Revert a published article back to draft state. The article stops being visible in agent search/context but is not deleted — re-publish with knowledge_publish. REQUIRES LOOPCTL_USER_KEY (user role — orchestrator role is NOT sufficient for this destructive operation).
Part of the Loopctl server.
Free to start. No card required.
AI agents may call knowledge_unpublish to permanently remove or destroy resources in Loopctl. Without a policy, an autonomous agent could delete critical data in a loop with no way to undo the damage. PolicyLayer blocks destructive tools by default and requires explicit human approval before enabling them.
Without a policy, an AI agent could call knowledge_unpublish in a loop, permanently destroying resources in Loopctl. There is no undo for destructive operations. PolicyLayer blocks this tool by default and only allows it when a human explicitly approves the action.
Destructive tools permanently remove data. Block by default. Only enable with explicit approval workflows.
{
"version": "1",
"default": "deny",
"hide": [
"knowledge_unpublish"
]
}See the full Loopctl policy for all 52 tools.
These attack patterns abuse exactly the kind of access knowledge_unpublish gives an agent. Each links to the full case and the policy that stops it:
Other destructive tools across the catalogue. The same approach applies to each: deny by default, or require human approval.
Revert a published article back to draft state. The article stops being visible in agent search/context but is not deleted — re-publish with knowledge_publish. REQUIRES LOOPCTL_USER_KEY (user role — orchestrator role is NOT sufficient for this destructive operation).. It is categorised as a Destructive tool in the Loopctl MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Loopctl MCP server in PolicyLayer and add a rule for knowledge_unpublish: 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 Loopctl. Nothing to install.
knowledge_unpublish 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_unpublish 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_unpublish. 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_unpublish is provided by the Loopctl MCP server (loopctl-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Deterministic rules across all 52 Loopctl tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.
Free to start. No card required.
4,600+ MCP servers and 31,000+ tools scanned and risk-classified.