TouchDesigner AI Companion
This server does not currently have a deployable release on Glama. Follow the repository's setup instructions to install and configure it for your MCP client, including any required credentials and local dependencies.
TouchDesigner AI Companion
A local desktop tool that captures your TouchDesigner node network via hotkey, sends the screenshot to Claude (with vision + function calling), and returns targeted, context-aware answers about your patches — with full session memory and Langfuse observability.
Stack
Layer | Tool |
Language | Python 3.11+ |
Screenshot |
|
Hotkey listener |
|
MCP server |
|
LLM | Claude Sonnet 4 ( |
Observability | Langfuse |
Session storage | SQLite |
Related MCP server: td-mcp
How to run
# 1. Clone and enter the project
git clone <repo-url> td-companion
cd td-companion
# 2. Install dependencies
pip install -r requirements.txt
# 3. Set your API keys
cp .env.example .env
# Edit .env with your ANTHROPIC_API_KEY and Langfuse keys
# 4. Launch
python main.py
# 5. Focus your TouchDesigner window, press Ctrl+Shift+T,
# type your question, and get an answer.macOS: Grant Accessibility permissions to your terminal app when prompted by
pynput.
How it works
Hotkey → Screenshot — Pressing
Ctrl+Shift+Ttriggersmssto capture your full screen. The PNG bytes are held in memory and sent to Claude as a base64 image.Claude with function calling — The image + question + full session history are sent to Claude Sonnet 4. Claude can invoke four MCP-defined tools (
analyze_network,suggest_next_node,diagnose_problem,explain_node) by extracting what it sees in the screenshot and routing the question to the right analytical frame.Session persistence + observability — Every turn (user question + assistant answer) is saved to a local SQLite database and logged as a Langfuse trace with model, token usage, and I/O metadata for debugging and cost tracking.
Project structure
td-companion/
├── main.py # Entry point, hotkey listener, main loop
├── screenshot.py # mss screen capture → PNG bytes
├── agent.py # Claude API with vision + function calling
├── session.py # SQLite session read/write
├── observability.py # Langfuse trace logging
├── mcp_server/
│ ├── __init__.py
│ └── tools.py # 4 FastMCP tools + Anthropic tool schemas
├── .env.example
├── .gitignore
└── requirements.txtTool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
Related MCP Connectors
Use AI models for chat, image, and video generation from Claude Code and other MCP hosts.
Connect ChatGPT and Claude to your Mac, Windows or Linux with secure MCP remote access.
MCP-native notes and memory for ChatGPT, Claude, and other AI tools.
Publish and schedule videos to TikTok, YouTube Shorts, Instagram, Facebook, LinkedIn, Pinterest, Bluesky, Threads and X from Claude, Cursor or any MCP client. Upload once, post everywhere, track views in unified analytics, and retry failed posts. Official platform APIs only, free plan available. Docs: https://docs.multi-upload-tool.com/mcp
Related MCP Servers
- AlicenseAqualityDmaintenanceAn MCP server for TouchDesigner that lets you control TouchDesigner with Claude5MIT
- AlicenseAqualityDmaintenanceMCP server for controlling TouchDesigner from AI coding agents like Claude Code and Codex CLI, enabling operator manipulation, parameter control, and screenshot capture.12MIT
- AlicenseNot gradedqualityCmaintenanceMCP server + web dashboard for TouchDesigner. Inspect, optimize, and control TD patches from Claude Code or the browser.MIT
- FlicenseAqualityDmaintenanceEnables Claude to capture screenshots, watch your screen in real-time, read text via OCR, and analyze video files, all running locally as an MCP server.14-