AI agents call ai_describe_room to retrieve information from Loenn without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
Based on the tool name and sibling tools on the server (particularly 'ai_analyze_map' and 'analyze_*' variants), this tool most likely retrieves and analyzes data about a room in a Celeste map file without modifying it. This is a Read operation with low severity since it only accesses map data that the user has already loaded into the MCP context.
From the tool's definition Tool name 'ai_describe_room' suggests analyzing or describing a room within a Celeste map file. The server description indicates tools that 'read, edit, analyze, procedurally generate, and preview' maps.
Attacks that exploit this kind of access
ai_describe_room. It is categorised as a Read tool in the Loenn MCP Server, which means it retrieves data without modifying state.
Register the Loenn MCP server in PolicyLayer and add a rule for ai_describe_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.
ai_describe_room is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the ai_describe_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 ai_describe_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.
ai_describe_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 →