Delete multiple memories by IDs
AI agents call bulk_forget 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 memories without apparent recovery mechanism. Destructive category is appropriate as deletion is irreversible. Severity is high because an AI agent misusing this could delete many memories at once (bulk operation), potentially losing important context or agent state.
From the tool's definition Tool name 'bulk_forget' combined with description 'Delete multiple memories by IDs' indicates irreversible deletion of data. The 'bulk' prefix suggests batch deletion affecting potentially many records.
Risk signalsBulk/mass operation — affects multiple targets
Attacks that exploit this kind of access
Delete multiple memories by IDs. 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 bulk_forget: 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.
bulk_forget 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 bulk_forget 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 bulk_forget. 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.
bulk_forget 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 →