AIBase
EN
Explore
Unreal MCP
U

Unreal MCP

This is a server based on the Model Context Protocol (MCP) that allows AI assistants to control the Unreal Engine game engine through the remote control API, enabling game development automation. It supports various functions such as asset management, actor control, editor operations, level management, animation physics, visual effects, and Sequencer control.
Games and gamificationDeveloper tools#Game Development#Engine Control#Automation Tools#Remote Operation.TypeScript
2.5 points
9.3K
Open Site

Overview

Installation

Tools List

Content Details

Alternatives

What is the Unreal Engine MCP Server?

This is a server based on the Model Context Protocol (MCP) that allows AI assistants (such as Claude, Cursor, etc.) to directly interact with the Unreal Engine editor. Through the remote control API, AI can perform various editor operations, from simple asset management to complex animation and visual effect creation, greatly improving the efficiency of game development.

How to use the Unreal Engine MCP Server?

Before use, ensure that Unreal Engine is installed and the necessary plugins are configured. Then install the MCP server via NPM and configure the connection information in the AI client. The server will automatically connect to Unreal Engine, and the AI assistant can then control the editor through natural language instructions.

Applicable Scenarios

Suitable for automation tasks in game development, rapid prototyping, batch operations, test scenario setup, visual effect debugging, animation preview, and other scenarios. It is particularly suitable for workflows that require frequent repetitive operations or complex combined operations.

Main Features

Asset Management
Browse, import, and create game assets, including materials, textures, models, etc. It supports multiple asset types and provides an intelligent caching mechanism to improve performance.
Actor Control
Generate, delete, and manipulate actors in the scene, supporting physical effects, position and rotation adjustment, component management, etc.
Editor Control
Control the editor state, including PIE (Play In Editor) sessions, camera operations, viewport mode switching, etc.
Level Management
Load and save levels, manage level lighting and environmental settings, and build the basic framework of the game world.
Animation and Physics
Create animation blueprints, state machines, and set up advanced features such as ragdoll physics and physical constraints.
Visual Effects
Generate particle effects, Niagara systems, GPU simulations, and debug shapes to create cool visual special effects.
Sequencer Control
Manage the Sequencer timeline, create cinematic animations, camera animations, and complex sequence controls.
Console Commands
Safely execute Unreal Engine console commands with a built - in dangerous command filtering mechanism to protect the project.
Environment Building
Create terrains, landscapes, and vegetation systems to quickly build the natural environment of the game world.
Blueprint Management
Create and edit blueprint classes, add components, set variables and functions, and implement visual programming.
Advantages
Improve development efficiency: Automate repetitive tasks through AI, saving a lot of manual operation time.
Lower the technical threshold: Non - technical users can control complex editor functions through natural language.
Flexible integration: Support multiple AI clients (Claude Desktop, Cursor, etc.).
Safe and reliable: Built - in dangerous command filtering to prevent accidental operations from damaging the project.
Automatic reconnection: Automatically attempt to reconnect when the network is interrupted to ensure service stability.
Performance optimization: The asset caching mechanism reduces repeated requests and improves response speed.
Limitations
Requires Unreal Engine to run: The Unreal Engine editor must be started to use it.
Plugin dependency: Multiple Unreal Engine plugins need to be enabled, and the configuration steps are numerous.
Network requirements: It needs to run in a local network environment, and additional configuration is required for remote connection.
Version limitation: Only supports Unreal Engine versions 5.0 - 5.6.
Learning curve: Basic Unreal Engine concepts and terms need to be understood.

How to Use

Environment Preparation
Ensure that Node.js 18+ and Unreal Engine 5.0 - 5.6 are installed. Enable the necessary plugins in Unreal Engine: Remote Control API, Remote Control Web Interface, Python Editor Script Plugin, Editor Scripting Utilities.
Configure Unreal Engine
Edit the project configuration file to enable remote execution and Python script support.
Install the MCP Server
Install the Unreal Engine MCP server globally or locally via NPM.
Configure the AI Client
Configure the MCP server connection information in AI clients such as Claude Desktop or Cursor.
Start and Use
Start the Unreal Engine editor, ensure that the AI client is connected, and then start controlling the editor through natural language.

Usage Examples

Rapid Scene Setup
Need to quickly create a test scene containing terrain, lighting, and several test models.
Batch Material Processing
Need to create and apply the same material settings to multiple models.
Performance Debugging
There are performance issues during game runtime, and various performance statistics need to be quickly viewed.
Animation Testing
Need to test the performance of character animations under different physical conditions.

Frequently Asked Questions

Why can't I connect to Unreal Engine?
Which Unreal Engine versions are supported?
How to ensure operation safety?
Is remote connection supported?
What should I do if there is no response when executing a command?
Can multiple AI clients be connected simultaneously?

