PyMOL MCP server

Enables direct interaction with PyMOL molecular visualization software for executing commands, manipulating structures, and analyzing molecular data through a socket connection that translates natural language to PyMOL-compatible Python code.
Back to servers
Setup instructions
Provider
Edoardo Cilia
Release date
Mar 18, 2025
Language
Python
Stats
20 stars

PyMOL-MCP creates a powerful connection between PyMOL and Claude AI through the Model Context Protocol (MCP). This integration enables conversational control of PyMOL, allowing you to manipulate molecular structures, perform analyses, and visualize molecules using natural language instructions through Claude.

Installation Requirements

Before getting started, ensure you have:

  • PyMOL installed on your system
  • Claude for Desktop
  • Python 3.10 or newer
  • Git

Installation Process

Setting Up the Environment

First, install the UV package manager:

macOS:

brew install uv

Windows:

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

For other platforms, check the UV installation guide.

Next, clone the repository and set up a Python virtual environment:

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

# Create virtual environment
python -m venv venv

# Activate it (macOS/Linux)
source venv/bin/activate

# Activate it (Windows)
venv\Scripts\activate

# Install dependencies
pip install mcp

Configuring Claude Desktop

  1. Open Claude Desktop
  2. Navigate to Claude > Settings > Developer > Edit Config
  3. Add the MCP server configuration to the claude_desktop_config.json file:
{
  "mcpServers": {
    "pymol": {
      "command": "[Full path to your venv python]",
      "args": ["[Full path to pymol_mcp_server.py]"]
    }
  }
}

Example configuration:

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

Note: Use actual full paths on your system. On Windows, use forward slashes (/) in the paths.

Installing the PyMOL Plugin

  1. Open PyMOL
  2. Go to Plugin → Plugin Manager
  3. Select the "Install New Plugin" tab
  4. Click "Choose file..." and navigate to the cloned repository
  5. Select the pymol-mcp-socket-plugin/__init__.py file
  6. Click "Open" and follow the installation prompts

Using PyMOL-MCP

Establishing the Connection

  1. In PyMOL:

    • Navigate to Plugin → PyMOL MCP Socket Plugin
    • Click "Start Listening"
    • Verify the status changes to "Listening on port 9876"
  2. In Claude Desktop:

    • Look for the hammer icon in the tools section while chatting
    • Click it to access the PyMOL tools

Example Commands

You can ask Claude to perform various operations in PyMOL using natural language:

  • "Load PDB 1UBQ and display it as cartoon"
  • "Color the protein by secondary structure"
  • "Highlight the active site residues with sticks representation"
  • "Align two structures and show their differences"
  • "Calculate the distance between these two residues"
  • "Save this view as a high-resolution image"

Troubleshooting

If you encounter issues:

  • Connection problems: Ensure the PyMOL plugin is listening before attempting to connect from Claude
  • Command errors: Check the PyMOL output window for error messages
  • Missing plugin: Restart PyMOL and verify the plugin installation
  • Claude connection failure: Double-check the paths in your Claude configuration file

For additional support, join the Bio-MCP Community on Slack: https://join.slack.com/t/bio-mcpslack/shared_invite/zt-31z4pho39-K5tb6sZ1hUvrFyoPmKihAA

How to install this MCP server

For Claude Code

To add this MCP server to Claude Code, run this command in your terminal:

claude mcp add-json "pymol" '{"command":"${python}","args":["${workspaceRoot}/pymol_mcp_server.py"]}'

See the official Claude Code MCP documentation for more details.

For Cursor

There are two ways to add an MCP server to Cursor. The most common way is to add the server globally in the ~/.cursor/mcp.json file so that it is available in all of your projects.

If you only need the server in a single project, you can add it to the project instead by creating or adding it to the .cursor/mcp.json file.

Adding an MCP server to Cursor globally

To add a global MCP server go to Cursor Settings > Tools & Integrations and click "New MCP Server".

When you click that button the ~/.cursor/mcp.json file will be opened and you can add your server like this:

{
    "mcpServers": {
        "pymol": {
            "command": "${python}",
            "args": [
                "${workspaceRoot}/pymol_mcp_server.py"
            ]
        }
    }
}

Adding an MCP server to a project

To add an MCP server to a project you can create a new .cursor/mcp.json file or add it to the existing one. This will look exactly the same as the global MCP server example above.

How to use the MCP server

Once the server is installed, you might need to head back to Settings > MCP and click the refresh button.

The Cursor agent will then be able to see the available tools the added MCP server has available and will call them when it needs to.

You can also explicitly ask the agent to use the tool by mentioning the tool name and describing what the function does.

For Claude Desktop

To add this MCP server to Claude Desktop:

1. Find your configuration file:

  • macOS: ~/Library/Application Support/Claude/claude_desktop_config.json
  • Windows: %APPDATA%\Claude\claude_desktop_config.json
  • Linux: ~/.config/Claude/claude_desktop_config.json

2. Add this to your configuration file:

{
    "mcpServers": {
        "pymol": {
            "command": "${python}",
            "args": [
                "${workspaceRoot}/pymol_mcp_server.py"
            ]
        }
    }
}

3. Restart Claude Desktop for the changes to take effect

Want to 10x your AI skills?

Get a free account and learn to code + market your apps using AI (with or without vibes!).

Nah, maybe later