What are the prerequisites?
PyMOL, Claude for Desktop, Python 3.10 or newer, Git, and the UV package manager (for environment setup).
@vrtejus
Basic information
No overview available yet
Add this server to your MCP-compatible client using the configuration below.
{
"mcpServers": {
"rosetta-symmetry": {
"command": "/Users/ammachi/Developer/GitHub/MCP/mcp-rosetta/venv/bin/python",
"args": [
"/Users/ammachi/Developer/GitHub/MCP/mcp-rosetta/pymol_mcp_server.py"
]
}
}
}Tool list not available yet
This listing does not currently have a tool list to display. This does not mean the server has no tools; check its documentation for supported capabilities.
We auto-extract tools from the README. The maintainer can list them under a ## Tools heading to populate this section.
PyMOL-MCP connects PyMOL to Claude AI through the Model Context Protocol (MCP), enabling Claude to directly interact with and control PyMOL. This integration allows for conversational structural biology, molecular visualization, and analysis through natural language.
Clone the repository, create a Python 3.10+ virtual environment, install the mcp package, add the server configuration to Claude Desktop’s claude_desktop_config.json, and install the included PyMOL socket plugin via PyMOL’s Plugin Manager. Start the plugin’s “Listening” mode in PyMOL, then use Claude Desktop; a hammer icon in the tools section gives access to PyMOL commands.
PyMOL, Claude for Desktop, Python 3.10 or newer, Git, and the UV package manager (for environment setup).
A socket-based server runs inside PyMOL via the included plugin, listening on port 9876. Claude talks to that server through MCP, requiring both applications to be running on the same machine.
You can load structures, change representations and colors, run alignments, measure distances, execute arbitrary Python code in PyMOL, and save views as images.
Ensure the PyMOL plugin is listening before attempting a connection from Claude. Restart PyMOL to refresh the plugin list, and verify the Python path and script paths in `claude_desktop_config.json` are correct.
It uses a local TCP socket on port 127.0.0.1:9876. There is no authentication; the connection is local and requires PyMOL and Claude to be on the same machine.
A curated list of references for MLOps

Handl speaks the Model Context Protocol. Your whole billing operation — projects, invoices, clients, reports, approvals — as tools any AI assistant can call, inside your autonomy rules.
AI Agents & MCPs & AI Workflow Automation • (~400 MCP servers for AI agents) • AI Automation / AI Agent with MCPs • AI Workflows & AI Agents • MCPs for AI Agents

Model Context Protocol Servers

Yuppsy MCP: build and publish real estate websites from your AI assistant. Yuppsy lets your AI assistant create live websites for real estate agents and individual property listings. You don't need a designer or any code
Comments