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
7.9K
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

R
Rsdoctor
Rsdoctor is a build analysis tool specifically designed for the Rspack ecosystem, fully compatible with webpack. It provides visual build analysis, multi - dimensional performance diagnosis, and intelligent optimization suggestions to help developers improve build efficiency and engineering quality.
TypeScript
6.7K
5 points
N
Next Devtools MCP
The Next.js development tools MCP server provides Next.js development tools and utilities for AI programming assistants such as Claude and Cursor, including runtime diagnostics, development automation, and document access functions.
TypeScript
9.2K
5 points
T
Testkube
Testkube is a test orchestration and execution framework for cloud-native applications, providing a unified platform to define, run, and analyze tests. It supports existing testing tools and Kubernetes infrastructure.
Go
4.9K
5 points
M
MCP Windbg
An MCP server that integrates AI models with WinDbg/CDB for analyzing Windows crash dump files and remote debugging, supporting natural language interaction to execute debugging commands.
Python
9.2K
5 points
R
Runno
Runno is a collection of JavaScript toolkits for securely running code in multiple programming languages in environments such as browsers and Node.js. It achieves sandboxed execution through WebAssembly and WASI, supports languages such as Python, Ruby, JavaScript, SQLite, C/C++, and provides integration methods such as web components and MCP servers.
TypeScript
6.1K
5 points
N
Netdata
Netdata is an open-source real-time infrastructure monitoring platform that provides second-level metric collection, visualization, machine learning-driven anomaly detection, and automated alerts. It can achieve full-stack monitoring without complex configuration.
Go
8.1K
5 points
M
MCP Server
The Mapbox MCP Server is a model context protocol server implemented in Node.js, providing AI applications with access to Mapbox geospatial APIs, including functions such as geocoding, point - of - interest search, route planning, isochrone analysis, and static map generation.
TypeScript
6.6K
4 points
U
Uniprof
Uniprof is a tool that simplifies CPU performance analysis. It supports multiple programming languages and runtimes, does not require code modification or additional dependencies, and can perform one-click performance profiling and hotspot analysis through Docker containers or the host mode.
TypeScript
8.2K
4.5 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
18.6K
4.5 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
30.6K
5 points
D
Duckduckgo MCP Server
Certified
The DuckDuckGo Search MCP Server provides web search and content scraping services for LLMs such as Claude.
Python
62.6K
4.3 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
21.2K
4.3 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#
26.4K
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
57.4K
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
19.5K
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
41.8K
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