How can an AI agent control TouchDesigner?

An MCP-compatible AI agent can use DCC-MCP to inspect and automate operator networks, parameters, TOP capture, and project saves on the host main thread. The agent selects the correct application instance or integration, discovers available tools, and reads their parameter definitions before acting and checking the result. These typed tools declare their inputs, outputs, and parameter types.

TouchDesigner MCP and TouchDesigner CLI

The TouchDesigner MCP endpoint and TouchDesigner CLI workflow share the same DCC-MCP adapter and tool catalog. Use dcc-mcp-cli with --dcc-type touchdesigner to limit tool searches to TouchDesigner. Tools declare their inputs, outputs, and parameter types so arguments can be checked before a call.

dcc-mcp-cli search --query "inspect project state, operator paths, families, and parameters" --dcc-type touchdesigner

What can an AI agent do in TouchDesigner?

• inspect project state, operator paths, families, and parameters.
• create and connect typed operators, then set and read back bounded parameters.
• capture a TOP to PNG, save a TOE project, and verify returned size and hash metadata.

Capabilities change with the adapter version and loaded Skills. Search and describe tools first instead of guessing current tool names from this page.

Safe operating flow

1. Install and follow the public dcc-mcp Skill.
2. Inspect the existing CLI, adapter, and live hosts; obtain consent before installing software or changing system state.
3. Use health, dcc-types, and list to verify the Gateway and target instance.
4. Search and describe tools for the actual TouchDesigner task, then follow every returned next_step.
5. Make one bounded change and verify it through host state, files, previews, logs, or rendered output.

dcc-mcp-cli health
dcc-mcp-cli dcc-types
dcc-mcp-cli list

Copyable prompt

Use the dcc-mcp Skill to connect to my TouchDesigner session. Inspect the existing CLI, adapter, and live instance first; ask before installing software or changing system state. Search for and describe typed tools related to "create and connect typed operators, then set and read back bounded parameters", then follow every returned next_step. Do not delete, overwrite, or publish existing work. Make the smallest verifiable change, then check the result against this requirement: "capture a TOP to PNG, save a TOE project, and verify returned size and hash metadata". Report the instance, tool, result, and evidence path.

Current availability and official source

The current catalog lists touchdesigner as the adapter identifier. Catalog definitions do not establish host acceptance; run dcc-mcp-cli dcc-types, then discover and describe the live instance's tools before operating.

• TouchDesigner adapter repository: source of truth for installation, compatibility, host-specific capabilities, and troubleshooting.
• All AI + DCC control guides: return to every public application and pipeline integration.
• Agent workflow: shared discovery, call, validation, and diagnostic steps.

This page describes the shared Agent workflow. Each integration's repository owns its installation, API, and compatibility details.