Featured

Deploy OpenClaw in 60 seconds — 20% off logoDeploy OpenClaw in 60 seconds — 20% off

Launch OpenClaw on Hostinger in about 60 seconds and keep your agent live 24/7. Our referral link gives you 20% off, no coupon code needed.

Launch on Hostinger
Run your Hermes agent on Hostinger, fully managed logoRun your Hermes agent on Hostinger, fully managed

Launch Hermes on Hostinger in one click, fully managed, no VPS knowledge needed. Use code ZACAARON10 for 10% off.

Launch on Hostinger
Crawl and scrape any site into clean data, 10% off logoCrawl and scrape any site into clean data, 10% off

Firecrawl crawls and scrapes any site into clean markdown for your agent. Get 1,000 free credits, and new users get 10% off their first purchase.

Try Firecrawl free
Your own AI agent, running 24/7 with QwikClaw logoYour own AI agent, running 24/7 with QwikClaw

QwikClaw sets up and runs an always-on OpenClaw agent for you. One click, no config files, no server setup.

Deploy now
One API to scrape, enrich, and extract the internet. logoOne API to scrape, enrich, and extract the internet.

Context.dev gives your agents a single API to scrape, enrich, and extract live web data — no proxies, no parsers, no maintenance.

Start building free
SetupClaw: done-for-you OpenClaw for founders & exec teams logoSetupClaw: done-for-you OpenClaw for founders & exec teams

White-glove OpenClaw for founders and exec teams (4–50+ employees): we install, harden, integrate your tools, and maintain it — secured from day one.

Get it set up for you
SEO data APIs for your agent, $1 free credit logoSEO data APIs for your agent, $1 free credit

DataForSEO gives your agent live access to SERP results, keyword data, backlinks, and on-page SEO data through one API. New accounts get a $1 credit, good for up to 20,000 keyword or backlink lookups.

Try DataForSEO free
Reach 47,000+ AI builders

A flat monthly placement in front of developers actively installing AI tools. No lock-in, cancel anytime.

Advertise here

Works with

Claude CodeClaude DesktopCursorVS CodeClineCodex CLIOpenClaw+ any MCP client

Install to Claude Code

This server doesn't publish a one-line install command. Follow the setup in the source repository.

Summary

MCP server for TouchDesigner - Control and operate TouchDesigner projects through AI agents

README.md

TouchDesigner MCP

![Version](https://www.npmjs.com/package/touchdesigner-mcp-server) ![Downloads](https://www.npmjs.com/package/touchdesigner-mcp-server)

This is an implementation of an MCP (Model Context Protocol) server for TouchDesigner. Its goal is to enable AI agents to control and operate TouchDesigner projects.

English / 日本語

Overview

![demo clip](https://youtu.be/V2znaqGU7f4?si=6HDFbcBHCFPdttkM&t=635)

TouchDesigner MCP acts as a bridge between AI models and the TouchDesigner WebServer DAT, enabling AI agents to:

  • Create, modify, and delete nodes
  • Query node properties and project structure
  • Programmatically control TouchDesigner via Python scripts

Installation

Please refer to the Installation Guide.

If you are updating, please refer to the procedure in the Latest Release.

MCP Server Features

This server enables AI agents to perform operations in TouchDesigner using the Model Context Protocol (MCP).

Tools

Tools allow AI agents to perform actions in TouchDesigner.

| Tool Name | Description | | :---------------------- | :----------------------------------------------------------------- | | create_td_node | Creates a new node. | | delete_td_node | Deletes an existing node. | | describe_td_tools | Generates a manifest of the available TouchDesigner tools. | | exec_node_method | Calls a Python method on a node. | | execute_python_script | Executes an arbitrary Python script in TouchDesigner. | | get_td_class_details | Gets details of a TouchDesigner Python class or module. | | get_td_classes | Gets a list of TouchDesigner Python classes. | | get_td_info | Gets information about the TouchDesigner server environment. | | get_td_module_help | Gets Python help() documentation for TouchDesigner modules/classes.| | get_td_node_errors | Checks for errors on a specified node and its children. | | get_td_node_parameters| Gets the parameters of a specific node. | | get_td_nodes | Gets nodes under a parent path, with optional filtering. | | get_top_image | Captures the current output of a TOP node as an image. | | update_td_node_parameters | Updates the parameters of a specific node. |

