add_room · Loenn MCP: Risk & Policy

WHAT IT DOES

What add_room does on Loenn

AI agents use add_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.

WHY IT NEEDS A POLICY

Why add_room needs a policy

Creating new rooms in a map file is a reversible Write operation—rooms can be removed or modified. It does not execute arbitrary code, delete data irreversibly, or commit financial transactions. The empty description slightly lowers confidence, but the tool name and server purpose make the Write classification clear.

From the tool's definition Tool name 'add_room' indicates creation of new content within Celeste map files. Server description states it enables 'edit' and 'procedurally generate' map files.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

add_room Rate-limited

add_room stays usable, but capped — an agent stuck in a loop can't make hundreds of changes a minute. Everything else on the server is denied unless you say otherwise.

View as policy code

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "add_room": {
      "limits": [
        {
          "counter": "add_room_rate",
          "window": "minute",
          "max": 30,
          "scope": "grant"
        }
      ]
    }
  }
}

LIMIT THIS TOOL →

Instant setup, no code required.

PolicyLayer is an MCP gateway: every tool call is checked against your rule before it reaches Loenn, so you can run agents against it safely.

FAQ

Questions about add_room

What does the add_room tool do? +

add_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.

How do I enforce a policy on add_room? +

Register the Loenn MCP server in PolicyLayer and add a rule for add_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.

What risk level is add_room? +

add_room is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.

Can I rate-limit add_room? +

Yes. Add a rate_limit block to the add_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.

How do I block add_room completely? +

Set action: deny in the PolicyLayer policy for add_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.

What MCP server provides add_room? +

add_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.