Remove expired memories (TTL elapsed). Use dry_run to preview without deleting.
AI agents call memory_prune 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 permanently deletes data (expired memories) from persistent storage. Although deletion is conditional on TTL expiration, the operation is irreversible and fits the Destructive category.
From the tool's definition Tool description states 'Remove expired memories' and explicitly mentions 'deleting', with dry_run option to preview before deletion. The verb 'prune' combined with 'Remove' and 'deleting' indicates irreversible data removal.
Attacks that exploit this kind of access
Remove expired memories (TTL elapsed). Use dry_run to preview without deleting. 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 memory_prune: 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.
memory_prune 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_prune 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_prune. 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_prune 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 →