Remove memories. Single deletion by ref or category+title.
AI agents call forget to permanently remove resources in Loom — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
This tool irreversibly deletes agent memories by reference or by category+title lookup. Deletion of persistent state is inherently destructive and cannot be reversed. An AI agent misusing this could erase critical episodic memories, identity context, or knowledge that the agent relies upon for coherent behavior across sessions.
From the tool's definition Remove memories. Single deletion by ref or category+title. The tool explicitly performs deletion ('Remove') of stored memory data, which cannot be undone.
Attacks that exploit this kind of access
Remove memories. Single deletion by ref or category+title. It is categorised as a Destructive tool in the Loom MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Loom MCP server in PolicyLayer and add a rule for 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 Loom. Nothing to install.
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 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 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.
forget is provided by the Loom MCP server (jbarket/loom). 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 →