Remove expired memories from the database
AI agents call clean_expired to permanently remove resources in Mementos — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
This tool permanently deletes records from a database without the ability to recover them. While the deletion targets only 'expired' entries (suggesting a filtered operation), the irreversible nature of removal from a database qualifies it as Destructive.
From the tool's definition Tool name 'clean_expired' and description 'Remove expired memories from the database' indicates irreversible deletion of data. The word 'Remove' combined with the context of a memory system confirms permanent data loss.
Attacks that exploit this kind of access
Remove expired memories from the database. It is categorised as a Destructive tool in the Mementos MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Mementos MCP server in PolicyLayer and add a rule for clean_expired: 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 Mementos. Nothing to install.
clean_expired 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 clean_expired 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 clean_expired. 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.
clean_expired is provided by the Mementos MCP server (@hasna/mementos). 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 →