Apply local retention cleanup after a dry run. Requires confirm=
AI agents call apply_retention_cleanup 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.
Retention cleanup operations purge/delete data that has aged out or exceeded retention policies. The requirement for explicit confirmation (confirm=) strongly implies the action is irreversible. This falls under Destructive as it permanently removes data rather than modifying it reversibly.
From the tool's definition 'Apply local retention cleanup' - cleanup operations remove data, and requiring 'confirm=' suggests an irreversible destructive action that deletes retained items
Attacks that exploit this kind of access
Apply local retention cleanup after a dry run. Requires confirm=. 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 apply_retention_cleanup: 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.
apply_retention_cleanup 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 apply_retention_cleanup 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 apply_retention_cleanup. 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.
apply_retention_cleanup 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 →