Skip to main content
Glama

Set up body tracking

setup_body_tracking

Loads the MediaPipe engine into your TouchDesigner project to capture a webcam and output real-time body pose tracking with a 33-landmark skeleton.

Instructions

One-shot body tracking from a webcam: loads the free mediapipe-touchdesigner ENGINE (install it first with tdmcp install mediapipe-touchdesigner) into your project, starts the timeline (the engine captures the webcam through an embedded browser that only runs while playing), reads its pose JSON DAT through an adapter that emits a 33-landmark pose CHOP, and builds a live skeleton so you only need to pick your webcam and enable Pose. If the engine isn't installed yet, it tells you how. Loading the engine will prompt for camera permission on macOS (click Allow).

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
tox_pathNoPath to the MediaPipe ENGINE .tox (MediaPipe.tox — the full tracker that captures the webcam, not the bare pose_tracking.tox processor). Defaults to the package staged by `tdmcp install mediapipe-touchdesigner`, falling back to the legacy ~/tdmcp-packages path.
parent_pathNoCOMP to load the engine into./project1
build_skeletonNoAlso build a pose-skeleton visual wired to the tracked body so you see it working.
Behavior4/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

The description discloses key behavioral traits: loading an engine, starting the timeline, reading pose data, and building a skeleton. It also warns about macOS camera permission. Annotations indicate non-destructive and open-world, so the description adds meaningful context beyond annotations, though some side effects (e.g., exact component creation) are not fully detailed.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is concise (4 sentences) and front-loaded with the main purpose. Each sentence adds value: what it does, prerequisites, process, and a behavioral note. No fluff or redundancy.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the complexity (3 parameters, no output schema), the description covers the setup process, prerequisites, and result (live skeleton). It lacks details on error handling or what happens if the engine is already installed, but overall it's sufficiently complete for a setup tool.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100% with descriptions for all 3 parameters. The description adds significant context: explaining tox_path as the full engine vs. bare processor, build_skeleton as visual wiring, and parent_path as target COMP. This enriches understanding beyond the schema.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool's purpose: 'One-shot body tracking from a webcam'. It details the specific steps (loads engine, starts timeline, reads pose data, builds skeleton) and distinguishes it from sibling tools like setup_face_tracking or create_pose_tracking by focusing on body tracking setup.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description provides clear usage context, including the prerequisite of installing mediapipe-touchdesigner via tdmcp. It implies it's for initial setup but does not explicitly contrast with alternatives like create_body_reactive or manually setting up tracking, lacking explicit when-not guidance.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Install Server

Other Tools

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/Pantani/tdmcp'

If you have feedback or need assistance with the MCP directory API, please join our Discord server