Unity-MCP and godot-mcp
About Unity-MCP
IvanMurzak/Unity-MCP
AI-powered bridge connecting LLMs and advanced AI agents to the Unity Editor via the Model Context Protocol (MCP). Chat with AI to generate code, debug errors, and automate game development tasks directly within your project.
Implements MCP server architecture running both in the Unity Editor and compiled runtime, supporting stdio-based local execution and HTTP-based remote deployment without vendor lock-in. Generates dynamic "skills" metadata reflecting project state (Unity version, OS, installed plugins) to enhance LLM context, and provides extensible MCP Tools for editor automation alongside in-game runtime capabilities for NPC behavior and live debugging. Compatible across multiple AI clients (Claude, Cursor, GitHub Copilot, VS Code, Rider) and deployable via npm CLI, Docker, or direct UPM package integration.
About godot-mcp
tugcantopaloglu/godot-mcp
MCP server for full Godot 4.x engine control — 149 tools for AI-driven game development
Implements a TCP-based runtime interaction server alongside a TypeScript MCP server, enabling both headless scene parsing (via GDScript operations) and live game manipulation through arbitrary code execution, property inspection, and signal management. Covers 149 tools spanning physics, networking, audio, animation trees, UI theming, shader parameters, skeletal animation, procedural geometry, and export automation—essentially exposing Godot's entire API surface to AI assistants. Designed for AI-driven game development workflows where LLMs can prototype, test, debug, and iterate games through a single MCP interface.
Related comparisons
Scores updated daily from GitHub, PyPI, and npm data. How scores work