AI agents use update_room to create or update resources in Loenn — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Loenn environment.
The 'update_room' tool modifies existing room data in Celeste map files, which is a reversible write operation. While the description is empty, the tool name and server purpose (editing map files) clearly indicate this creates or modifies data. It's Write rather than Execute because it operates on specific game map structures, not arbitrary code execution.
From the tool's definition Tool name 'update_room' and server context enabling AI agents to 'edit' Celeste .bin map files. Sibling tools include 'add_room', 'add_entity', 'add_trigger' which are clearly write operations on game map data.
Attacks that exploit this kind of access
update_room. It is categorised as a Write tool in the Loenn MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Loenn MCP server in PolicyLayer and add a rule for update_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.
update_room is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the update_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 update_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.
update_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 →