Related Resources

GitHub Repository
Project source code and latest updates
NPM Package Page
NPM installation package and version information
MCP Protocol Documentation
Official specification of the Model Context Protocol
Unreal Engine Documentation
Official Unreal Engine documentation and tutorials
Docker Image
Docker containerized deployment

Installation

Copy the following command to your Client for configuration
{
  "mcpServers": {
    "unreal-engine": {
      "command": "npx",
      "args": ["unreal-engine-mcp-server"],
      "env": {
        "UE_HOST": "127.0.0.1",
        "UE_RC_HTTP_PORT": "30010",
        "UE_RC_WS_PORT": "30020",
        "UE_PROJECT_PATH": "C:/Users/YourName/Documents/Unreal Projects/YourProject"
      }
    }
  }
}

{
  "mcpServers": {
    "unreal-engine": {
      "command": "node",
      "args": ["path/to/Unreal_mcp/dist/cli.js"],
      "env": {
        "UE_HOST": "127.0.0.1",
        "UE_RC_HTTP_PORT": "30010",
        "UE_RC_WS_PORT": "30020",
        "UE_PROJECT_PATH": "C:/Users/YourName/Documents/Unreal Projects/YourProject"
      }
    }
  }
}
Note: Your key is sensitive information, do not share it with anyone.

Alternatives

V
Vestige
Vestige is an AI memory engine based on cognitive science. By implementing 29 neuroscience modules such as prediction error gating, FSRS - 6 spaced repetition, and memory dreaming, it provides long - term memory capabilities for AI. It includes a 3D visualization dashboard and 21 MCP tools, runs completely locally, and does not require the cloud.
Rust
10.1K
4.5 points
M
Moltbrain
MoltBrain is a long-term memory layer plugin designed for OpenClaw, MoltBook, and Claude Code, capable of automatically learning and recalling project context, providing intelligent search, observation recording, analysis statistics, and persistent storage functions.
TypeScript
9.6K
4.5 points
B
Bm.md
A feature-rich Markdown typesetting tool that supports multiple style themes and platform adaptation, providing real-time editing preview, image export, and API integration capabilities
TypeScript
14.5K
5 points
S
Security Detections MCP
Security Detections MCP is a server based on the Model Context Protocol that allows LLMs to query a unified security detection rule database covering Sigma, Splunk ESCU, Elastic, and KQL formats. The latest version 3.0 is upgraded to an autonomous detection engineering platform that can automatically extract TTPs from threat intelligence, analyze coverage gaps, generate SIEM-native format detection rules, run tests, and verify. The project includes over 71 tools, 11 pre-built workflow prompts, and a knowledge graph system, supporting multiple SIEM platforms.
TypeScript
7.5K
4 points
P
Paperbanana
Python
9.6K
5 points
B
Better Icons
An MCP server and CLI tool that provides search and retrieval of over 200,000 icons, supports more than 150 icon libraries, and helps AI assistants and developers quickly obtain and use icons.
TypeScript
10.2K
4.5 points
A
Assistant Ui
assistant - ui is an open - source TypeScript/React library for quickly building production - grade AI chat interfaces, providing composable UI components, streaming responses, accessibility, etc., and supporting multiple AI backends and models.
TypeScript
9.5K
5 points
A
Apify MCP Server
The Apify MCP Server is a tool based on the Model Context Protocol (MCP) that allows AI assistants to extract data from websites such as social media, search engines, and e-commerce through thousands of ready-to-use crawlers, scrapers, and automation tools (Apify Actors). It supports OAuth and Skyfire proxy payment and can be integrated into MCP clients such as Claude and VS Code through HTTPS endpoints or local stdio.
TypeScript
9.2K
5 points
N
Notion Api MCP
Certified
A Python-based MCP Server that provides advanced to-do list management and content organization functions through the Notion API, enabling seamless integration between AI models and Notion.
Python
24.3K
4.5 points
G
Gitlab MCP Server
Certified
The GitLab MCP server is a project based on the Model Context Protocol that provides a comprehensive toolset for interacting with GitLab accounts, including code review, merge request management, CI/CD configuration, and other functions.
TypeScript
26.6K
4.3 points
D
Duckduckgo MCP Server
Certified
The DuckDuckGo Search MCP Server provides web search and content scraping services for LLMs such as Claude.
Python
80.2K
4.3 points
M
Markdownify MCP
Markdownify is a multi-functional file conversion service that supports converting multiple formats such as PDFs, images, audio, and web page content into Markdown format.
TypeScript
38.4K
5 points
U
Unity
Certified
UnityMCP is a Unity editor plugin that implements the Model Context Protocol (MCP), providing seamless integration between Unity and AI assistants, including real - time state monitoring, remote command execution, and log functions.
C#
37.8K
5 points
F
Figma Context MCP
Framelink Figma MCP Server is a server that provides access to Figma design data for AI programming tools (such as Cursor). By simplifying the Figma API response, it helps AI more accurately achieve one - click conversion from design to code.
TypeScript
70.8K
4.5 points
G
Gmail MCP Server
A Gmail automatic authentication MCP server designed for Claude Desktop, supporting Gmail management through natural language interaction, including complete functions such as sending emails, label management, and batch operations.
TypeScript
24.4K
4.5 points
M
Minimax MCP Server
The MiniMax Model Context Protocol (MCP) is an official server that supports interaction with powerful text-to-speech, video/image generation APIs, and is suitable for various client tools such as Claude Desktop and Cursor.
Python
55.2K
4.8 points
AIBase
Zhiqi Future, Your AI Solution Think Tank
English简体中文繁體中文にほんご
© 2026AIBase