mcpforunityserver

What it is and what it does

mcpforunityserver is a Model Context Protocol (MCP) server that acts as a bridge between AI language models and the Unity Editor. It exposes Unity's capabilities as MCP tools and resources, allowing Claude, Cursor, and other AI assistants to read scene state, modify game objects, run scripts, and automate workflows through natural language. The server runs as a standalone Python process and communicates with Unity Editor via WebSocket; it supports both stdio and HTTP transports, making it suitable for local development or remote team deployments.

The package bundles httpx, fastmcp, mcp, pydantic, fastapi, uvicorn, and click to handle protocol translation, HTTP serving, and CLI argument parsing. It requires Python 3.10+ and the uv package manager to run. Most users install it via uvx and configure it in their MCP client (Claude Desktop, Cursor, etc.); advanced deployments can enable remote-hosted mode with API key authentication for shared team servers. No license restrictions apply—MIT terms allow commercial and open-source use.

Use it for:

• Automate repetitive game development tasks (scene setup, prefab instantiation, property tweaking) by describing them in natural language to Claude or Cursor.
• Rapidly prototype game mechanics by having an AI assistant generate and modify C# scripts or scene configurations based on your descriptions.
• Debug and inspect game state interactively—ask an LLM to read scene hierarchies, check component values, or run diagnostics without manual clicking.
• Deploy a shared MCP server for a game dev team, with per-user API key authentication and session isolation in remote-hosted mode.
• Integrate Unity workflows into AI-powered code generation pipelines where the LLM needs to inspect or modify the game project state.

Worth the install?

AI-flagged interpretation of the facts on this page — verify before relying

Runs a Model Context Protocol server that lets AI assistants control Unity Editor through natural language commands, bridging Claude, Cursor, and other LLMs to game development workflows.

Yes. The package is actively maintained, has no known vulnerabilities, installs with low friction, and carries a permissive MIT license. Install it if you want to control Unity Editor through AI assistants—it's the only tool that bridges MCP and Unity. Prerequisite: you must have uv installed and the Unity MCP Plugin set up in your Editor project for it to work.

Install

mcpforunityserver on PyPI

pip install mcpforunityserver

uv add mcpforunityserver

poetry add mcpforunityserver

Installing mcpforunityserver

Before you install

Low friction: pure Python wheel with no compiled dependencies. Active maintenance—released 12 days ago with 13396 repository stars. Requires uv and the Unity MCP Plugin installed in your Unity project to function.

License in practice

MIT license permits unrestricted use, modification, and distribution with minimal obligations—suitable for commercial and open-source projects alike.

Quickstart

# Install via uv (required)
uvx --from mcpforunityserver mcp-for-unity --transport http --http-url http://localhost:8080

# Configure MCP client (e.g., Claude Desktop)
# Add to config.json:
# {
#   "mcpServers": {
#     "UnityMCP": {
#       "url": "http://localhost:8080/mcp"
#     }
#   }
# }

Requires uv package manager installed; Unity MCP Plugin must be installed in your Unity Editor project; server connects to Unity automatically when both are running.

Verify before relying

• Specific Unity Editor versions supported or tested against.
• Performance characteristics when controlling complex scenes or many game objects.
• Latency expectations for LLM-to-Unity command execution over HTTP vs stdio transport.

Package facts

Evidence: mcpforunityserver-10.1.2-py3-none-any.whl

Keywords: mcp, unity, ai, model context protocol, gamedev, unity3d, automation, llm, agent

Tags

More Python Modules packages

Further reading