gems-mcp
MCP server wrapping xGEMS for thermodynamic equilibrium calculations, offering tools to list systems, get system info, and run simulations.
README
GEMS CLI
封装 xGEMS 库的热力学模拟 CLI 工具和 MCP Server,供 AI Agent 和研究者调用。
项目结构
gemscli/
├── gems_cli/ # Python 包
│ ├── engine.py # GemsEngine 核心封装 + GemsExplorer
│ ├── cli.py # CLI 入口 (gems-cli)
│ ├── mcp_server.py # MCP Server (gems-mcp),4 个工具
│ ├── utils.py # 单位转换、路径解析
│ └── templates/ # JSON 模拟模板
├── data/systems/ # 7 个预导出的 GEMS3K 热力学系统
├── examples/ # 使用示例 + 论文复现脚本
├── docs/ # 技术文档
├── GEMS3.11.2/ # GEM-Selektor 分发包(二进制 + 数据库)
└── pyproject.toml
快速开始
1. 安装依赖
conda config --add channels conda-forge
conda create -n gems python=3.11 -y
conda activate gems
conda install xgems -y
pip install mcp # MCP Server 依赖
pip install -e . # 开发模式安装
2. 使用 CLI
# 列出可用系统
gems-cli --list-systems
# 查看系统元数据
gems-cli --system-info calcite
# 运行平衡计算(内联参数)
gems-cli --system calcite --T 25 --P 1 \
--bulk-composition '{"Ca":0.01,"C":0.01,"H":111,"O":55.5}'
# 运行平衡计算(JSON 文件)
gems-cli --input gems_cli/templates/aragonite_calcite.json
3. 启动 MCP Server
gems-mcp # stdio 模式(默认)
gems-mcp --transport sse --port 8765 # SSE 模式
可用系统
| 系统 | 元素 | 相 | 说明 |
|---|---|---|---|
calcite |
10 | 13 | Ca-C-O-H 地球化学,文石/方解石平衡 |
cement_hydration |
24 | 110 | 完整水泥水化(C-S-H, CH, AFt, AFm 等) |
iron_redox |
7 | 4 | Fe²⁺/Fe³⁺ 氧化还原体系 |
exchange_sorption |
8 | 7 | 铀在粘土矿物上的离子交换吸附 |
PC_leaching |
13 | 84 | 硅酸盐水泥浸出 |
mortar_dissolution |
13 | 81 | 砂浆骨料溶解 |
ferrite_carbonation |
8 | ~30 | C4AF 铁铝酸盐强制碳化(从 PC_leaching 精简) |
验证
本项目已通过以下文献的热力学模拟结果验证:
- Ma Z, Jiang Y, Ding T, et al. Elucidating the behaviours and mechanisms of enforced carbonation in ferrite. Cement and Concrete Research, 2025, 195: 107916. DOI: 10.1016/j.cemconres.2025.107916
- Kim N, Seo J, Jang J G, et al. Thermodynamic modeling of carbonated Portland cement under groundwater and seawater conditions. Cement and Concrete Composites, 2025, 162: 106141. DOI: 10.1016/j.cemconcomp.2025.106141
- Gao W, Zhao M, Li C, et al. Synergistic mechanisms of multiple components in lithium slag-based low-carbon cement: Multi-scale insights from thermodynamic modeling to hydration-driven microstructural evolution. Cement and Concrete Composites, 2026, 162: 106508. DOI: 10.1016/j.cemconcomp.2026.106508
- Pang L, Sun J, Provis J L, et al. Thermodynamic simulation-assisted design of the electrolytic manganese residue-slag-Ca(OH)₂ cementitious system. Cement and Concrete Research, 2025. DOI: 10.1016/j.cemconres.2025.108119
相关资源
- xGEMS 源码: https://bitbucket.org/gems4/xgems
- xGEMS Jupyter 示例: https://github.com/gemshub/xgems-jupyter
- GEM-Selektor 文档: https://gemshub.github.io/start/gemselektor/documentation/
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.