Prompts

Prompts provide instructions for AI agents to perform specific actions in TouchDesigner.

| Prompt Name | Description | | :------------------| :-------------------------------------------------------------------------- | | Search node | Fuzzy searches for nodes and retrieves information based on name, family, or type. | | Node connection | Provides instructions to connect nodes within TouchDesigner. | | Check node errors| Checks for errors on a specified node, and recursively for its children. |

Resources

Not implemented.

Developer Guide

Looking for local setup, client configuration, project structure, or release workflow notes? See the Developer Guide for all developer-facing documentation.

Troubleshooting

Troubleshooting version compatibility

The MCP server and the TouchDesigner component are versioned on two independent axes: the npm package version and the API version (the contract between the MCP server and the .tox component). Each release declares the API version it ships with (expectedApiVersion) and the minimum it supports (minApiVersion, currently 1.3.0). The connected component's API version is compared against those two values — the npm package version itself never gates compatibility, so updating the MCP server alone never invalidates a supported component.

| API Server (component) | Condition | Behavior | Status | |------------------------|-----------|----------|--------| | = expected API version | Matches the shipped .tox | ✅ Works silently | Compatible | | ≥ minimum, < expected | Older component | ⚠️ "Update Recommended" notice appended to responses, continues | Warning | | > expected, same MAJOR | Newer component | ⚠️ Warning to update the MCP server, continues | Warning | | MAJOR above expected | Newer API generation | ❌ Execution stops — update the MCP server | Error | | < minimum (or missing) | Too old | ❌ Execution stops — update the component | Error |

  • To resolve compatibility errors:
  1. Download the latest touchdesigner-mcp-td.zip from the releases page.
  2. Delete the existing touchdesigner-mcp-td folder and replace it with the newly extracted contents.
  3. Remove the old mcp_webserver_base component from your TouchDesigner project and import the .tox from the new folder.
  4. Restart TouchDesigner and the AI agent running the MCP server (e.g., Claude Desktop).
  • For developers: When developing locally, run npm run version after editing package.json (or simply use npm version ...). This keeps the Python API (pyproject.toml + td/modules/utils/version.py), mcpCompatibility.expectedApiVersion, MCP bundle manifest, and registry metadata in sync so that the runtime compatibility check succeeds.

For a deeper look at how the MCP server enforces these rules, see Version Compatibility Verification.

Troubleshooting connection errors

  • TouchDesignerClient caches failed connection checks for 60 seconds. Subsequent tool calls reuse the cached error to avoid spamming TouchDesigner and automatically retry after the TTL expires.
  • When the MCP server cannot reach TouchDesigner, you now get guided error messages with concrete fixes:
  • ECONNREFUSED / "connect refused": start TouchDesigner, ensure the WebServer DAT from mcp_webserver_base.tox is running, and confirm the configured port (default 9981).
  • ETIMEDOUT / "timeout": TouchDesigner is responding slowly or the network is blocked. Restart TouchDesigner/WebServer DAT or check your network connection.
  • ENOTFOUND / getaddrinfo: the host name is invalid. Use 127.0.0.1 unless you explicitly changed it.
  • The structured error text is also logged through ILogger, so you can check the MCP logs to understand why a request stopped before hitting TouchDesigner.
  • Once the underlying issue is fixed, simply run the tool again—the client clears the cached error and re-verifies the connection automatically.

Contributing

We welcome your contributions!

  1. Fork the repository.
  2. Create a feature branch (git checkout -b feature/amazing-feature).
  3. Make your changes.
  4. Add tests and ensure everything works (npm test).
  5. Commit your changes (git commit -m 'Add some amazing feature').
  6. Push to your branch (git push origin feature/amazing-feature).
  7. Open a pull request.

Please always include appropriate tests when making implementation changes.

License

MIT

See related servers & alternatives →

Related MCP servers

Browse all →

Related guides

Hand-picked reading to help you choose and use AI & ML servers.