Skip to main content

MCP Server for Unreal Engine integration

Project description

unreal-mcp-server

unreal-mcp-server is a Python-based server that implements the Model Context Protocol (MCP) for Unreal Engine. It enables smooth communication between MCP clients (e.g., Claude, Cursor, Windsurf) and the Unreal Editor, and is intended to be used together with the Unreal-MCPython Plugin.

🎯 Why Choose Unreal-MCPython?

  • 🧠 Unreal AI integration - Direct Claude AI assistance in Unreal Engine
  • 🔗 Native MCP protocol support - Seamless communication between AI and UE
  • 🎮 Intelligent game development - AI-powered asset management and scene manipulation
  • Smart automation - Context-aware blueprint scripting with AI guidance
  • 🎨 Technical artist focused - AI assistance for complex production pipelines

Key Features

  • MCP server for communication with Unreal Engine
  • Built-in routers for various operations (e.g., Actor, Asset, Editor, etc)
  • Supports Python 3.11 and later

Installation

Clone the repository:

git clone https://github.com/your-org/unreal-mcp-server.git
cd unreal-mcp-server

Running the Server

You can start the MCP server with the following command:

uv --directory absolute/path/to/unreal-mcp-server run src/unreal_mcp/main.py

Example Configuration (Using Claude, VSCode, Cursor)

The following is an example configuration for launching the MCP server from Claude, VSCode, or Cursor:

{
    "mcpServers": {
        "unreal-mcpython": {
            "command": "uv",
            "args": [
                "--directory",
                "/absolute/path/to/unreal-mcp-server",  // e.g., D:/GitHub/unreal-mcp-server
                "run",
                "src/unreal_mcp/main.py"
            ]
        }
    }
}

This configuration approach works similarly across editors like VSCode and Cursor.

License

This project is licensed under the Apache-2.0 License. See the LICENSE file for details.

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distributions

No source distribution files available for this release.See tutorial on generating distribution archives.

Built Distribution

If you're not sure about the file name format, learn more about wheel file names.

iflow_mcp_genorca_unrealmcp-1.0.1-py3-none-any.whl (22.0 kB view details)

Uploaded Python 3

File details

Details for the file iflow_mcp_genorca_unrealmcp-1.0.1-py3-none-any.whl.

File metadata

  • Download URL: iflow_mcp_genorca_unrealmcp-1.0.1-py3-none-any.whl
  • Upload date:
  • Size: 22.0 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? No
  • Uploaded via: uv/0.10.0 {"installer":{"name":"uv","version":"0.10.0","subcommand":["publish"]},"python":null,"implementation":{"name":null,"version":null},"distro":{"name":"Debian GNU/Linux","version":"13","id":"trixie","libc":null},"system":{"name":null,"release":null},"cpu":null,"openssl_version":null,"setuptools_version":null,"rustc_version":null,"ci":null}

File hashes

Hashes for iflow_mcp_genorca_unrealmcp-1.0.1-py3-none-any.whl
Algorithm Hash digest
SHA256 d59c200e5a6841991066912adde625f02003fa0da5d8f58d774111e332418e83
MD5 e9d0d886063b0a11585bbf2a98888a45
BLAKE2b-256 3d125fd55f092c6b30cd7656e81734fc7c0e52dfe5a2fd6f1c4b85f63f2eb7d6

See more details on using hashes here.

Supported by

AWS Cloud computing and Security Sponsor Datadog Monitoring Depot Continuous Integration Fastly CDN Google Download Analytics Pingdom Monitoring Sentry Error logging StatusPage Status page