Skip to main content
Glama

Make a network react to body pose

create_pose_reactive

Create reactive scalar channels (height, openness, angle, velocity) from MediaPipe pose landmarks with confidence gating and smoothing, ready for parameter binding.

Instructions

Body-pose binder parallel to bind_audio_reactive: take the 33-sample MediaPipe pose CHOP produced by setup_body_tracking and derive scalar reactive channels (right-hand height, arms openness, elbow angle, hand velocity, …) on a Null CHOP ready for bind_to_channel. Each channel is a Select→Math→Hold→Filter→Limit→Rename chain inside a fresh baseCOMP, all merged into one null_out. Supported metrics: y/x/z (1 landmark), distance/openness (2 landmarks), angle (3 — vertex middle), velocity (1, time-derivative). Optional bindings[] writes expression-mode binds directly onto target parameters (same shape as bind_to_channel; failures collected as warnings, not throws). Exposes a Reactive custom page with Smoothing/Intensity/Bypass/Gate_ knobs. Heads-up: MediaPipe's landmarks are 2D (z near-zero) — z/distance/angle/velocity are unreliable unless the adapter exposes worldLandmarks; the tool emits a warning when it detects a constant tz. Run setup_body_tracking first.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
source_chopYesPath to the 33-sample MediaPipe pose CHOP (tx/ty/tz/confidence channels) — typically the Null produced by setup_body_tracking.
channelsYesReactive channels to derive. Landmark IDs cheat-sheet — 0 nose, 11 L-shoulder, 12 R-shoulder, 13 L-elbow, 14 R-elbow, 15 L-wrist, 16 R-wrist, 23 L-hip, 24 R-hip, 25 L-knee, 26 R-knee, 27 L-ankle, 28 R-ankle.
parent_pathNoParent COMP path./project1
container_nameNoContainer baseCOMP name (created under parent_path).pose_reactive
bindingsNoOptional list of parameter paths to bind to the derived channels (expression-mode bind, like bind_audio_reactive).
smoothingNo0=raw, 1=very smoothed (drives filter width).
intensityNoMaster reactivity scaler (0=off, 1=normal, 2=strong).
expose_controlsNoAppend Smoothing/Intensity/Bypass/Gate_<name> knobs to the container.
Behavior4/5

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

Annotations indicate readOnlyHint=false (creates network), destructiveHint=false, openWorldHint=true. The description adds details: it creates a fresh baseCOMP with a node chain (Select→Math→Hold→Filter→Limit→Rename), merges into one null_out, emits warnings for constant tz, and handles binding failures as non-throwing warnings. No contradiction with annotations.

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

Conciseness3/5

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

The description is long but well-structured: first sentence introduces purpose, then technical details, then caveats. However, it is dense with information and could be more concise while retaining value.

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?

For a tool with no output schema, the description covers the output (null_out), the container created, the Reactive custom page, prerequisites (setup_body_tracking), and warnings. It is fairly complete, though missing explicit mention of the output format (a Null CHOP with channels).

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%, so baseline 3. The description adds value by explaining the node chain, supported metrics, and the behavior of bindings (array of binds, warnings). It also includes a landmark ID cheat-sheet in the schema description, enhancing 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 states it is a 'Body-pose binder parallel to bind_audio_reactive' and explains it takes a MediaPipe pose CHOP to derive scalar reactive channels, providing specific metrics. It distinguishes itself from sibling tools like bind_audio_reactive and bind_to_channel by naming them and noting similarities.

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 explicitly instructs to run setup_body_tracking first and provides a heads-up about MediaPipe's 2D landmarks. It does not list explicit when-not-to-use conditions, but the context is clear and includes prerequisites.

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