What are the system requirements?
Node.js 16+ and Unity 2022.3 LTS or newer are required.
@GrandMasterK414
基本情報
Unity MCP Server for integration with Smithery.ai
Reads the contents of a file in the Unity project
Searches for text patterns in project files
Lists project assets of a certain type or in a folder
Gets high-level information about the Unity project
Parses a Unity scene file to extract game objects hierarchy
Parses a Unity prefab file to extract components
Finds scenes containing a specific GameObject or component
Compiles C# code to find compiler errors
Finds references to a C# class or method
Creates a new C# script file from a template
Compiles a shader and reports errors
Inspects a YAML asset file
Runs Unity's automated tests in batch mode
Experimental - runs a scene in play mode for a short duration
A Model Context Protocol (MCP) server that bridges AI assistants (e.g., Cursor AI, Claude) with Unity projects. It runs in batch mode and provides tools for reading files, parsing scenes/prefabs, analyzing C# code, running tests, and more.
Install Node.js 16+ and Unity 2022.3 LTS+, clone the repository, run npm install && npm build, then configure config/default.json with your Unity and project paths. Start with npm start or for Smithery mode npm run smithery:start. It can also be run in a Docker container.
Node.js 16+ and Unity 2022.3 LTS or newer are required.
Edit `config/default.json` and set the `unityPath` and `projectPath` fields under the `unity` section.
Run `npm start` from the project directory, or `npm run smithery:start` for Smithery integration.
Yes, a Dockerfile is included. Build with `docker build -t unity-mcp-server .` and mount your project as a volume.
The server provides 14 tools including `open_file`, `search_files`, `parse_scene`, `analyze_cs_code`, `run_tests`, `generate_script`, `validate_shader`, and more.

Handl speaks the Model Context Protocol. Your whole billing operation — projects, invoices, clients, reports, approvals — as tools any AI assistant can call, inside your autonomy rules.
A search tool helps dev to solve the naming things problem.
A curated list of references for MLOps

Health by Dr Brad works out a health plan from your own results: which screening is due at your age, and evidence-based suggestions, each with the reason and the published guideline or study behind it. Your record is one

A good sequence diagram can solve almost any communication problem in engineering. Volley lets your agent write them as plain text, with the real request and response payloads on every arrow. It checks its own syntax wi
コメント