UE-Editor-MCPServer

UE-Editor-MCPServer

Wraps Unreal Editor as an MCP server, enabling AI agents to automate editor tasks through Python scripts.

Category
Visit Server

README

UE-Editor-MCPServer

将 Unreal Editor 封装为 MCP (Model Context Protocol) Server,供 AI Agent 通过 Python 脚本驱动编辑器,实现自动化迭代。


快速开始

1. 安装 Python 依赖

插件根目录下执行(需要 uv):

uv sync

不使用 uv:pip install -r requirements.txt

2. 启动 UE 编辑器

启动编辑器后,C++ 模块自动启动 Forwarder(监听 127.0.0.1:8100)。

3. 配置 MCP 客户端

stdio 模式(推荐)

由 MCP 客户端自动拉起 main.py,无需手动操作。

{
  "mcpServers": {
    "ue-editor": {
      "command": "uv",
      "args": [
        "run", "--directory", "D:\\MCP\\Plugins\\UE-Editor-MCPServer",
        "python", "main.py",
        "--project", "D:\\MCP\\YourProj.uproject"
      ]
    }
  }
}

--project 指向 .uproject 路径,用于额外暴露 open_editor / close_editor 工具(自动 GPF/Build/启动/关闭编辑器)。省略则只暴露 execute_command / excute_file / get_editor_state 三个工具。

SSE 模式

手动启动 MCPStandalone:

python main.py --transport sse

客户端配置:

{
  "mcpServers": {
    "ue-editor": {
      "url": "http://127.0.0.1:8099/SSE"
    }
  }
}

SSE 端点路径大小写不敏感:/SSE、/sse、/Sse 均可。


配置说明

配置优先级:命令行参数 > 环境变量 > .env 文件 > 默认值。

.env 配置文件

在插件根目录创建 .env(可复制 .env.example):

# MCP 服务监听地址(仅 SSE 模式使用)
MCP_HOST=127.0.0.1
MCP_PORT=8099

# UE 编辑器 Forwarder 地址(TCP 转发器)
EDITOR_HOST=127.0.0.1
EDITOR_PORT=8100

默认端口:MCP 8099,Editor Forwarder 8100。多项目需分配不同端口。

参数 说明 默认值
--transport 传输模式:stdio(默认)或 sse stdio
--mcp-host MCP 监听地址(仅 SSE 模式) 127.0.0.1
--mcp-port MCP 监听端口(仅 SSE 模式) 8099
--editor-host 编辑器 Forwarder 地址 127.0.0.1
--editor-port 编辑器 Forwarder 端口 8100
--project .uproject 绝对路径,启用 open_editor / close_editor 无
--debug 调试模式(输出详细日志到 stderr) 关闭
--mypy-enabled 执行 Python 代码前启用 mypy 类型检查 关闭

mypy 类型检查(可选)

在 Python 代码执行前自动进行 mypy 类型检查,尽早发现类型错误。

启用

# .env
MYPY_ENABLED=true

或命令行:python main.py --mypy-enabled

需要系统 Python 安装 mypy:pip install mypy


故障排除

客户端无法连接

  • stdio 模式:检查客户端配置中的 command 和 args 路径是否正确
  • SSE 模式:确认已手动运行 python main.py --transport sse
  • 确认端口未被占用(默认 8099/8100)
  • 使用调试模式:python main.py --transport sse --debug

工具调用失败 / execute_command 无返回

  • 确认编辑器已完全加载(底部状态栏无"Loading")
  • 确认 Forwarder 正常运行:在编辑器 Python 控制台执行 from mcp_server import Start; Start.print_status()
  • 检查 8099 和 8100 端口是否都可访问
  • 查看 MCPStandalone 的 stderr 输出(stdio 模式在客户端日志中)

端口冲突

修改 .env:

MCP_PORT=8199
EDITOR_PORT=8200

重启编辑器并更新客户端配置。


Recommended Servers

playwright-mcp

playwright-mcp

A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.

Official
Featured
TypeScript
Magic Component Platform (MCP)

Magic Component Platform (MCP)

An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.

Official
Featured
Local
TypeScript
Audiense Insights MCP Server

Audiense Insights MCP Server

Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.

Official
Featured
Local
TypeScript
VeyraX MCP

VeyraX MCP

Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.

Official
Featured
Local
graphlit-mcp-server

graphlit-mcp-server

The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.

Official
Featured
TypeScript
Kagi MCP Server

Kagi MCP Server

An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.

Official
Featured
Python
E2B

E2B

Using MCP to run code via e2b.

Official
Featured
Neon Database

Neon Database

MCP server for interacting with Neon Management API and databases

Official
Featured
Exa Search

Exa Search

A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.

Official
Featured
Qdrant Server

Qdrant Server

This repository is an example of how to create a MCP server for Qdrant, a vector search engine.

Official
Featured