eval_python · Touchdesigner MCP: Risk & Policy

WHAT IT DOES

What eval_python does on Touchdesigner

AI agents invoke eval_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 eval_python needs a policy

Executing arbitrary Python expressions is an Execute-category action. Despite being framed as 'eval' (read-like), Python expressions can have side effects, access the filesystem, network, or system resources. The blast radius is high because a malicious or mistaken expression could manipulate the TouchDesigner environment, exfiltrate data, or cause unintended system interactions.

From the tool's definition "Evaluate a single Python expression in TD and return its value" — runs arbitrary Python code inside TouchDesigner

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

eval_python Rate-limited

eval_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": {
    "eval_python": {
      "limits": [
        {
          "counter": "eval_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 eval_python

What does the eval_python tool do? +

Evaluate a single Python expression in TD and return its value. 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 eval_python? +

Register the Touchdesigner MCP server in PolicyLayer and add a rule for eval_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 eval_python? +

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

Can I rate-limit eval_python? +

Yes. Add a rate_limit block to the eval_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 eval_python completely? +

Set action: deny in the PolicyLayer policy for eval_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 eval_python? +

eval_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.