Pymol MCP

🚀 PyMOL-MCP: Integrating PyMOL with Claude AI

PyMOL-MCP connects PyMOL to Claude AI via the Model Context Protocol (MCP), enabling Claude to directly control and operate PyMOL. This powerful integration makes it possible to conduct structural biology, molecular visualization, and analysis through natural language.

https://github.com/user-attachments/assets/687f43dc-d45e-477e-ac2b-7438e175cb36

✨ Features

• Bidirectional Communication: Connects Claude AI to PyMOL through a socket-based server.
• Intelligent Command Parsing: Utilizes natural language processing for PyMOL commands.
• Molecular Visualization Control: Manipulate representations, colors, and views.
• Structural Analysis: Perform measurements, alignments, and other analyses.
• Code Execution: Run arbitrary Python code in PyMOL from Claude.

📦 Installation

Prerequisites

• PyMOL installed on the system.
• Claude for Desktop.
• Python 3.10 or higher.
• Git.

Step 1: Install the UV Package Manager

On macOS:

brew install uv

On Windows:

powershell -c "irm https://astral.sh/uv/install.ps1 | iex"
set Path=C:\Users\[YourUsername]\.local\bin;%Path%

For other platforms, visit the UV Installation Guide.

Step 2: Clone the Repository

git clone https://github.com/vrtejus/pymol-mcp
cd pymol-mcp

Step 3: Set Up the Environment

Create and activate a Python virtual environment:

python -m venv venv

On macOS/Linux:

source venv/bin/activate

On Windows:

venv\Scripts\activate

Step 4: Install Dependencies

After activating the virtual environment:

pip install mcp

Step 5: Configure Claude Desktop

1. Open Claude Desktop.
2. Go to Claude > Settings > Developer > Edit Configuration.
3. This will open the claude_desktop_config.json file.
4. Add the MCP server configuration:

{
  "mcpServers": {
    "pymol": {
      "command": "[The actual full path on your system]",
      "args": ["[The actual full path of PyMOL_MCP_Server.py]"]
    }
  }
}

For example:

{
  "mcpServers": {
    "pymol": {
      "command": "/Users/username/pymol-mcp/venv/bin/python",
      "args": ["/Users/username/pymol-mcp/pymol_mcp_server.py"]
    }
  }
}

⚠️ Important Note

Use the actual full path on your system. On Windows, use forward slashes (/) instead of backslashes.

Step 6: Install the PyMOL Plugin

1. Open PyMOL.
2. Go to Plug-in → Plug-in Manager.
3. Click the “Install New Plugin” tab.
4. Select “Choose file...”, then navigate to the cloned repository.
5. Select the pymol-mcp-socket-plugin/__init__.py file.
6. Click “Open” to install the plugin.

💻 Usage Examples

Load the Plugin When Starting PyMOL

To automatically load the plugin when PyMOL starts, add the following line to the ~/.pymolrc file:

load_plugin /path/to/pymol-mcp-socket-plugin/pymol_mcp_plugin.so

🤝 Contributing

Contributions are welcome! Please feel free to submit a Pull Request.

📄 License

This project is licensed under the MIT License. See the LICENSE file for details.