Skip to main content
Glama

Create pose tracking

create_pose_tracking

Set up full-body pose tracking to drive body-reactive visuals. Produces canonical pose and keypoints CHOPs with optional smoothing and mirror.

Instructions

Set up full-body pose tracking — the foundation for body-reactive visuals (the camera/skeleton counterpart to extract_audio_features). Produces a canonical pose CHOP (33 MediaPipe landmarks as samples, channels tx/ty/tz/confidence) plus a 'keypoints' CHOP of ready-to-bind scalar channels (r_wrist_y, l_wrist_x, hips_x, hand_span, height, …). Source defaults to a self-contained SYNTHETIC animated pose so it builds and previews with no camera and no plugin; switch to 'mediapipe' (the free torinmb/mediapipe-touchdesigner plugin), 'osc', or an existing pose CHOP for the real performer. Smoothing and Mirror included. Feed the output into create_pose_skeleton or create_body_reactive.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
sourceNoWhere the 33-landmark pose stream comes from. 'synthetic' (default) = a self-contained animated human pose that needs NO camera and NO plugin — use it to build and preview the look instantly. 'mediapipe' = the live CHOP from the free torinmb/mediapipe-touchdesigner plugin (point mediapipe_chop_path at its pose landmarks CHOP). 'osc' = landmarks arriving over OSC (osc_port). 'existing_chop' = a pose CHOP you already built (e.g. the output of create_pose_tracking).synthetic
mediapipe_chop_pathNoPath to the MediaPipe plugin's pose-landmarks CHOP (source='mediapipe'). The plugin emits 33 samples with tx/ty/tz channels.
osc_portNoUDP port the OSC In CHOP listens on (source='osc').
existing_chop_pathNoPath of an existing pose CHOP — 33 samples, tx/ty/tz channels (source='existing_chop').
smoothingNoTemporal smoothing (0..0.95): each landmark is blended with its previous frame so jittery tracking glides instead of snapping. 0 = raw/instant; higher = smoother but laggier. Exposed as a live knob.
mirrorNoFlip the pose horizontally (negate tx) so a webcam feed reads like a mirror — the performer's right hand is on the right of the frame. Build-time; off by default.
expose_controlsNoExpose a live 'Smoothing' knob (0 = raw).
parent_pathNoParent COMP path the self-contained 'pose_tracking' container is created inside./project1
Behavior5/5

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

The description goes beyond annotations by detailing the exact outputs (canonical pose CHOP with 33 landmarks and keypoints CHOP with specific channels), the source options including a default synthetic source, and the inclusion of smoothing and mirror features. Annotations indicate readOnlyHint=false and destructiveHint=false, which align with the description's production of new CHOPs without destruction.

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 a single, front-loaded paragraph of three sentences. Every sentence is informative: first states purpose, second details outputs and sources, third mentions smoothing/mirror and next steps. No wasted words.

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 (8 parameters, no output schema), the description covers the main purpose, outputs, and usage scenarios. It mentions the key CHOP outputs and how to use them. However, it does not explicitly describe the container node that is created or the path it is placed at (parent_path is in schema but not highlighted).

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

Parameters3/5

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

Schema description coverage is 100%, so the baseline is 3. The description does not add extra meaning to parameters beyond what the schema already provides; it focuses on outputs and usage context.

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 verb 'set up' and the resource 'full-body pose tracking', and distinguishes it from siblings by mentioning it is the 'camera/skeleton counterpart to extract_audio_features' and that its output feeds into 'create_pose_skeleton or create_body_reactive'. It also specifies the exact CHOP outputs produced.

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 context for when to use this tool (as foundation for body-reactive visuals) and explains that the synthetic source allows building without a camera. It mentions alternatives like feeding into create_pose_skeleton, but does not explicitly state when not to use this tool in favor of others.

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