How does MCP Unreal Server discover Unreal instances?
It uses multicast discovery on the default group endpoint `239.0.0.1:6766`. Ensure Unreal instances are running with the MCP plugin and multicast traffic is allowed.
@radial-hks
基本信息
A MCP Server implementation for interacting with Unreal Engine instances through remote Python execution.
使用下面的配置,将此服务器添加到你的 MCP 客户端。
{
"mcpServers": {
"MCP-Unreal-Server": {
"command": "python",
"args": [
"-m",
"src.mcp_server_unreal.server"
]
}
}
}工具列表暂未提供
当前收录暂时没有可展示的工具列表,不代表服务没有工具。请查阅项目文档了解支持的能力。
工具是从 README 中自动提取的。维护者可以在 ## Tools 标题下列出工具,即可填充这部分内容。
MCP Unreal Server is a server implementation that enables interaction with Unreal Engine instances through remote Python execution. It is designed for developers who need to programmatically control Unreal Engine environments, run scripts, and monitor nodes.
Install dependencies via pip install -r requirements.txt, then start the server with python -m src.mcp_server_unreal.server. Connect to an Unreal instance using the connect tool (multicast group 239.0.0.1:6766 by default) and execute Python code with the execute tool, specifying node ID, code, and execution mode.
mcp_unreal.log) and consoleIt uses multicast discovery on the default group endpoint `239.0.0.1:6766`. Ensure Unreal instances are running with the MCP plugin and multicast traffic is allowed.
Three modes are supported: `MODE_EXEC_FILE` (execute a Python file), `MODE_EXEC_STATEMENT` (execute a Python statement), and `MODE_EVAL_STATEMENT` (evaluate a Python expression).
Verify that Unreal instances are running and have the MCP plugin enabled. Check firewall settings for multicast traffic and inspect `mcp_unreal.log` for node status changes.
Logging can be adjusted in `server.py`: file logging level and console logging level can be set (e.g., `DEBUG` for files, `INFO` for console). Logs are written to `mcp_unreal.log`.
The server requires Python and the dependencies listed in `requirements.txt`. It communicates with Unreal Engine via remote Python execution over the network.
Hindsight: Agent Memory That Learns

Request dedicated senior developers to work on your project, write job descriptions, and prep technical interviews — all without leaving your Claude chat. Just describe what you need, and Lemon.io MCP does the rest. 1–3

Connect your AI assistant to your own YOUB endurance training account. Read recorded activities with full analysis, planned sessions, race goals, wellness (HRV, sleep, resting HR) and your athletic profile. Create or mov

Model Context Protocol Servers
YC (S26) | Open Computer History | Continuously record your company computer work, map your workflows, help you find work worth automating, and power your agents' context
评论