Featured

Deploy OpenClaw in 60 seconds — 20% off logoDeploy OpenClaw in 60 seconds — 20% off

Launch OpenClaw on Hostinger in about 60 seconds and keep your agent live 24/7. Our referral link gives you 20% off, no coupon code needed.

Launch on Hostinger
Run your Hermes agent on Hostinger, fully managed logoRun your Hermes agent on Hostinger, fully managed

Launch Hermes on Hostinger in one click, fully managed, no VPS knowledge needed. Use code ZACAARON10 for 10% off.

Launch on Hostinger
Crawl and scrape any site into clean data, 10% off logoCrawl and scrape any site into clean data, 10% off

Firecrawl crawls and scrapes any site into clean markdown for your agent. Get 1,000 free credits, and new users get 10% off their first purchase.

Try Firecrawl free
Your own AI agent, running 24/7 with QwikClaw logoYour own AI agent, running 24/7 with QwikClaw

QwikClaw sets up and runs an always-on OpenClaw agent for you. One click, no config files, no server setup.

Deploy now
One API to scrape, enrich, and extract the internet. logoOne API to scrape, enrich, and extract the internet.

Context.dev gives your agents a single API to scrape, enrich, and extract live web data — no proxies, no parsers, no maintenance.

Start building free
SetupClaw: done-for-you OpenClaw for founders & exec teams logoSetupClaw: done-for-you OpenClaw for founders & exec teams

White-glove OpenClaw for founders and exec teams (4–50+ employees): we install, harden, integrate your tools, and maintain it — secured from day one.

Get it set up for you
SEO data APIs for your agent, $1 free credit logoSEO data APIs for your agent, $1 free credit

DataForSEO gives your agent live access to SERP results, keyword data, backlinks, and on-page SEO data through one API. New accounts get a $1 credit, good for up to 20,000 keyword or backlink lookups.

Try DataForSEO free
Reach 47,000+ AI builders

A flat monthly placement in front of developers actively installing AI tools. No lock-in, cancel anytime.

Advertise here

Works with

Claude CodeClaude DesktopCursorVS CodeClineCodex CLIOpenClaw+ any MCP client

Install to Claude Code

This server doesn't publish a one-line install command. Follow the setup in the source repository.

Summary

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

README.md

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 commandargs 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 80998100 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。

---

See related servers & alternatives →

Related MCP servers

Browse all →

Related guides

Hand-picked reading to help you choose and use Productivity servers.