destroy_collection
AI agents call destroy_collection to permanently remove resources in Zvec — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
An AI agent that decides to call destroy_collection doesn't hesitate, doesn't double-check, and doesn't stop at one. Whatever it removes from Zvec is gone — there is no undo for destructive operations.
Attacks that exploit this kind of access
destroy_collection. It is categorised as a Destructive tool in the Zvec MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Zvec MCP server in PolicyLayer and add a rule for destroy_collection: 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 Zvec. Nothing to install.
destroy_collection 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 destroy_collection 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 destroy_collection. 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.
destroy_collection is provided by the Zvec MCP server (zvec-ai/zvec-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.