exec_python · Touchdesigner MCP: Risk & Policy

WHAT IT DOES

What exec_python does on Touchdesigner

AI agents invoke exec_python to trigger actions in Touchdesigner. 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 IT NEEDS A POLICY

Why exec_python needs a policy

This tool allows execution of arbitrary Python code within a running TouchDesigner instance. This is a classic Execute category tool with critical severity because: (1) arbitrary Python execution can perform any action the TouchDesigner process permits, including file I/O, network access, and system commands; (2) TouchDesigner is a visual effects/multimedia platform often used in production environments, making…

From the tool's definition Tool description explicitly states 'Execute arbitrary Python inside TouchDesigner.' The name 'exec_python' and sibling tool 'eval_python' confirm execution capabilities. The server description mentions 'run arbitrary Python' as a core feature.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

exec_python Rate-limited

exec_python stays usable, but rate-capped — a runaway agent can't fire it dozens of times a minute. Everything else on the server is denied unless you say otherwise.

View as policy code

policy.json

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

RATE-LIMIT THIS TOOL →

Instant setup, no code required.

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

FAQ

Questions about exec_python

What does the exec_python tool do? +

Execute arbitrary Python inside TouchDesigner. It is categorised as a Execute tool in the Touchdesigner MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on exec_python? +

Register the Touchdesigner MCP server in PolicyLayer and add a rule for exec_python: 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 Touchdesigner. Nothing to install.

What risk level is exec_python? +

exec_python is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.

Can I rate-limit exec_python? +

Yes. Add a rate_limit block to the exec_python 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 exec_python completely? +

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

exec_python is provided by the Touchdesigner MCP server (mrinalghosh/touchdesigner-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.