unity-mcp and Unity-AI-Tools-Template
The first is a fully-featured MCP server implementation for Unity that enables AI assistants to interact with the editor, while the second is a template project for developers to build custom MCP tools within Unity—making them ecosystem siblings where one provides the production bridge and the other enables extensibility.
About unity-mcp
CoplayDev/unity-mcp
Unity MCP acts as a bridge, allowing AI assistants (like Claude, Cursor) to interact directly with your Unity Editor via a local MCP (Model Context Protocol) Client. Give your LLM tools to manage assets, control scenes, edit scripts, and automate tasks within Unity.
Implements a comprehensive Python-based MCP server using HTTP transport that operates locally within the Unity Editor, exposing 40+ tools across physics, animation, graphics, builds, and scene management alongside introspection resources like `unity_reflect` for live API inspection. The architecture supports multi-instance routing, async long-running operations with polling, batch execution for performance optimization, and integrates with popular LLM clients (Claude, Cursor, VS Code Copilot, Windsurf) through configurable connection protocols. Available as a Git-based package in the Unity Package Manager, Asset Store, and OpenUPM with Python 3.10+ and the `uv` package manager as runtime dependencies.
About Unity-AI-Tools-Template
IvanMurzak/Unity-AI-Tools-Template
Unity MCP Tool template project
Provides scaffolding to build custom MCP (Model Context Protocol) tools for the Unity-MCP framework, supporting both Editor and Runtime tools with separate code paths and attribute-based registration. Includes automated package initialization, version management, and CI/CD workflows for distributing tools via OpenUPM or GitHub registries. Tools interact with Unity through main-thread execution guards, enabling AI agents to manipulate scenes and access Editor APIs.
Related comparisons
Scores updated daily from GitHub, PyPI, and npm data. How scores work