Remove a room from a map.
AI agents call remove_room to permanently remove resources in Loenn — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
Removing a room from a Celeste map file is an irreversible deletion that cannot be undone through normal tool operations (there is no 'restore_room' or 'undo' capability). This falls squarely into the Destructive category. The severity is high because it can result in permanent loss of map content, though not as critical as wholesale map deletion would be.
From the tool's definition Tool name is 'remove_room' with description 'Remove a room from a map.' The verb 'remove' combined with the inability to undo deletion of map data constitutes an irreversible destructive operation on the .bin file structure.
Attacks that exploit this kind of access
Remove a room from a map. It is categorised as a Destructive tool in the Loenn MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Loenn MCP server in PolicyLayer and add a rule for remove_room: 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 Loenn. Nothing to install.
remove_room 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_room 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_room. 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_room is provided by the Loenn MCP server (magedeline/loenn-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 →