Remove any tile at position. Auto-solves.
AI agents call remove_tile 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 performs an irreversible deletion of tile data from a level. While the impact is scoped to game level content rather than arbitrary data, removing tiles cannot be undone and fundamentally alters the level state. The "Auto-solves" behavior suggests automatic side effects that may not be easily predictable or reversible. This is destructive of level design work rather than merely modifying it.
From the tool's definition Tool name "remove_tile" indicates deletion of level data. Description states "Remove any tile at position" with no undo mechanism indicated. Context of Ice Puzzle level design suggests this irreversibly alters level layouts.
Attacks that exploit this kind of access
Remove any tile at position. Auto-solves. 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 remove_tile: 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.
remove_tile 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 remove_tile 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 remove_tile. 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.
remove_tile 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 →