GC

gdamitha/chimerax-alphafold-mcp

Developer tools

このページは AI により自動翻訳されています。技術的な詳細は原文をご確認ください。 原文を見る

7 stars 6 forks 品質 63 トレンド 15MIT

ChimeraX-AlphaFold-MCP connects ChimeraX and its AlphaFold Tool to Claude AI through the Model Context Protocol (MCP), enabling Claude to directly interact with and control PyMOL.

概要

ChimeraX-AlphaFold-MCP connects ChimeraX and its AlphaFold Tool to Claude AI through the Model Context Protocol (MCP), enabling Claude to directly interact with and control PyMOL. This powerful integration allows for conversational structural biology, molecular visualization, and structure prediction and analysis capabilities through natural language. - : Connect Claude AI to ChimeraX through a REST API. - : Natural language processing for Chimera and AlphaFold commands - : Manipulate representations, colors, and views - : Perform measurements, alignments, and other analyses - : Run arbitrary Python code in ChimeraX from Claude - : Directly run AlphaFold & ESMFold Commands by typing your workflow. - ChimeraX installed on your system (Any Version After March 18th 2024) - Claude for Desktop - Python 3.10 or newer - Git For other platforms, visit the UV installation guide. Create and activate a Python virtual environment: 1. Open Claude Desktop 2.

README

以下は原文 README の抜粋です。原文を見る。

ChimeraX-AlphaFold-MCP: Integrating ChimeraX and AlphaFold with Claude AI

ChimeraX-AlphaFold-MCP connects ChimeraX and its AlphaFold Tool to Claude AI through the Model Context Protocol (MCP), enabling Claude to directly interact with and control PyMOL. This powerful integration allows for conversational structural biology, molecular visualization, and structure prediction and analysis capabilities through natural language.

Uploading 0402.mp4.zip…

Features

  • Two-way communication: Connect Claude AI to ChimeraX through a REST API.
  • Intelligent command parsing: Natural language processing for Chimera and AlphaFold commands
  • Molecular visualization control: Manipulate representations, colors, and views
  • Structural analysis: Perform measurements, alignments, and other analyses
  • Code execution: Run arbitrary Python code in ChimeraX from Claude
  • Protein Structure Prediction: Directly run AlphaFold & ESMFold Commands by typing your workflow.

Installation Guide

Prerequisites

  • ChimeraX installed on your system (Any Version After March 18th 2024)
  • Claude for Desktop
  • Python 3.10 or newer
  • 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/GDAmitha/chimerax-alphafold-mcp.git
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

With the virtual environment activated:

pip install mcp

Step 5: Configure Claude Desktop

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

For example:

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

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

Step 6: Start listening on ChimeraX

  1. Open ChimeraX
  2. Type “remotecontrol rest start” into the command line.

Usage

Starting the Connection

In Claude Desktop:

  • You should see a hammer icon in the tools section when chatting
  • Click it to access the ChimeraX & AlphaFold tools
GitHub で README 全文を見る

インストール

This server does not publish a one-line install command.

Open the repository installation guide MCP 初心者?mcpskill.org のガイドから始めましょう →

設定

{ "mcpServers": { "pymol": { "command": "[Full path to your venv python]", "args": ["[Full path to pymol_mcp_server.py]"] } } }