@appleweed
基本信息
An Unreal Engine plugin that implements an MCP server allowing MCP clients to access the UE Editor Python API.
使用下面的配置,将此服务器添加到你的 MCP 客户端。
{
"mcpServers": {
"unreal-engine": {
"command": "python",
"args": [
"[mac_or_windows_format_path_to_unreal_mcp_client.py]"
]
}
}
}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。
Unreal Engine MCP Python Bridge Plugin is an Unreal Engine plugin that implements the Model Context Protocol (MCP) server. It allows MCP clients, such as Anthropic’s Claude, to access the full Unreal Engine Python API, enabling AI-assisted development and automation within Unreal Engine projects.
Install the plugin from the Fab store or build from source. After enabling the plugin in Unreal Engine, click the “Start MCP Bridge” toolbar button to start a socket server on 127.0.0.1:9000. Configure your MCP client (e.g., Claude) to use unreal_mcp_client.py as the server script, then attach the client to the running bridge.
create_castle, create_town).unreal_mcp_client.py) that communicates over sockets.Add a new function decorated with `@mcp.tool()` in `unreal_mcp_client.py` that sends a command to Unreal Engine, and implement the corresponding server‑side method in `unreal_server_init.py` under the plugin’s `Content` folder. Restart Unreal Engine after server changes; restart Claude after client changes.
Python 3.10 or higher must be available on the system `PATH` with the MCP Python SDK installed (`pip install mcp`). Unreal Engine 5 with Python Editor Script Plugin enabled is required. Visual Studio 2019+ is needed only if building from source.
No. The `unreal_mcp_client.py` runs as a subprocess of your AI agent using the system Python. It communicates with Unreal Engine over a local socket.
The easiest way is from the Fab store. GitHub installation requires cloning into the `Plugins` folder of a C++ Unreal Engine project, generating Visual Studio project files, building, then enabling the plugin.
The server uses a local TCP socket (127.0.0.1:9000). No authentication is mentioned; it is designed for local use by the AI agent.
Agent-Native Terminal
Catch intent conflicts before code conflicts. The open-source coordination protocol for coding agents, built above Git.
Launch your product from your AI agent. Connect Claude Code, Codex, Cursor or ChatGPT to Launchdog over MCP and your agent drafts the listing, picks a launch week and books it. 50 launches a week, ranked only by human vo
Set up and manage the Eddyter AI rich text editor by talking to your AI agent — for Claude, Cursor, Codex and other MCP tools. A Model Context Protocol server that lets AI tools add Eddyter to a React, Next.js, Vite or R
Modelglass turns "which model should I use?" into a lookup instead of a guess. Seven tools give your agent live pricing across image, language, video, and audio models. Sourced and versioned, not scraped once and forgott
评论