touchdesigner-mcp

Control a running TouchDesigner instance through the twozero MCP interface.

Updated May 12, 2026
One-click install
npx skills add https://github.com/hungthinh04/Hermes_AI_Agent --skill touchdesigner-mcp-hungthinh04
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: touchdesigner-mcp
Source: https://github.com/hungthinh04/Hermes_AI_Agent/tree/main/skills/creative/touchdesigner-mcp
Command: npx skills add https://github.com/hungthinh04/Hermes_AI_Agent --skill touchdesigner-mcp-hungthinh04

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires PyYAML, and includes scripts (resource) and references (resource) components.

What problem does it solve?

This Skill removes the friction of building and debugging TouchDesigner networks by letting an AI inspect, create, wire, and repair operators directly through MCP.

Core Features & Use Cases

  • Real-time network control: Create operators, set parameters safely, wire connections, inspect errors, and capture screenshots in a running TouchDesigner instance.
  • Creative coding workflows: Build GLSL visuals, audio-reactive systems, feedback loops, projection-mapped outputs, and recording pipelines with validated TouchDesigner patterns.
  • Robust production guidance: The Skill emphasizes discovery-first parameter lookup, relative-path scripting, native MCP tools, and troubleshooting rules that reduce version-specific failures.
  • Use case: A creative technologist can ask for an audio-reactive visual setup, and the Skill can assemble the CHOP, TOP, and GLSL network, verify parameters, and help iterate on the result.

Quick Start

Ask the assistant to inspect the current TouchDesigner network and build a small audio-reactive GLSL setup with safe parameter discovery and verified connections.

Frequently Asked Questions about touchdesigner-mcp

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I automate TouchDesigner network creation with AI?

Automate TouchDesigner network creation by using an MCP interface to let AI inspect, create, wire, and repair operators directly in a running instance. This removes friction by applying validated patterns for parameter editing and real-time visual builds.

Can I build audio-reactive GLSL visuals in TouchDesigner through AI prompts?

Build audio-reactive GLSL visuals by asking an AI assistant to assemble the required CHOP, TOP, and GLSL network. The AI verifies parameters and connections, ensuring safe operator creation and iteration within your TouchDesigner environment.

Does this TouchDesigner MCP control approach support projection mapping and recording pipelines?

Control projection mapping and recording pipelines in TouchDesigner through native MCP tools that manage real-time visual builds. The approach handles interactive installations and recording setups using discovery-first parameter lookup and validated wiring.

What is the best way to debug TouchDesigner operators without manual inspection?

Debug TouchDesigner operators without manual inspection by leveraging an MCP interface to capture screenshots, inspect errors, and apply validation-driven error handling. The AI repairs networks directly by using safe relative-path scripting.

Why does my AI-assisted TouchDesigner parameter editing fail on different versions?

AI-assisted TouchDesigner parameter editing fails across versions when safe discovery-first parameter lookup is skipped. Using native MCP tools and relative-path scripting reduces version-specific failures by validating parameter existence before editing.

Do I need a running TouchDesigner instance to use MCP for creative coding workflows?

A running TouchDesigner instance is required to use MCP for creative coding workflows. The MCP interface controls live operators, meaning the AI creates, wires, and debugs networks by interacting with your active project file in real time.