Use this only when the user explicitly wants a todo removed permanently.
AI agents call todo_delete to permanently remove resources in Todo MCP — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
This tool permanently deletes todo items, which cannot be undone. Although the blast radius is limited to task data rather than critical systems, permanent deletion is irreversible and falls under the Destructive category. Severity is high because an AI agent could maliciously or erroneously delete all user tasks without recovery options.
From the tool's definition Tool name is 'todo_delete' and description states 'removed permanently', indicating irreversible deletion of data.
Attacks that exploit this kind of access
Use this only when the user explicitly wants a todo removed permanently. It is categorised as a Destructive tool in the Todo MCP 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 todo_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 Todo MCP. Nothing to install.
todo_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 todo_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 todo_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.
todo_delete is provided by the Todo MCP server (peterfabakker/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 →