execute_rhinoscript

What execute_rhinoscript does on Aos

AI agents invoke execute_rhinoscript to trigger actions in Aos. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call: builds kicked off, notifications sent, workflows started.

Why execute_rhinoscript is rated High

This tool executes arbitrary scripts in the Rhino environment, giving an AI agent the ability to run code whose effects depend entirely on script content. While the tool description is empty, the name and server context make the Execute category clear. Severity is high rather than critical because the blast radius is limited to Rhino's local geometry operations, not system-level or financial impacts.

From the tool's definition Tool name is 'execute_rhinoscript' which explicitly indicates execution of RhinoScript code. Server description states the system gives 'AI agents direct, programmatic control of Rhino 8' and mentions 'execute arbitrary Python scripts' as a core capability.

The rule that runs execute_rhinoscript safely

PolicyLayer is an MCP gateway: it sits between your AI agents and Aos, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For execute_rhinoscript, this is the rule to start with:

{
  "version": "1",
  "default": "deny",
  "tools": {
    "execute_rhinoscript": {
      "limits": [
        {
          "counter": "execute_rhinoscript_rate",
          "window": "minute",
          "max": 10,
          "scope": "grant"
        }
      ]
    }
  }
}

Questions about execute_rhinoscript