drio
Open app

Unreal Engine Generative AI Support Plugin

Source

UnrealMCP is here!! Automatic blueprint and scene generation from AI!! An Unreal Engine plugin for LLM/GenAI models & MCP UE5 server. Supports Claude Desktop App, Windsurf & Cursor, also includes OpenAI's GPT4o, DeepseekR1, Claude Sonnet 3.7 APIs and Grok 3, with plans to add Gemini, audio & realtime APIs soon.

Catalog onlyCatalog onlySTDIO

Overview

UnrealGenAISupport is a plugin designed for Unreal Engine that provides long-term support for various cutting-edge LLM/GenAI models, enabling seamless integration of AI capabilities into game development.

To use the plugin, integrate it into your Unreal Engine project by adding it as a submodule, setting up the necessary API keys, and enabling it in the Unreal Editor. Detailed instructions are provided in the documentation.

  • Supports multiple AI models including OpenAI's GPT-4o and Deepseek R1. - Integration with Model Control Protocol (MCP) for enhanced functionality. - Blueprint and C++ support for easy implementation. - Secure API key management and cross-platform compatibility.
  1. Enhancing NPC behavior with AI-driven dialogues.
  2. Generating dynamic game content using generative AI models.
  3. Implementing real-time AI responses in interactive experiences.

Add to your AI client

Use these steps to connect Unreal Engine Generative AI Support Plugin in Cursor, Claude, VS Code, and other MCP-compatible apps. The same JSON appears in the Use with menu above for one-click copy.

Cursor

Add this to your .cursor/mcp.json file in your project root, then restart Cursor.

.cursor/mcp.json

{
  "mcpServers": {
    "unrealgenaisupport-prajwalshettydev": {
      "command": "npx",
      "args": [
        "-y",
        "@modelcontextprotocol/server-unrealgenaisupport-prajwalshettydev"
      ]
    }
  }
}

Claude Desktop

Add this server entry to the mcpServers object in your Claude Desktop config, then restart the app.

~/Library/Application Support/Claude/claude_desktop_config.json (macOS) or %APPDATA%\Claude\claude_desktop_config.json (Windows)

{
  "mcpServers": {
    "unrealgenaisupport-prajwalshettydev": {
      "command": "npx",
      "args": [
        "-y",
        "@modelcontextprotocol/server-unrealgenaisupport-prajwalshettydev"
      ]
    }
  }
}

Claude Code

Add this to your project's .mcp.json file. Claude Code will detect it automatically.

.mcp.json (project root)

{
  "mcpServers": {
    "unrealgenaisupport-prajwalshettydev": {
      "command": "npx",
      "args": [
        "-y",
        "@modelcontextprotocol/server-unrealgenaisupport-prajwalshettydev"
      ]
    }
  }
}

VS Code (Copilot)

Add this to your .vscode/mcp.json file. Requires the GitHub Copilot extension with MCP support enabled.

.vscode/mcp.json

{
  "servers": {
    "unrealgenaisupport-prajwalshettydev": {
      "type": "stdio",
      "command": "npx",
      "args": [
        "-y",
        "@modelcontextprotocol/server-unrealgenaisupport-prajwalshettydev"
      ]
    }
  }
}

Windsurf

Add this to your Windsurf MCP config file, then restart Windsurf.

~/.codeium/windsurf/mcp_config.json

{
  "mcpServers": {
    "unrealgenaisupport-prajwalshettydev": {
      "command": "npx",
      "args": [
        "-y",
        "@modelcontextprotocol/server-unrealgenaisupport-prajwalshettydev"
      ]
    }
  }
}

Cline

Open Cline settings, navigate to MCP Servers, and add this server configuration.

Cline MCP Settings (via UI)

{
  "mcpServers": {
    "unrealgenaisupport-prajwalshettydev": {
      "command": "npx",
      "args": [
        "-y",
        "@modelcontextprotocol/server-unrealgenaisupport-prajwalshettydev"
      ]
    }
  }
}

FAQ

Is the plugin ready for production use?

No, the plugin is currently under development and not ready for production use.

What AI models are currently supported?

The plugin currently supports OpenAI's GPT-4o, GPT-4o-mini, and Deepseek R1, with plans to add more models soon.

How do I set up the API keys?

API keys can be set as environment variables in your system, and detailed instructions are provided in the documentation.