Delete a remote draft from Firebase by ID
AI agents call delete_remote_draft 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.
The tool irreversibly deletes data (a draft level) from Firebase storage. This is a classic destructive operation that cannot be undone. While the blast radius is constrained to draft levels (not live published content or financial systems), the permanent loss of user work justifies 'high' severity. Confidence is high because the intent is unambiguous from both name and description.
From the tool's definition Tool name contains 'delete' and description states 'Delete a remote draft from Firebase by ID' — this explicitly removes data from a remote database without possibility of reversal.
Attacks that exploit this kind of access
Delete a remote draft from Firebase 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 delete_remote_draft: 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.
delete_remote_draft 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 delete_remote_draft 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 delete_remote_draft. 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.
delete_remote_draft 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 →