Isaac Sim MCP Server

by whats2000

Overview Schema Source Related Servers Discussions Admin

get_lidar_point_cloud

Fetch lidar sensor point clouds in Isaac Sim, returning a summary, sampled points, or writing the full sweep to a .npy file.

Instructions

Get point cloud data from a lidar sensor.

Requires the timeline to be playing — RTX lidar data is produced by Replicator while the sim runs, and a sweep only completes on some frames, so an empty read means "not this frame", not "saw nothing".

By default returns a summary rather than the raw cloud: point_count, bounds, and the nearest hit. A full sweep is tens of thousands of points and megabytes of JSON, which is rarely what you want in a response.

Args: prim_path: Prim path of the lidar sensor. max_points: Include this many points in the response, sampled at an even stride across the sweep. Omit for summary only. output_path: Write the complete cloud to this .npy file and return its path; numpy.load() reads it back as an (N, 3) array.

Input Schema

TableJSON Schema

Name	Required	Default
`prim_path`	No	/World/Lidar
`max_points`	No
`output_path`	No

Output Schema

TableJSON Schema

Name	Required	Description	Default
`result`	Yes

Schema Changelog

Changes observed during successful MCP inspections.

Changed2 schema fields changedv0.6.1Sep 22, 2026

addedInput schema / properties / max_points

Added value: +{
+  "anyOf": [
+    {
+      "type": "integer"
+    },
+    {
+      "type": "null"
+    }
+  ],
+  "default": null,
+  "title": "Max Points"
+}

addedInput schema / properties / output_path

Added value: +{
+  "anyOf": [
+    {
+      "type": "string"
+    },
+    {
+      "type": "null"
+    }
+  ],
+  "default": null,
+  "title": "Output Path"
+}

First observedv0.1.0Jun 4, 2026

TDQS

A4.8/5.0

Behavior5/5

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

With no annotations, the description carries the full burden, and it excels: it explains the timing-dependent nature of RTX lidar data, the meaning of empty reads, the default summary behavior, the large size of raw clouds, and that output_path writes an .npy file readable as an (N, 3) array. This goes well beyond the minimum.

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 well-structured and front-loaded with the most critical caveat (timeline playing, sweep timing) before parameter details. Every sentence adds value, and the Args section maps cleanly to the schema without unnecessary repetition.

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?

The description fully covers prerequisites, common failure semantics, output modes, and parameter behavior. Since an output schema exists, detailed return-shape documentation is unnecessary, and nothing critical an agent needs to call the tool correctly appears missing.

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

Parameters5/5

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

Schema description coverage is 0%, so the description must compensate, and it does. Each parameter gets meaningful semantics: prim_path identifies the lidar sensor, max_points controls sampled points at even stride and can be omitted for summary-only, and output_path writes the complete cloud and returns a loadable path.

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 opens with 'Get point cloud data from a lidar sensor', a specific verb plus resource, and clearly distinguishes itself from siblings like create_lidar and capture_image. It further clarifies that the tool can return either a summary or raw points, leaving no ambiguity about its purpose.

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 gives clear context for when to use the tool: the timeline must be playing, a sweep only completes on some frames, and an empty read means 'not this frame'. It also advises when to prefer the summary over raw points, though it does not explicitly name alternative tools or exclusion conditions.

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