Permanently delete a trashed document and all its data (chunks, links, versions, comments). This cannot be undone.
AI agents call purge_document to permanently remove resources in Ai Brain — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
purge_document irreversibly deletes data with no recovery mechanism. It destroys multiple data types (chunks, links, versions, comments) associated with a document in a single operation. This is categorized as Destructive rather than Write because deletion is permanent and cannot be reversed.
From the tool's definition Tool description states: 'Permanently delete a trashed document and all its data (chunks, links, versions, comments).
Attacks that exploit this kind of access
Permanently delete a trashed document and all its data (chunks, links, versions, comments). This cannot be undone. It is categorised as a Destructive tool in the Ai Brain MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Ai Brain MCP server in PolicyLayer and add a rule for purge_document: 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 Ai Brain. Nothing to install.
purge_document 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 purge_document 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 purge_document. 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.
purge_document is provided by the Ai Brain MCP server (thejoshgriffith/ai-brain). 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 →