Rosetta MCP
Enables protein modeling and design using the Rosetta suite via Docker, including structure refinement, mutation stability analysis, docking, and loop modeling through natural language commands.
README
Rosetta MCP
Protein modeling and design using the Rosetta suite via Docker
An MCP (Model Context Protocol) server for molecular modeling with 7 core tools:
- Protein structure refinement using Relax protocol
- Mutation stability analysis (ΔΔG calculations)
- Submit protein-protein docking jobs with async tracking
- Submit loop modeling jobs
- Submit protein-ligand docking jobs
- Monitor and retrieve job results
- List available example structures
Quick Start with Docker
Approach 1: Pull Pre-built Image from GitHub
The fastest way to get started. A pre-built Docker image is automatically published to GitHub Container Registry on every release.
# Pull the latest image
docker pull ghcr.io/macromnex/rosetta_mcp:latest
# Register with Claude Code (runs as current user to avoid permission issues)
claude mcp add rosetta -- docker run -i --rm --user `id -u`:`id -g` -v `pwd`:`pwd` ghcr.io/macromnex/rosetta_mcp:latest
Note: Run from your project directory. `pwd` expands to the current working directory.
Requirements:
- Docker
- Claude Code installed
That's it! The Rosetta MCP server is now available in Claude Code.
Approach 2: Build Docker Image Locally
Build the image yourself and install it into Claude Code. Useful for customization or offline environments.
# Clone the repository
git clone https://github.com/MacromNex/rosetta_mcp.git
cd rosetta_mcp
# Build the Docker image
docker build -t rosetta_mcp:latest .
# Register with Claude Code (runs as current user to avoid permission issues)
claude mcp add rosetta -- docker run -i --rm --user `id -u`:`id -g` -v `pwd`:`pwd` rosetta_mcp:latest
Note: Run from your project directory. `pwd` expands to the current working directory.
Requirements:
- Docker
- Claude Code installed
- Git (to clone the repository)
About the Docker Flags:
-i— Interactive mode for Claude Code--rm— Automatically remove container after exit--user `id -u`:`id -g`— Runs the container as your current user, so output files are owned by you (not root)-v— Mounts your project directory so the container can access your data
Verify Installation
After adding the MCP server, you can verify it's working:
# List registered MCP servers
claude mcp list
# You should see 'rosetta' in the output
In Claude Code, you can now use all 7 Rosetta tools:
refine_protein_structurecalculate_ddgsubmit_protein_dockingsubmit_loop_modelingsubmit_ligand_dockingget_job_statusget_job_result
Next Steps
- Detailed documentation: See detail.md for comprehensive guides on:
- Available MCP tools and parameters
- Local Python environment setup (alternative to Docker)
- Example workflows and use cases
- PyRosetta license information
- Troubleshooting
Usage Examples
Once registered, you can use the Rosetta tools directly in Claude Code. Here are some common workflows:
Example 1: Protein Structure Refinement
I have a protein structure at /path/to/protein.pdb. Can you use refine_protein_structure to refine it with 5 trajectories and 100 cycles, saving results to /path/to/results/?
Example 2: Mutation Stability Analysis
I want to analyze how mutations A10G, A10L, and A10F affect the stability of /path/to/protein.pdb. Can you use calculate_ddg with 5 trajectories and report which mutations are stabilizing vs destabilizing?
Example 3: Protein-Protein Docking
I have a protein complex at /path/to/complex.pdb with chain break at residue 150. Can you submit a docking job using submit_protein_docking with 20 trajectories, save results to /path/to/docking/, and monitor progress until completion?
Troubleshooting
Docker not found?
docker --version # Install Docker if missing
Claude Code not found?
# Install Claude Code
npm install -g @anthropic-ai/claude-code
PyRosetta not available?
- All tools work in demo mode without PyRosetta
- For full functionality, a PyRosetta academic or commercial license is required
- See detail.md for PyRosetta installation instructions
License
Rosetta License — Based on Rosetta Commons software suite. Academic use is free with registration.
推荐服务器
Baidu Map
百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。
Playwright MCP Server
一个模型上下文协议服务器,它使大型语言模型能够通过结构化的可访问性快照与网页进行交互,而无需视觉模型或屏幕截图。
Magic Component Platform (MCP)
一个由人工智能驱动的工具,可以从自然语言描述生成现代化的用户界面组件,并与流行的集成开发环境(IDE)集成,从而简化用户界面开发流程。
Audiense Insights MCP Server
通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。
VeyraX
一个单一的 MCP 工具,连接你所有喜爱的工具:Gmail、日历以及其他 40 多个工具。
graphlit-mcp-server
模型上下文协议 (MCP) 服务器实现了 MCP 客户端与 Graphlit 服务之间的集成。 除了网络爬取之外,还可以将任何内容(从 Slack 到 Gmail 再到播客订阅源)导入到 Graphlit 项目中,然后从 MCP 客户端检索相关内容。
Kagi MCP Server
一个 MCP 服务器,集成了 Kagi 搜索功能和 Claude AI,使 Claude 能够在回答需要最新信息的问题时执行实时网络搜索。
e2b-mcp-server
使用 MCP 通过 e2b 运行代码。
Neon MCP Server
用于与 Neon 管理 API 和数据库交互的 MCP 服务器
Exa MCP Server
模型上下文协议(MCP)服务器允许像 Claude 这样的 AI 助手使用 Exa AI 搜索 API 进行网络搜索。这种设置允许 AI 模型以安全和受控的方式获取实时的网络信息。