Skip to main content
Glama

Set up hand tracking

setup_hand_tracking

Configures MediaPipe hand tracking from a webcam, converting hand landmarks into a CHOP for gesture detection and skeleton binding.

Instructions

One-shot MediaPipe hand tracking from a webcam: loads the mediapipe-touchdesigner ENGINE (install with tdmcp install mediapipe-touchdesigner), starts the timeline, locates the engine's hand JSON DAT, and builds an adapter Script CHOP that converts the hand JSON into a canonical max_hands×21-landmark CHOP (channels: tx/ty/tz/confidence/handedness). Use coordinate_space='world' for gesture detection (3D, curled fingers separate in z). The output CHOP at <parent_path>/<adapter_name>/hand is ready for bind_to_channel or create_pose_skeleton. Shares the same engine as setup_body_tracking — both can run in the same project.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
tox_pathNoPath to the MediaPipe ENGINE .tox (MediaPipe.tox). Defaults to the package staged by `tdmcp install mediapipe-touchdesigner`, falling back to ~/tdmcp-packages. The same engine is shared with setup_body_tracking.
parent_pathNoCOMP to load the engine into./project1
max_handsNoMaximum number of hands tracked (1 or 2). Output CHOP allocates max_hands*21 samples.
coordinate_spaceNo'world' reads worldLandmarks (3D, meters, gesture-safe — curled fingers separate in z). 'image' reads normalised 2D landmarks, centred on the wrist. Use 'world' for gesture detection.world
adapter_nameNobaseCOMP name created under parent_path to house the hand Script CHOP.mp_hand_adapter
Behavior4/5

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

Annotations indicate non-read-only, non-destructive, open-world. Description adds context: engine loading, timeline start, output CHOP structure, and coordinate space behavior. No contradictions.

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

Conciseness4/5

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

Single, dense paragraph that front-loads the main action. Each sentence adds value, though could be broken into more structured points.

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?

Covers inputs, outputs (CHOP details), and relationship to body tracking. Parameter descriptions are detailed. Lacks explicit explanation of return format but compensated by description.

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%, and description adds value by explaining output CHOP format and coordinate_space implications, complementing schema effectively.

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 it sets up MediaPipe hand tracking from a webcam, with specific details on engine loading, timeline starting, and CHOP building. It distinguishes from sibling setup_body_tracking by noting shared engine.

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?

Provides explicit context for use: one-shot setup, coordinate_space advice for gesture detection, and engine sharing with body tracking. Does not specify when not to use, but offers clear 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