Purge soft-deleted artifacts past retention period from local store.
AI agents call cleanup_artifacts 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.
The tool performs permanent deletion ("purge") of artifacts that have been soft-deleted, making this action irreversible. While soft-deleted items may be recoverable in some systems, this cleanup operation removes them permanently from storage. This qualifies as Destructive rather than Write because it cannot be undone and represents data loss.
From the tool's definition Tool description explicitly states "Purge" soft-deleted artifacts, indicating irreversible deletion of data from the local store past a retention period.
Attacks that exploit this kind of access
Purge soft-deleted artifacts past retention period from local store. 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 cleanup_artifacts: 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.
cleanup_artifacts 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 cleanup_artifacts 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 cleanup_artifacts. 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.
cleanup_artifacts 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 →