Isaac Sim MCP Server

by whats2000

Overview Schema Source Related Servers Discussions Admin

create_camera

Add a camera sensor to an Isaac Sim scene by specifying its path, position, rotation, resolution, or a target point to aim at.

Instructions

Add a camera sensor to the scene.

Prefer target= over rotation= for aiming: cameras look down their local -Z and carry a built-in orientation, so hand-computed euler angles are easy to get wrong and give you a picture of the sky. The response echoes the rotation that was applied under "rotation" and the point under "aimed_at".

Args: prim_path: Prim path for the camera. position: [x, y, z] world position. rotation: [rx, ry, rz] rotation in degrees. Ignored if target is given. resolution: [width, height] image resolution. Default 1280x720. target: [x, y, z] world point to look at, using +Z as up. Needs a position — either passed here or already on the prim.

Input Schema

TableJSON Schema

Name	Required	Default
`target`	No
`position`	No
`rotation`	No
`prim_path`	No	/World/Camera
`resolution`	No

Output Schema

TableJSON Schema

Name	Required	Description	Default
`result`	Yes

Schema Changelog

Changes observed during successful MCP inspections.

Changed1 schema field changedv0.6.1Sep 22, 2026

addedInput schema / properties / target

Added value: +{
+  "anyOf": [
+    {
+      "items": {
+        "type": "number"
+      },
+      "type": "array"
+    },
+    {
+      "type": "null"
+    }
+  ],
+  "default": null,
+  "title": "Target"
+}

First observedv0.1.0Jun 4, 2026

TDQS

A4.4/5.0

Behavior4/5

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

With no annotations, the description must disclose behavior on its own. It reveals that cameras look down local -Z, that rotation is ignored if target is given, and that the response echoes the applied rotation and aimed_at point. This goes beyond basic schema and helps the agent anticipate outcomes. It does not mention side effects or permissions, but for a creation tool this is sufficient.

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?

The description is well-structured: a one-line purpose, a usage tip, and an Args list. The most critical guidance (prefer target over rotation) is front-loaded. It is somewhat long but every sentence earns its place given the tool's complexity. No fluff.

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 tool's complexity (aiming, multiple parameters, response echo) and lack of annotations, the description covers the essential aspects thoroughly. An output schema exists, so return format details are not needed here. It does not mention error conditions or edge cases, but those are minor for a creation tool.

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 fully compensate. It explains each parameter's meaning, units, defaults, and interactions – e.g., rotation is in degrees and ignored if target is given, target needs a position, resolution defaults to 1280x720. This is exemplary and provides all necessary semantic 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 opens with 'Add a camera sensor to the scene', which is a specific verb and resource. It is clearly distinct from sibling tools like create_light or create_lidar, so an agent can immediately understand what this tool does without inspecting the schema.

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 advises 'Prefer target= over rotation= for aiming' and explains the reason, plus states that rotation is ignored when target is given. This gives clear guidance on when to use each parameter. It does not directly contrast with sibling creation tools, but the usage context within the tool is well covered.

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