A connection checker and setup guide for linking an AI client to TouchDesigner, software for interactive graphics and multimedia. It verifies the connection and guides repairs when TouchDesigner is not responding.

Use it to check the TouchDesigner connection, inspect the connected version and system, and troubleshoot failed connections.

It helps distinguish a connection problem from a problem in the TouchDesigner project or code.

setup — Skill for Claude Code by 8beeeaaat/touchdesigner-mcp

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent

npx skills add 8beeeaaat/touchdesigner-mcp --skill setup

Clone the repo

git clone --depth 1 https://github.com/8beeeaaat/touchdesigner-mcp

Made for: Claude Code.

Or install touchdesigner, the plugin that ships this one along with the rest of its 7 skills, 2 hooks.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

README.md

[![agentmods](https://agentmods.dev/badge/skills/8beeeaaat/touchdesigner-mcp/setup/github.svg)](https://agentmods.dev/skills/8beeeaaat/touchdesigner-mcp/setup)

Your own site

<a href="https://agentmods.dev/skills/8beeeaaat/touchdesigner-mcp/setup"><img src="https://agentmods.dev/badge/skills/8beeeaaat/touchdesigner-mcp/setup/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

Your own site · 80×15

<a href="https://agentmods.dev/skills/8beeeaaat/touchdesigner-mcp/setup"><img src="https://agentmods.dev/badge/skills/8beeeaaat/touchdesigner-mcp/setup.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 96 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 903 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

Model	Per session	Once invoked
Fable 5.1	$0.00096	$0.00903
Opus 5.5	$0.00038	$0.00361
Sonnet 5.5	$0.00019	$0.00181
Haiku 4.5	$0.00010	$0.00090

Measured 25d ago against content hash 3f4a4d299482, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

setup scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 25d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

plugin/touchdesigner/skills/setup/SKILL.md · 30 lines

How it starts

The opening of the file, as written. The whole thing — 30 lines — stays where its author put it; the contents beside it link to each section on GitHub.

TD Setup

Verify that the bundled touchdesigner-mcp server can reach a running TouchDesigner instance, and walk through a fix when it cannot.

Workflow

Resolve the TouchDesigner endpoint from the active client's MCP configuration or the touchdesigner configuration session context when available. get_td_info takes no connection parameters; the MCP server's startup configuration selects the endpoint. The bundled default is http://127.0.0.1:9981. If configuration is unavailable, label that endpoint as an assumption, not a verified setting. Absence of a SessionStart hook is normal in clients that do not run Claude hooks.
Call get_td_info with no parameters.
If it succeeds, the response carries TouchDesigner's build metadata (server name, version, operating system). Report these values back to the user in plain language (e.g. "Connected to TouchDesigner on ") and confirm the connection is ready. Optionally call describe_td_tools (e.g. with detailLevel: "summary") to summarize the available tool categories so the user sees what's usable from here. Stop here — no further diagnostics are needed.
If get_td_info fails, walk the following diagnostic ladder one step at a time, asking the user to confirm each fix before moving to the next, and re-calling get_td_info after every confirmed fix: a. Is TouchDesigner running? Ask the user to confirm the TouchDesigner application is open with a project loaded. If not, ask them to launch it and load their project, then retry. b. Is mcp_webserver_base.tox imported? The project must have this component dragged into /project1. It ships in the td/ directory of the touchdesigner-mcp GitHub repository (also attached to GitHub releases). If the user hasn't imported it — or TouchDesigner isn't running at all — offer /touchdesigner:launch, which automates downloading the tox, launching TouchDesigner with it imported, and waiting for the connection; otherwise point them to the repo/release and ask them to drag it in, then retry. c. Is the WebServer DAT active on the configured port? Inside the imported component, the WebServer DAT must be running and bound to the port resolved in step 1. Ask the user to check the DAT's Active parameter and port, then retry. d. Does the configured endpoint match TouchDesigner? Compare the WebServer DAT with the endpoint resolved in step 1. In Claude Code, update the plugin's touchdesigner_host / touchdesigner_port options, then run /reload-plugins or start a new session. In Codex, rebuild the OpenAI package with the desired --host / --port, reinstall, and start a new session. For ChatGPT's registered MCP connection, update the server or tunnel configuration and refresh the connection. Do not add a duplicate server as an override.

Read the full file on GitHub · 30 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

25d ago First seen · 30 lines · 96 tokens per session scan A 3f4a4d299482

Subscribe to this mod's changes

setup is a skill published in the GitHub repository 8beeeaaat/touchdesigner-mcp (582 stars, last pushed 4d ago), licensed MIT. It adds 96 tokens to every session and 903 once invoked, about $0.0004 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-21.

Debugging mcp mcp-server touchdesigner

operator-gotchas

MUST READ before wiring a TOP, CHOP, MAT, DAT, light, camera or instancing chain you have not built before: the parameter names TD abbreviates, the defaults that silently do the wrong thing, and the input-order rules, per operator, verified on TD 2025.33230. Pair with describeoptype.

dylanroscover/Embody · 74 tokens

debug-operator

TRIGGER when operator errors appear or user reports broken behavior. Systematic diagnosis workflow.

dylanroscover/Embody · 21 tokens

chrome-devtools-cli

Use this skill to write shell scripts or run shell commands to automate tasks in the browser or otherwise use Chrome DevTools via CLI.

ChromeDevTools/chrome-devtools-mcp · 31 tokens

a11y-debugging

Uses Chrome DevTools MCP for accessibility (a11y) debugging and auditing based on web.dev guidelines. Use when testing semantic HTML, ARIA labels, focus states, keyboard navigation, tap targets, and color contrast.

ChromeDevTools/chrome-devtools-mcp · 50 tokens

chrome-devtools

Uses Chrome DevTools via MCP for efficient debugging, troubleshooting and browser automation. Use when debugging web pages, automating browser interactions, analyzing performance, or inspecting network requests. This skill does not apply to --slim mode (MCP configuration).

ChromeDevTools/chrome-devtools-mcp · 55 tokens

n8n-validation-expert

Interpret validation errors and guide fixing them. Use when encountering validation errors, validation warnings, false positives, operator structure issues, or need help understanding validation results. Also use when asking about validation profiles, error types, the validation loop process, or auto-fix capabilities.…

czlonkowski/n8n-mcp · 91 tokens