add_entity · Loenn MCP: Risk & Policy

WHAT IT DOES

What add_entity does on Loenn

AI agents use add_entity 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_entity needs a policy

This tool creates or modifies map data by adding entities to Celeste .bin files. While reversible (entities can be removed), it represents a write operation that changes the game map structure. Severity is high because uncontrolled entity addition could corrupt maps or create unintended gameplay effects.

From the tool's definition Tool name 'add_entity' combined with server description stating it 'enables AI agents to read, edit, analyze, procedurally generate, and preview Celeste .bin map files'.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

add_entity Rate-limited

add_entity 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_entity": {
      "limits": [
        {
          "counter": "add_entity_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_entity

What does the add_entity tool do? +

add_entity. 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_entity? +

Register the Loenn MCP server in PolicyLayer and add a rule for add_entity: 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_entity? +

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

Can I rate-limit add_entity? +

Yes. Add a rate_limit block to the add_entity 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_entity completely? +

Set action: deny in the PolicyLayer policy for add_entity. 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_entity? +

add_entity 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.