Quick Start

What Is AgentUX?

AgentUX is a unified product that combines two capabilities into a single package:

• AgentUX Plugin: a UE 5.6+ editor plugin that exposes the Unreal Editor as a JSON-RPC 2.0 API over WebSocket
• UE-GraphRAG: a 19.1M+ node knowledge base built from 27 UE5 releases, with semantic search

Together, they give your AI the ability to control the editor AND understand the engine internals, something no AI model can do out of the box.

What You're Installing

Both capabilities are exposed to Claude Code as MCP tools. Editor Control works standalone: you can start with just the plugin and add Engine Knowledge later.

Prerequisites

Quick Setup

The full setup takes four steps. For detailed instructions, see the Installation Guide.

1. Install the Plugin

Retail build: Copy the AgentUX folder into your project's plugin directory:

<YourProject>/Plugins/AgentUX/

Source build: Copy into the engine's plugin directory and build:

Engine/Build/BatchFiles/Build.bat UnrealEditor Win64 Development -Module=AgentUX

Enable the plugin in your .uproject:

{
  "Plugins": [
    { "Name": "AgentUX", "Enabled": true }
  ]
}

2. Run the Installer

From the AgentUX root directory:

python install.py

The installer handles Python dependencies, Neo4j configuration (if available), knowledge base restoration, and MCP config generation. To skip GraphRAG:

python install.py --skip-graphrag

3. Configure Claude Code

Add the generated MCP servers to your Claude Code settings (.claude/settings.json):

{
  "mcpServers": {
    "agentux": {
      "command": "python",
      "args": ["<path-to>/AgentUX/Bridge/agentux_mcp_bridge.py"]
    },
    "ue-graphrag": {
      "command": "python",
      "args": ["<path-to>/AgentUX/GraphRAG/mcp_server/server.py"],
      "env": {
        "GRAPHRAG_CONFIG": "<path-to>/AgentUX/GraphRAG/config.yaml"
      }
    }
  }
}

If you skipped GraphRAG, omit the ue-graphrag entry.

4. Launch and Verify

Open Unreal Editor.

If the AgentUX window is not already open, you may have enable to plugin by selecting it. After selecting, you will have to restart the Editor to see the menu item.

AgentUX starts listening on port 9877 automatically. Verify in the Output Log:

LogAgentUX: AgentUX WebSocket server listening on port 9877

Once the plugin is enabled, open the AgentUX window by selecting the Editor menu. AgentUX will appear on that menu, though the location is flexible depending on the other items you have loaded.

First Commands

Test editor control by spawning an actor and positioning the camera:

[
  {
    "jsonrpc": "2.0", "id": 1,
    "method": "editor.actor.spawn",
    "params": { "class": "PointLight", "location": { "x": 0, "y": 0, "z": 300 } }
  },
  {
    "jsonrpc": "2.0", "id": 2,
    "method": "editor.viewport.setCamera",
    "params": {
      "position": { "x": -500, "y": 0, "z": 300 },
      "rotation": { "pitch": -15, "yaw": 0, "roll": 0 }
    }
  }
]

All mutating operations are wrapped in undo transactions: press Ctrl+Z or call editor.state.undo to reverse them.

Built-in Safety Guards

AgentUX includes a two-layer safety system that prevents editor crashes:

• Layer 1: Hardcoded Guards (always active): Static checks block dangerous operations before they reach the engine. Examples: saving during PIE, modifying a dying actor, compiling a Blueprint mid-compilation.
• Layer 2: GraphRAG-Enhanced (when Engine Knowledge is connected): Queries the knowledge base for known assertions and preconditions, covering thousands of edge cases from check() and ensure() calls in the engine source.

Every safety error includes an actionable remediation message: the AI receives instructions like "Cannot save while PIE is running. Call editor.pie.stop first, then retry."

You can proactively check safety:

{ "jsonrpc": "2.0", "id": 1, "method": "agentux.safety.check", "params": { "operation": "editor.level.save" } }

MCP Tools Available

Next Steps

• Installation Guide: Detailed setup for all components
• API Reference: Complete reference for all 558+ methods
• GraphRAG Guide: Full knowledge base reference and workflows
• Recipes: Multi-step workflow examples