MCP LAMMPS Server
A Model Context Protocol server that enables AI assistants to interact with LAMMPS for molecular dynamics simulations through natural language commands.
README
MCP LAMMPS Server
A Model Context Protocol (MCP) server that enables AI assistants to interact with LAMMPS (Large-scale Atomic/Molecular Massively Parallel Simulator) for molecular dynamics simulations.
Status
This is still in experimental status. This package is developed in collaboration with AI coder.
Overview
This MCP is part of our workflow for the autonomous computational materials design with LLM. This MCP server provides a standardized interface for controlling LAMMPS molecular dynamics simulations through natural language commands. It enables AI assistants to:
- Set up and configure molecular dynamics simulations
- Run equilibration and production simulations
- Monitor simulation progress in real-time
- Analyze simulation results
- Manage simulation workflows
Features
Core Capabilities
- Simulation Management: Create, configure, and run LAMMPS simulations
- Structure Handling: Load molecular structures from various formats
- Real-time Monitoring: Track simulation progress and system properties
- Analysis Tools: Process trajectories and calculate thermodynamic properties
- Workflow Automation: Define and execute multi-step simulation workflows
Installation
Prerequisites
- Python 3.9 or higher
- LAMMPS with Python interface
Quick Start
-
Clone the repository:
git clone https://github.com/mcp-lammps/mcp-lammps.git cd mcp-lammps -
Create a virtual environment:
python -m venv venv source venv/bin/activate # On Windows: venv\Scripts\activate -
Install dependencies:
pip install -r requirements.txt -
Install in development mode:
pip install -e .
Usage
Basic Usage
Start the MCP server:
python -m mcp_lammps.server
Configuration
The server can be configured through environment variables or configuration files:
export MCP_LAMMPS_LOG_LEVEL=INFO
export MCP_LAMMPS_WORK_DIR=/path/to/workspace
python -m mcp_lammps.server
Example Prompt
``create a water simulation with 10 water molecules, save the relevant files, run the simulation at 300 K under NVT ensemble in the selected folder (examples)''
Development
Project Structure
mcp_lammps/
├── src/mcp_lammps/
│ ├── server.py # Main MCP server
│ ├── lammps_interface.py # LAMMPS wrapper
│ ├── simulation_manager.py # Simulation management
│ ├── data_handler.py # Data processing
│ ├── tools/ # MCP tools
│ └── utils/ # Utilities
├── tests/ # Test suite
├── examples/ # Usage examples
└── docs/ # Documentation
Contributing
- Fork the repository
- Create a feature branch
- Make your changes
- Add tests for new functionality
- Ensure all tests pass
- Submit a pull request
License
This project is licensed under the Apache License - see the LICENSE file for details.
Acknowledgments
- LAMMPS development team for the molecular dynamics engine
- Model Context Protocol community for the MCP framework
- Scientific computing community for inspiration and feedback
- LLM for writing the code
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。