Unpublish (soft-delete) one of your marketplace levels by ID
AI agents call unpublish_level to permanently remove resources in Ice Puzzle — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
Although described as a 'soft-delete' (suggesting potential reversibility), unpublishing a marketplace level removes it from public availability and invalidates user access, effectively destroying its live distribution state. This is irreversible from the user's perspective without manual intervention by support staff.
From the tool's definition Tool name 'unpublish_level' combined with description 'Unpublish (soft-delete) one of your marketplace levels' explicitly indicates irreversible removal of published content from the marketplace.
Attacks that exploit this kind of access
Unpublish (soft-delete) one of your marketplace levels by ID. It is categorised as a Destructive tool in the Ice Puzzle MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Ice Puzzle MCP server in PolicyLayer and add a rule for unpublish_level: 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 Ice Puzzle. Nothing to install.
unpublish_level 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 unpublish_level 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 unpublish_level. 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.
unpublish_level is provided by the Ice Puzzle MCP server (wmoten/ice-puzzle-mcp). 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 →