3D Slicer

🚀 MCP-Slicer - 3D Slicer Model Context Protocol Integration

MCP-Slicer connects 3D Slicer with model clients (such as Claude Desktop or Cline) through the Model Context Protocol (MCP), enabling direct interaction and control of 3D Slicer. This integration makes it possible to perform medical image processing, scene creation, and manipulation using natural language.

English Version | Traditional Chinese Version

✨ Features

1. list_nodes: List and filter MRML nodes and their attributes in 3D Slicer.
2. execute_python_code: Execute Python code in the 3D Slicer environment.

📦 Installation

Prerequisites

• 3D Slicer 5.8 or higher.
• Python 3.13 or higher.
• uv package manager.

If you are using a Mac, install uv with the following command:

brew install uv

For Windows users, run the following PowerShell command:

irm https://astral.sh/uv/install.ps1 | iex

Then execute:

set Path=C:\Users\nntra\.local\bin;%Path%

Otherwise, refer to the installation instructions on its official website: Install uv

⚠️ Important Note

Please install UV first.

Claude Desktop Integration

Go to Claude > Settings > Developer > Edit Configuration > claude_desktop_config.json and add the following content:

{
  "mcpServers": {
    "slicer": {
      "command": "uvx",
      "args": ["mcp-slicer"]
    }
  }
}

Cline Integration

{
  "mcpServers": {
    "slicer": {
      "command": "uvx",
      "args": ["mcp-slicer"]
    }
  }
}

🚀 Quick Start

Check Claude Settings

Please ensure that the corresponding slicer tool is added in the Claude Desktop application.

Start the Slicer Web Server

1. Open the Slicer Web Server module.
2. Make sure the desired interface is selected.
3. Then start the server.

💻 Usage Examples

Basic Usage

- list_nodes

What Markups nodes are there in the current Slicer scene? Please list their attributes.

- execute_python_code

Please run the following Python code to calculate the volume of a 3D model:

import numpy as np
from stl import mesh

# Load the STL file
model = mesh.Mesh.from_file("model.stl")
points = model.vectors.reshape(-1, 3)

# Calculate the volume
volume = np.abs(np.dot(points[0], np.cross(points[1], points[2]))) / 6.0
print(f"模型的体积为: {volume}")

📄 License

This project is a third - party integration project and is not developed by the 3D Slicer team.

Translation Notes

• The document structure remains consistent with the English version.
• Technical terms and command - line codes are translated accurately.
• Image descriptions and links are retained to ensure readers can correctly understand the illustrated content.
• JSON configuration examples are in the correct format and conform to Chinese reading habits.
• The overall language is fluent and natural while retaining the professionalism and formal tone of the original text.

If you need further assistance or information, please refer to the original English document.