ue5
Python-based MCP server for Unreal Engine 5 Blueprints. Enables LLM-powered editing of Blueprints, graphs, variables, functions, and components.
claude mcp add --transport stdio cutehusky-ue5-mcp python mcp_server.py \ --env PORT="Port to run MCP server on" \ --env UE5_REST_API_URL="http://localhost:<your_port>"
How to use
This MCP server exposes a Python-based interface that wraps the Unreal Engine 5 (UE5) Blueprint APIs via a custom UE plugin. It runs in streamable HTTP mode using FastMCP to accept and process requests to manage Blueprints, functions, variables, components, and visual scripting graphs. The server enables an AI agent to create, modify, and query Blueprint assets by issuing API calls that map to UE5 Editor Utility C++ API endpoints exposed by the plugin. Typical workflows include creating or compiling Blueprints, inspecting or editing variables and functions, adding or connecting nodes in the visual scripting graph, and managing components and their properties. Tools are organized around Blueprint Management, Blueprint Functions, Blueprint Visual Scripting, Blueprint Variables, and Blueprint Components, providing programmatic access to common UE5 Blueprint tasks via HTTP.
To use the server, run it with a configured UE5 REST API endpoint. The environment variables you’ll typically configure are PORT for the server port and UE5_REST_API_URL for the UE5 plugin/API base URL. Once running, you can issue HTTP requests (or use an agent) to perform operations such as creating a Blueprint, adding a function, or wiring up a node in a Blueprint graph. The server is designed to be integrated into larger AI-assisted pipelines where LLMs generate the requested Blueprint modifications and the MCP server executes them against the UE5 project.
How to install
Prerequisites:
- Unreal Engine 5 project with the UE5_MCP plugin installed and enabled
- Python 3.8+ installed
- Access to the project’s Plugins/ directory
Installation steps:
-
Open a terminal and navigate to your UE5 project Plugins directory:
cd <YourUEProject>/Plugins
-
Clone the MCP server repository:
git clone https://github.com/cutehusky/ue5-mcp.git
-
(Optional) Create a Python virtual environment and activate it:
python -m venv venv source venv/bin/activate # on Windows use: venv\Scripts\activate
-
Install Python dependencies for the MCP server:
cd Python/MCP pip install mcp httpx python-dotenv
-
Ensure the UE5_MCP plugin is enabled in UE5 and that the UE5 REST API is accessible at the URL you will configure in the environment variables.
-
Prepare environment variables for running the MCP server (see mcp_config for examples).
-
Run the MCP server:
python mcp_server.py
Additional notes
Tips and notes:
- Ensure the UE5 REST API endpoint (UE5_REST_API_URL) is reachable from where you run the MCP server and that any required authentication or network access is configured.
- The server uses a streamable HTTP mode via FastMCP; consider configuring the port (PORT) to avoid conflicts with other services.
- If you modify the plugin or endpoints, you may need to restart the MCP server to pick up changes.
- Use descriptive environment variable values or placeholders to document required inputs for your deployment environment.
- Common issues include network/firewall blocks between the MCP server and UE5 REST API, or missing Python dependencies; ensure the plugin is loaded in UE5 and the Python dependencies are installed.
- For debugging, check the MCP server logs for endpoint responses and any API failure messages to map them back to UE5 API calls.
Related MCP Servers
firecrawl
🔥 Official Firecrawl MCP Server - Adds powerful web scraping and search to Cursor, Claude and any other LLM clients.
Unreal_mcp
A comprehensive Model Context Protocol (MCP) server that enables AI assistants to control Unreal Engine through the native C++ Automation Bridge plugin. Built with TypeScript, C++, and Rust (WebAssembly) for ultra-high-performance game development automation.
MiniMax -JS
Official MiniMax Model Context Protocol (MCP) JavaScript implementation that provides seamless integration with MiniMax's powerful AI capabilities including image generation, video generation, text-to-speech, and voice cloning APIs.
furi
CLI & API for MCP management
flapi
API Framework heavily relying on the power of DuckDB and DuckDB extensions. Ready to build performant and cost-efficient APIs on top of BigQuery or Snowflake for AI Agents and Data Apps
ContextPods
Model Context Protocol management suite/factory. An MCP that can generate and manage other local MCPs in multiple languages. Uses the official SDKs for code gen.