Which AI tools are supported?
The server supports Claude Code, Cursor, VS Code/Copilot, Gemini CLI, Windsurf, JetBrains/Rider, Zed, and Amazon Q.
@aadeshrao123
Basic information
MCP bridge that connects AI coding assistants to the Unreal Engine 5 editor. Create materials, blueprints, spawn actors, manage data tables, profile performance, and 100+ more tools — all through natural language. Works with Claude Code, Cursor, VS Code, Gemini, Windsurf, JetBrai
Add this server to your MCP-compatible client using the configuration below.
{
"mcpServers": {
"unreal": {
"command": "unrealmcp",
"args": [],
"env": {}
}
}
}Tool list not available yet
This listing does not currently have a tool list to display. This does not mean the server has no tools; check its documentation for supported capabilities.
We auto-extract tools from the README. The maintainer can list them under a ## Tools heading to populate this section.
Unreal MCP is a Model Context Protocol bridge for Unreal Engine 5 that enables AI assistants to control the editor through over 100 tools. It is designed for game developers using UE5 who want to leverage AI coding assistants like Claude Code, Cursor, or GitHub Copilot to automate editor tasks.
Install the Python package via pip install unrealmcp, then add the server to your AI tool’s MCP configuration with "command": "unrealmcp". The server automatically discovers a running UE5 editor instance via a port file—no manual paths, tokens, or Docker setup are required.
"command": "unrealmcp" in your MCP configThe server supports Claude Code, Cursor, VS Code/Copilot, Gemini CLI, Windsurf, JetBrains/Rider, Zed, and Amazon Q.
A C++ plugin runs inside the UE5 editor as a TCP server. The Python MCP server translates AI tool calls into TCP commands. The server auto-discovers the editor via a port file, so no manual port configuration is needed.
The bridge has been tested on Unreal Engine 5.7 and may work on earlier 5.x versions.
The `unrealmcp` package handles the MCP side; a C++ plugin runs inside the UE5 editor. No additional tokens, paths, or Docker setup are required.
Yes. The server auto-discovers the running editor via a port file, eliminating the need for manual port configuration.

SSH MCP server for AI agents: remote commands, file transfer, log search and server audits through OpenSSH.

Build custom POS apps with your AI agent. Final's MCP server lets developers scaffold checkout flows, adapt vetted screen blueprints for counter POS, self-checkout kiosks, restaurant ordering and payment terminals, previ
OrangePro local-first CLI + MCP server for behavior mapping, grounded test generation, and dynamic proof.

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
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
Comments