unity-mcp-sharp
Verified Safeby Abbabon
Overview
Integrate AI assistants with Unity Editor for automation, allowing LLMs to manipulate scenes, assets, and runtime via MCP.
Installation
docker run -d --name unity-mcp-server -p 8080:8080 --restart unless-stopped ghcr.io/abbabon/unity-mcp-server:latestEnvironment Variables
- MCP_STDIO_MODE
Security Notes
The server leverages standard .NET 9.0 and ASP.NET Core with Docker containerization, which are generally robust. No obvious malicious patterns, obfuscation, or hardcoded sensitive secrets were found in the provided code snippets. Communication uses WebSocket (ws://localhost:8080/ws) and HTTP (http://localhost:8080/mcp), which for localhost operation is typically fine but would require WSS/HTTPS for production internet-facing deployments. The core function involves allowing AI assistants to execute powerful actions within the Unity Editor, including `unity_run_menu_item` which can trigger arbitrary Unity menu commands. While this is a designed feature for automation, it implies a high level of trust in the AI's instructions and the environment it operates in. Misaligned or compromised AI could lead to unintended modifications to the Unity project. This is a risk inherent to the tool's purpose, not a flaw in its implementation.
Similar Servers
unity-mcp
MCP for Unity acts as a bridge, allowing AI assistants to interact directly with the Unity Editor to manage assets, control scenes, edit scripts, and automate tasks.
cocos-mcp-server
Enables AI assistants to interact with the Cocos Creator editor through a Model Context Protocol (MCP) server, providing control over scene, node, component, asset, and project operations.
ncp
A unified Model Context Protocol (MCP) orchestrator that enables semantic tool discovery, management, scheduling, and execution across a diverse ecosystem of connected AI tools and services.
Unreal_mcp
Enables AI assistants to control and automate Unreal Engine via its Remote Control API for game development tasks.