While the blast radius is limited to individual task records rather than entire databases, unauthorized deletion of tasks could disrupt project management and cause loss of work history.
From the tool's definition Tool name is 'delete_todo' with description 'Delete a TODO item'. The verb 'delete' indicates irreversible removal of data.
Attacks that exploit this kind of access
Delete a TODO item. It is categorised as a Destructive tool in the Agent Todo MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Agent Todo MCP server in PolicyLayer and add a rule for delete_todo: 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 Agent Todo. Nothing to install.
delete_todo 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_todo 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_todo. 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_todo is provided by the Agent Todo MCP server (w04m1/agent-todo-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 →