C

Cerebro

CereBro.Unity is a model-agnostic AI agent wrapper based on CereBro, supporting the Model Context Protocol (MCP), allowing developers to write tools that can be used across AI models.
2.5 points
44
Installation
Copy the following command to your Client for configuration
Note: Your key is sensitive information, do not share it with anyone.

🚀 CereBro.Unity

CereBro.Unity is a model-agnostic AI agent wrapper based on CereBro for Unity, supporting the use of different AI models through the Model Context Protocol. Now you can write tools using the official C# SDK (https://github.com/modelcontextprotocol/csharp-sdk) without changing the code.

🚀 Quick Start

✨ Features

CereBro.Unity is a model-agnostic AI agent wrapper for Unity. It is based on CereBro and supports using different AI models via the Model Context Protocol. You can use the official C# SDK to write tools without code changes.

📦 Installation

Git URL

You can install CereBro.Unity from Unity's Package Manager via a Git URL. Please visit https://docs.unity3d.com/Manual/upm-ui-giturl.html for installation.

In your Unity project, use the following Git URL to install:

https://github.com/rob1997/CereBro.git?path=/Packages/com.cerebro.unity

Open UPM

Open UPM support is not currently available.

💻 Usage Examples

MCP Server

Step 1: Import the Server

Select CereBro > Import Server from the menu bar. This will import CereBro.Server.Unity into the root directory of your Unity project. It acts as an intermediary MCP server, responsible for relaying data between Unity and the AI model.

Step 2: Configure the Client

You need to configure the specific chat client to use CereBro.Server.Unity. You can add the following content to the client's configuration file:

"servers": {
      "cerebro-server-unity": {
        "type": "stdio",
        "command": "dotnet",
        "args": [
          "<Path to Unity Project>/CereBro.Server.Unity/CereBro.Server.Unity.dll",
          "--port",
          "<Port Number>"
        ]
      }
    }

If you are using the CereBro client, you can add the following content to the servers.json file:

[
  {
    "Id": "unity-server",
    "Name": "CereBro.Server.Unity",
    "TransportType": "stdio",
    "TransportOptions": {
      "command": "dotnet \"<Path To Unity Project>/CereBro.Server.Unity/CereBro.Server.Unity.dll\"",
      "arguments": "--port <Port Number>"
    }
  }
]

Step 3: Run CereBro in Unity

Next, you need to run CereBro in Unity. This will create a listener to listen for requests from CereBro.Server.Unity.

Editor Mode:

[InitializeOnLoad]
public static class CereBroEditorRunner
{
    static CereBroEditorRunner()
    {
        CereBroListener.RunForEditor(5050);
    }
}

Runtime Mode: At runtime, you need to call the CereBroListener.Run(int port = 5000, CancellationToken cancellationToken = default) method, which will return an Awaitable Task.

Now you can start the client and use CereBro in Unity.

MCP Client

MCP client support is not currently available.

Basic Usage

The following are some basic usage examples provided by the CereBro.Unity sample project:

You can import the sample project of CereBro.Unity in the Package Manager. It includes editor tools that can be directly called from the MCP client:

  • CreateShapeTool: Create a primitive shape (e.g., cube, sphere, cylinder, etc.) in the current scene.
  • GetCurrentPositionTool: Get the current position of a GameObject in the current scene.
  • MoveGameObjectTool: Move a GameObject by a specified offset in the x, y, and z directions.
  • RePositionTool: Move a GameObject to a specified position.
  • RotateGameObjectTool: Rotate a GameObject around the x, y, and z axes by a specified angle.

🤝 Contributing

If you wish to contribute to this project, you can fork the repository and create a pull request. You can also create an issue if you find any problems or have any feature requests.

Featured MCP Services
G
Gitlab MCP Server
Certified
The GitLab MCP server is a project based on the Model Context Protocol that provides a comprehensive toolset for interacting with GitLab accounts, including code review, merge request management, CI/CD configuration, and other functions.
TypeScript
121
4.3 points
N
Notion Api MCP
Certified
A Python-based MCP Server that provides advanced to-do list management and content organization functions through the Notion API, enabling seamless integration between AI models and Notion.
Python
172
4.5 points
D
Duckduckgo MCP Server
Certified
The DuckDuckGo Search MCP Server provides web search and content scraping services for LLMs such as Claude.
Python
860
4.3 points
M
Markdownify MCP
Markdownify is a multi-functional file conversion service that supports converting multiple formats such as PDFs, images, audio, and web page content into Markdown format.
TypeScript
1.8K
5 points
F
Figma Context MCP
Framelink Figma MCP Server is a server that provides access to Figma design data for AI programming tools (such as Cursor). By simplifying the Figma API response, it helps AI more accurately achieve one - click conversion from design to code.
TypeScript
6.7K
4.5 points
U
Unity
Certified
UnityMCP is a Unity editor plugin that implements the Model Context Protocol (MCP), providing seamless integration between Unity and AI assistants, including real - time state monitoring, remote command execution, and log functions.
C#
593
5 points
M
Minimax MCP Server
The MiniMax Model Context Protocol (MCP) is an official server that supports interaction with powerful text-to-speech, video/image generation APIs, and is suitable for various client tools such as Claude Desktop and Cursor.
Python
778
4.8 points
G
Gmail MCP Server
A Gmail automatic authentication MCP server designed for Claude Desktop, supporting Gmail management through natural language interaction, including complete functions such as sending emails, label management, and batch operations.
TypeScript
310
4.5 points
AIbase
Zhiqi Future, Your AI Solution Think Tank
© 2025AIbase