Hard-delete one or more archived knowledge pages and cascade their citations.
AI agents call knowledge_purge 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 removes archived knowledge and propagates deletions to dependent citations, making the action irreversible. An AI agent with access could unintentionally erase critical memory or knowledge artifacts that other agents or systems depend on, resulting in loss of persistent state.
From the tool's definition 'Hard-delete one or more archived knowledge pages and cascade their citations' — the explicit use of 'Hard-delete' and 'cascade' indicates irreversible deletion of data with downstream effects on referential integrity.
Attacks that exploit this kind of access
Hard-delete one or more archived knowledge pages and cascade their citations. 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 knowledge_purge: 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.
knowledge_purge 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 knowledge_purge 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 knowledge_purge. 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.
knowledge_purge 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 →