About MCP Unreal Server
MCP Unreal Server interacts with Unreal Engine instances through remote Python execution, for Unreal project development and automation. It supports automatic node discovery and status monitoring, with file execution and statement evaluation modes.
Key features
- 01Discover Unreal nodes automatically
- 02Monitor node status and connection health
- 03Run Python in Unreal environments
- 04Execute files and evaluate statements
- 05Provide file and console logging
Use cases
- 01Find and connect to running Unreal instances
- 02Run Python files in Unreal environments
- 03Execute or evaluate Python remotely
- 04Monitor node connections and status
MCP support
The MCP server provides clients with Unreal instance resources and remote Python execution, including file execution, statement execution, and expression evaluation.
Configuration
Local server config is the same for every client. Copy it into your client’s MCP config file.
We haven’t collected a package or remote endpoint for this server. Follow the instructions in the project README.
Tools
Local servers expose tools only once running on your machine, and the maintainer has not provided a tool list.
Details
From the project READMEMCP Unreal Server
A server implementation for interacting with Unreal Engine instances through remote Python execution.
Features
-
🚀 Unreal Instance Management
- Automatic discovery of Unreal nodes via multicast
- Real-time node status monitoring
- Resource listing through LSP-compatible clients
-
💻 Remote Execution
- Execute Python code in Unreal Engine environments
- Support for both attended and unattended execution modes
- File execution and statement evaluation modes
-
📊 Logging & Monitoring
- Detailed logging to file (
mcp_unreal.log) - Console logging with different verbosity levels
- Node connection health monitoring
- Detailed logging to file (
Installation
# Clone repository
git clone https://github.com/your-org/mcp-unreal-server.git
cd mcp-unreal-server
# Install dependencies
pip install -r requirements.txt
Configuration
Network Settings
Configure multicast parameters in RemoteExecutionConfig:
# Default multicast settings (modify in server.py)
config.multicast_group_endpoint = ("239.0.0.1", 6766)
Logging
Modify logging configuration in server.py:
# Adjust log levels
file_handler.setLevel(logging.DEBUG) # File logging
console_handler.setLevel(logging.INFO) # Console logging
Usage
Starting the Server
python -m src.mcp_server_unreal.server
Supported Tools
- Connect to Unreal Instance
{
"host": "239.0.0.1",
"port": 6766
}
- Execute Python Code
{
"node_id": "<unreal-node-id>",
"code": "print('Hello Unreal')",
"unattended": true
}
API Documentation
Resource Format
types.Resource(
uri="unreal://<node_id>",
name=f"Unreal Instance: {node_id}",
description="Unreal Engine instance",
mimeType="application/x-unreal"
)
Execution Modes
| Mode | Description |
|---|---|
| MODE_EXEC_FILE | Execute Python file |
| MODE_EXEC_STATEMENT | Execute Python statement |
| MODE_EVAL_STATEMENT | Evaluate Python expression |
Troubleshooting
Common Issues:
- No nodes discovered: Verify Unreal instances are running with MCP plugin
- Execution timeout: Check firewall settings for multicast traffic
- Connection drops: Monitor
mcp_unreal.logfor node status changes
License
Apache-2.0 License
Comments
New to MCP?
From what the protocol is to installing your first server, these answers cover most first questions.
An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.