Bonsai-mcp는 Bonsai를 통해 IFC (Industry Foundation Classes) 모델 전용 지원으로 오리지널 기능을 확장하는 BlenderMCP의 포크입니다. 이 통합은 LLM을 읽고 IFC 파일을 수정할 수있는 플랫폼입니다.

특징

• IFC 별 기능: Query IFC 모델, 공간 구조 분석, 건물 요소 검사 및 수량 추출

• Eleven IFC 도구 포함: Inspect 프로젝트 정보, 목록 entities, 검사 속성, 공간 구조를 탐구, 관계를 분석하고 더

• Sequential Thinking: 구조화된 문제 해결을 위한 modelcontextprotocol/servers의 순차적인 사고 도구를 포함합니다

• ** Original BlenderMCP 구현에서 심각한 코드 도구 **: 개체를 만들고 수정하고 재료를 적용하고, Blender에서 Python 코드를 실행

부품

체계는 2개의 주요 성분으로 이루어져 있습니다:

1. Blender Addon (addon.py): Blender에서 소켓 서버를 생성하는 Blender addon은 IFC-specific 작업을 포함한 명령을 수신하고 실행합니다.

2. MCP 서버 ([T1]]): Model Context Protocol을 구현하고 Blender addon에 연결합니다.

설치 - MCP 클라이언트 설정을 통해

Bonsai-mcp - Model Context Protocol Integration for IFC through IfcOpenShell and Blender

Bonsai-mcp is a fork of BlenderMCP that extends the original functionality with dedicated support for IFC (Industry Foundation Classes) models through Bonsai. This integration is a platform to let LLMs read and modify IFC files.

Features

• IFC-specific functionality: Query IFC models, analyze spatial structures, examine building elements and extract quantities

• Eleven IFC tools included: Inspect project info, list entities, examine properties, explore spatial structure, analyze relationships and more

• Sequential Thinking: Includes the sequential thinking tool from modelcontextprotocol/servers for structured problem solving

• Execute Code tool from the original BlenderMCP implementation: Create and modify objects, apply materials, and execute Python code in Blender

Components

The system consists of two main components:

1. Blender Addon (addon.py): A Blender addon that creates a socket server within Blender to receive and execute commands, including IFC-specific operations

2. MCP Server (tools.py): A Python server that implements the Model Context Protocol and connects to the Blender addon

Installation - Through MCP Client Settings

Prerequisites

• Blender 4.0 or newer

• Python 3.12 or newer

• uv package manager

• Bonsai BIM addon for Blender (for IFC functionality)

Installing uv:

Mac:

brew  install  uv

Windows:

powershell  -c  "irm https://astral.sh/uv/install.ps1 | iex"

set  Path=C:\Users\[username]\.local\bin;%Path%

For other platforms, see the uv installation guide.

Clone the repository

git  clone  https://github.com/JotaDeRodriguez/Bonsai_mcp

Claude for Desktop Integration

Edit your claude_desktop_config.json file (Claude > Settings > Developer > Edit Config) to include:

{
    "mcpServers": {
        "Bonsai-mcp": {
            "command": "uv",
            "args": [
              "--directory",
              "\\your\\path\\to\\Bonsai_mcp",
              "run",
              "tools.py"
          ]
        }
    }
}

Installation via Docker

The repository comes with a Dockerfile that makes deployment simple and consistent across different environments.

Quick Start

# Clone the repository
git clone https://github.com/JotaDeRodriguez/Bonsai_mcp
cd Bonsai_mcp

# Build the Docker image
docker build -t bonsai_mcp .

# Run the container
docker run -p 8000:8000 --name bonsai_mcp bonsai_mcp

Once running, the container will expose the MCP tools as REST/OpenAPI APIs at http://localhost:8000.

• To verify youtr installation, open your browser and navigate to
• http://localhost:8000/docs