Isaac Sim MCP Server

by whats2000

Overview Schema Source Related Servers Discussions Admin

create_action_graph

Build OmniGraph Action Graphs programmatically in Isaac Sim, wiring nodes and setting values. Use script_file or inline_script shortcuts for quick automated setup.

Instructions

Create and wire an OmniGraph Action Graph.

Builds a complete Action Graph with nodes, connections and attribute values using og.Controller.edit(). This is the programmatic equivalent of creating an Action Graph in the visual editor.

Args: graph_path: USD prim path for the graph (default "/World/ActionGraph"). nodes: List of node definitions. Each dict has: - "path": Node path relative to graph (e.g. "OnPlaybackTick") - "type": OmniGraph node type (e.g. "omni.graph.action.OnPlaybackTick") connections: List of [source_attr, target_attr] pairs for wiring nodes. Each attr is "NodePath.outputs:attrName" or "NodePath.inputs:attrName". values: List of attribute value overrides. Each dict has: - "attr": Full attribute path (e.g. "ScriptNode.inputs:script") - "value": The value to set evaluator: Graph evaluator type (default "execution", what Action Graphs use). "push" evaluates every application update regardless of the timeline, so an OnPlaybackTick-driven ScriptNode would keep running even while the simulation is stopped. script_file: Convenience shortcut — path to a local Python script file. When provided, automatically creates OnPlaybackTick → ScriptNode nodes, wires them, and attaches the script file (sets usePath + scriptPath). The nodes and connections parameters are ignored when script_file is set. RECOMMENDED for anything you will iterate on — edit the file and reload_script "just works", with the better reload story. inline_script: Convenience shortcut — inline Python (must define setup(db)/compute(db)). Auto-creates OnPlaybackTick → ScriptNode, wires them, and sets the script inline (usePath=False). For small, static graphs. For anything you will iterate on, prefer script_file — it has the better reload story (edit the file + reload_script "just works"; inline edits need edit_action_graph).

Example (inline script — one-step): create_action_graph( inline_script="def setup(db): pass\ndef compute(db): return True" )

Example (script file — one-step, recommended for iteration): create_action_graph( script_file="/path/to/controller.py" )

Input Schema

TableJSON Schema

Name	Required	Default
`nodes`	No
`values`	No
`evaluator`	No	execution
`graph_path`	No	/World/ActionGraph
`connections`	No
`script_file`	No
`inline_script`	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

changedInput schema / properties / evaluator / default
```
Previous value: -"push"New value: +"execution"
```

addedInput schema / properties / inline_script

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

First observedv0.1.0Jun 4, 2026

TDQS

A5/5.0

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 does so thoroughly. It discloses the underlying og.Controller.edit() mechanism, automatic node creation/wiring for shortcuts, the usePath/scriptPath side effects, and explains evaluator behavior, e.g., push evaluates every application update even when the simulation is stopped.

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?

Although long, it is tightly organized with Args and two examples, and every section adds operational value. The repeated reload guidance is minor redundancy, not bloat, given how important that choice is.

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 is complete for a tool of this complexity: it covers all parameters, gives usage examples, explains tradeoffs, references sibling tools like reload_script and edit_action_graph, and the output schema is present to cover return values.

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: every one of the seven parameters is documented with defaults, expected formats, and concrete examples. It even gives exact attribute path syntax for connections and values.

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 a specific verb and resource: 'Create and wire an OmniGraph Action Graph.' It clarifies this is the programmatic equivalent of building one in the visual editor and differentiates from editing by saying it builds the complete graph, reinforced by the later reference to edit_action_graph.

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?

The description gives explicit when-to-use guidance: script_file is 'RECOMMENDED for anything you will iterate on', inline_script is 'For small, static graphs', and it states that inline edits need edit_action_graph. It also notes that nodes and connections are ignored when script_file is set, preventing misuse.

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