编程

unreal-plugin

通过 MCP 客户端驱动正在运行的 Unreal Engine 编辑器，管理关卡、Actor、PIE 与控制台命令。

它能做什么

通过本地 27184 端口的嵌入式 MCP 桥接服务，以及向 OpenClaw Gateway 发起 HTTP 轮询的连接方式，控制在跑的 UE 编辑器；两种模式可同时运行。工具覆盖关卡打开/保存、Actor 创建/删除与属性编辑、基于 UE 反射的位置/旋转/缩放读写、PIE 启动/暂停/停止、视口截图、项目日志读取、键鼠模拟输入，以及控制台命令执行。插件默认开启 disableModelInvocation: true，并根据安全说明，要求在删除 Actor、保存关卡、执行控制台命令或模拟输入等破坏性操作前获得用户确认。

什么时候用它

在关卡中放置并整理基本体、灯光、相机等 Actor
迭代调试过程中读取与修改 Actor 的位置、旋转、缩放
从 MCP 客户端启动、暂停或停止 PIE
截取编辑器视口截图并读取项目日志辅助调试

技能文档

OpenClaw Unreal Plugin

MCP skill for controlling Unreal Engine Editor via OpenClaw.

Connection Modes

Mode A: OpenClaw Gateway (Remote)

The plugin connects to OpenClaw Gateway via HTTP polling. Works automatically when Gateway is running.

Mode B: MCP Direct (Claude Code / Cursor)

The plugin runs an embedded HTTP server on port 27184. Use the included MCP bridge:

# Claude Code
claude mcp add unreal -- node /path/to/Plugins/OpenClaw/MCP~/index.js

# Cursor — add to .cursor/mcp.json
{"mcpServers":{"unreal":{"command":"node","args":["/path/to/Plugins/OpenClaw/MCP~/index.js"]}}}

Both modes run simultaneously.

Editor Panel

Window → OpenClaw Unreal Plugin — opens a dockable tab with:

Connection status indicator
MCP server info (address, protocol)
Connect / Disconnect buttons
Live log of tool calls and messages

Tools

Level

level.getCurrent — current level name
level.list — all levels in project
level.open — open level by name
level.save — save current level

Actor

actor.find — find by name/class
actor.getAll — list all actors
actor.create — create actors: StaticMeshActor (Cube, Sphere, Cylinder, Cone), PointLight, Camera
actor.delete — delete by name
actor.getData — detailed actor info
actor.setProperty — set properties via UE reflection system

Transform

transform.getPosition / transform.setPosition
transform.getRotation / transform.setRotation
transform.getScale / transform.setScale

Transform tools require a valid RootComponent (works on StaticMeshActor, PointLight, etc. — not on bare Actor).

Component

component.get — get component data
component.add — add component (not yet implemented)
component.remove — remove component (not yet implemented)

Editor

editor.play — start PIE (uses RequestPlaySession)
editor.stop — stop PIE
editor.pause / editor.resume — pause/resume PIE
editor.getState — current editor state

Debug

debug.hierarchy — actor hierarchy tree
debug.screenshot — capture editor viewport
debug.log — write to output log

Input

input.simulateKey — simulate key press
input.simulateMouse — simulate mouse
input.simulateAxis — simulate axis

Asset

asset.list — list assets at path
asset.import — import asset (not yet implemented)

Console

console.execute — run console command
console.getLogs — read project log file; params: count (number of lines), filter (text filter)

Blueprint

blueprint.list — list blueprints
blueprint.open — open blueprint (not yet implemented)

Troubleshooting

Stale binaries / plugin not loading

Clear the build cache and restart the editor:

rm -rf YourProject/Plugins/OpenClaw/Binaries YourProject/Plugins/OpenClaw/Intermediate

Connection issues

Ensure OpenClaw Gateway is running: openclaw gateway status
Check the Editor Panel log for errors
Verify the MCP port is not blocked by firewall

Security & Privacy Disclosure

This skill drives a live Unreal Editor. Full disclosure of capabilities and current limitations:

Local HTTP server hardening (plugin v1.3.1+): the embedded server (port 27184) rejects browser-originated requests (any Origin header → 403) and supports optional shared-secret auth — set OPENCLAW_BRIDGE_TOKEN for both the Unreal Editor process and the MCP client to require X-OpenClaw-Token on every request. Without the token set, keep the port on trusted machines only — any local process can send editor commands.
Destructive operations — confirm with the user before: deleting actors, saving levels, importing assets, running console commands (console.execute), and simulating keyboard/mouse input. None of these should run implicitly from a vague request.
Data visibility: debug.screenshot and console.getLogs can capture whatever is on screen or in project logs — including credentials, tokens, or source paths if present. Review before sharing captures outside the machine.
Trigger scope: routine-sounding requests ("clean up the level", "save everything", "just run it") map to state-changing Editor operations — confirm once before the first state-changing call in a session.
Safety defaults: disableModelInvocation: true is set — the model cannot auto-invoke this skill; it runs only on explicit user request. Keep the project under source control before automation sessions. The Korean SKILL_KO.md states the same recommendation; if the two ever disagree, this file governs.

License

Apache-2.0 — See LICENSE.md