Molecule Visualization (ChimeraX, PyMOL) MCP server

Molecule-MCP is a specialized server that connects molecular science tools to Claude AI through the Model Context Protocol (MCP). This integration allows Claude to directly interact with and control molecular modeling tools, effectively serving as a co-scientist for prompt-assisted molecule modeling tasks.

Prerequisites

• Claude Desktop must be installed and running on your system

Installation

Step 1: Install Required Python Packages

pip install "mcp[cli]" chatmol
pip install git+https://github.com/ChatMol/gromacs_copilot.git  # optional, for gromacs_copilot
which mcp  # note the path to the mcp executable

Step 2: Clone the Repository

git clone https://github.com/ChatMol/molecule-mcp.git
cd molecule-mcp
pwd  # note this directory path

Step 3: Configure Claude Desktop

1. Open Claude Desktop
2. Navigate to Settings > Developer > Edit Config > claude_desktop_config.json
3. Add the following configuration, replacing the paths with your actual paths:

{
  "mcpServers": {
    "pymol": {
      "command": "/path/to/mcp",
      "args": [
        "run",
        "/path/to/molecule-mcp/pymol_server.py"
      ]
    },
    "chimerax": {
      "command": "/path/to/mcp",
      "args": [
        "run",
        "/path/to/molecule-mcp/ChimeraX_server.py"
      ]
    },
    "gromacs_copilot": {
      "command": "/path/to/mcp",
      "args": [
        "run",
        "/path/to/molecule-mcp/mcp_server.py"
      ]
    }
  }
}

Make sure to replace:

• /path/to/mcp with the actual path to your mcp executable (from the which mcp command)
• /path/to/molecule-mcp with the actual path to the molecule-mcp directory (from the pwd command)

Usage

After installation, you can use the Molecule-MCP servers with Claude Desktop. Here's how to work with each available integration:

PyMOL Integration

When using Claude Desktop, you can instruct Claude to interact with PyMOL for molecular visualization and analysis. For example:

@pymol Please load the PDB structure 1ABC and display it as a cartoon representation

ChimeraX Integration

You can use Claude to control ChimeraX for advanced molecular visualization:

@chimerax Please open the PDB file 2XYZ and color the structure by hydrophobicity

GROMACS Copilot

If you installed the optional GROMACS copilot package, you can use it for molecular dynamics simulations:

@gromacs_copilot Please set up a simulation of my protein in water and run it for 10 nanoseconds

Each of these commands triggers Claude to communicate with the respective molecular modeling tool through the Molecule-MCP server, allowing it to execute the requested operations and return results.

How to add this MCP server to 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 > MCP and click "Add new global MCP server".

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

{
    "mcpServers": {
        "cursor-rules-mcp": {
            "command": "npx",
            "args": [
                "-y",
                "cursor-rules-mcp"
            ]
        }
    }
}

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 explictly ask the agent to use the tool by mentioning the tool name and describing what the function does.