Skip to main content
Glama

Create point cloud

create_point_cloud

Convert a depth map or synthetic pattern into a point cloud. Points are placed on a grid with Z from brightness, supporting camera, file, or animated noise inputs.

Instructions

Render a point cloud from a depth/luminance map (or a synthetic source): scatter a resolution×resolution grid of points and push each point's XYZ from the texture — X/Y from its grid position, Z from the map's brightness × depth_scale. Unlike create_depth_displacement (a continuous shaded mesh), this is a cloud of discrete dots. A GLSL TOP packs each point's position into one RGBA32float buffer, then a Geometry COMP TOP-instances a tiny sphere once per texel (reaching resolution², up to 512²≈262k points). Creates a new baseCOMP under parent_path holding the source, a monochrome heightmap, a GLSL position-pack buffer, the instanced Geometry COMP, Camera, Light, and Render TOP ending in a Null output. Source can be an animated synthetic pattern (testable without any device, the default), a movie file, the live camera (may prompt for macOS permission), or an existing TOP (e.g. a real depth map). Use create_depth_displacement instead for a continuous shaded mesh rather than discrete dots. Exposes DepthScale, PointSize, and Spin knobs — bind DepthScale to a tempo ramp or an audio feature to make the cloud heave. Returns a summary plus a JSON block with the container path, created node paths, the effective and requested source, the point count, the output path, exposed controls, any node errors, warnings, and an inline preview image.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
sourceNoTexture whose brightness drives each point's depth (Z). 'synthetic' = an animated Noise pattern, so the cloud moves and the chain is testable without any device permission (the default). 'file' = a movie file. 'camera' = live webcam/capture device (creating it may pop a one-time macOS camera-permission dialog — click Allow). 'existing' = sample a TOP you already have (e.g. a real depth map).synthetic
fileNoPath to a movie file to play as the source; used only when source='file'.
existingNoPath of an existing TOP to sample as the depth map; used only when source='existing' (falls back to synthetic noise with a warning if missing).
resolutionNoGrid side: the cloud is resolution×resolution points (count = resolution², e.g. 128 → 16 384). One point per texel of the position buffer. Capped at 512 (262 144 points) to stay GPU-sane.
depth_scaleNoHow far bright pixels push each point along +Z. 0 = a flat sheet; higher = a deeper relief.
point_sizeNoRadius of each dot (the source sphere SOP scale). TOP-instancing applies translate only, so per-point size lives on the sphere, not on instance scale.
rotateNoWhole-cloud spin around Y in degrees/sec (0 = still).
expose_controlsNoWhen true (default), expose live DepthScale, PointSize, and Spin knobs on the system container.
parent_pathNoParent network where the point-cloud container is created (default '/project1')./project1
Behavior4/5

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

Describes creation of nodes, use of GLSL and Geometry COMP, point count limits up to 512², and camera permission prompt. Annotations already indicate non-read-only and non-destructive, so description adds context.

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?

Well-structured with main action front-loaded. Every sentence adds value, no redundancy. Despite length, it's efficient for the complexity.

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

Completeness5/5

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

Thoroughly covers all aspects: rendering process, limitations, node creation, source options, exposed knobs, return value. No gaps given the tool's complexity and lack of output schema.

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%, baseline 3. Description adds meaning by explaining source options, resolution cap, depth_scale effect, point_size instance behavior, and expose_controls functionality.

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?

Clearly states it renders a point cloud from depth/luminance maps, distinguishes from sibling tool create_depth_displacement which produces a continuous shaded mesh. Uses specific verb 'render' and resource 'point cloud'.

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

Usage Guidelines5/5

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

Explicitly recommends when to use this tool vs create_depth_displacement. Also notes source options and potential macOS camera permission dialog.

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