Remove a memory subscription by ID.
AI agents call memory_unsubscribe 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.
Removing a subscription by ID is an irreversible deletion operation. Once unsubscribed, the subscription record is gone and cannot be recovered without re-creating it. This aligns with the Destructive category. Severity is medium since it affects subscription state but is scoped to a single subscription ID.
From the tool's definition 'Remove a memory subscription by ID' — permanently removes/deletes a subscription record
Attacks that exploit this kind of access
Remove a memory subscription by ID. 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 memory_unsubscribe: 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.
memory_unsubscribe 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 memory_unsubscribe 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 memory_unsubscribe. 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.
memory_unsubscribe 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 →