AI agents call read_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.
This tool queries and retrieves data from a Celeste map file. It performs no write, execute, or destructive operations. The verb 'Get' and the lack of any mention of modification, deletion, or external execution clearly place this in the Read category. Severity is low because unauthorized access to map file data poses minimal security risk in typical contexts.
From the tool's definition Tool name 'read_room' and description 'Get detailed data for a specific room: tiles, entities, triggers' indicate retrieval of data without modification or side effects.
Attacks that exploit this kind of access
Get detailed data for a specific room: tiles, entities, triggers. 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 read_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.
read_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 read_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 read_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.
read_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 →