solarAI-X MCP Server
Integrates with OpenAI-compatible models to process natural language queries and orchestrate MCP tools for solar and perovskite domain tasks, including knowledge retrieval, calculations, simulations, and plotting.
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@solarAI-X MCP ServerSimulate a perovskite solar cell with bandgap 1.6 eV and show J-V curve"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
SolarAI-X
太阳能与钙钛矿领域工具应用:自然语言提问经OpenAI兼容模型与MCP编排,完成知识检索、带隙计算、仿真/预测及绘图,保存任务过程与生成结果。
9个MCP工具、5类Gradio业务页面、FastAPI/SSE流式交互。
异步模型流;工具白名单、Schema校验、超时和只读检索有限重试。
SQLite任务与会话、取消和重启恢复;标准/旧版MCP错误均明确记录。
生成结果目录与下载权限一致;PNG结构、校验和及像素解码共同验证。
flowchart LR
U[Gradio页面] --> A[FastAPI与SSE]
A --> L[OpenAI兼容模型]
L --> T[MCP工具编排]
T --> R[知识检索]
T --> C[计算与科学模型]
T --> V[图表产物]
T --> S[SQLite任务与会话]
R --> L
C --> L
V --> U快速开始
Python 3.12。在项目根目录安装基础依赖:
py -3.12 -m venv .venv
.\.venv\Scripts\python.exe -m pip install --index-url https://download.pytorch.org/whl/cpu "torch>=2.3,<3.0"
.\.venv\Scripts\python.exe -m pip install -r requirements.txt -r requirements-dev.txt
Copy-Item .env.example .env按 .env.example 配置自己的模型服务,再分别运行 run_mcp.bat、run_api.bat、run_ui.bat。
打开 API健康状态、接口文档、Gradio页面。已有 .env 时直接保留原配置。
Related MCP server: MCP Hub
固定演示与真实验证
无需模型密钥的离线演示:
.\.venv\Scripts\python.exe scripts/run_offline_demo.py此模式使用脚本模型和真实本地工具,不代表模型自主决策质量。另有 三分钟演示步骤、真实任务摘要 和 实际生成曲线。
已启动MCP并配置模型后,可手动执行以下真实任务评测(会消耗额度):
.\.venv\Scripts\python.exe scripts/evaluate_agent_live.py --live --max-cases 2验证与边界
历史验证:2026-10-19早期本地Windows回归156项通过;2026-10-18的2条真实模型与SSE MCP固定任务通过,并用v3图片校验复评。数量不代表通用准确率、科学预测精度或生产吞吐。
本轮扩展评测:40道独立任务首轮32/40、含重复46/56严格验收通过;固定8任务中7个三次通过。保留失败并修复标识漏检、错误类别丢失和无效表格数据,修复后Windows本地198项回归及8项实际MCP检查通过,尚未真实模型复测。详见 扩展验收及限制。
BGE语义检索与AutoGluon预测需要额外依赖及模型资产;能力状态接口会报告实际可用情况。关键词降级结果不会称为语义检索。
当前为本机单用户、单API worker演示。另在不含 .env 的全新Python 3.12环境完成安装、同样数量的回归与实际启动验证。当前PR通过Windows与Ubuntu工作流执行回归,结果以Pull Request检查为准。
带隙功能当前提供 MAPbIBr 原项目线性公式演示;CsMAFAPbIBr、MAFA、CsFA 缺少可核验训练资料,暂不可预测。详见 v4科学模型契约修复。
新增公开光谱文献训练的带隙基线、严格留出评估与12任务验证工具;详见 v5改进。三个低样本材料家族仍未开放。12任务的真实模型验收结果见下节。
真实模型验收(固定12任务)
使用 qwen-plus 与真实本地MCP工具,12道固定任务12道通过(8正向、4负向),新增23次聊天、0次Embedding;覆盖公式/公开测量基线、绘图、越界与不可用状态。持久工具事件离线重评分仍为12/12。此结果限于这组作者编写任务,不代表通用Agent准确率或并发生产验证。见 完整验收及限制。
本轮可靠性修复:将计算结果引用绑定到实际绘图数据,最终回答在产物路径核对通过后输出;5个真实本地MCP场景通过。 最新Windows本地完整回归231项通过,未追加付费模型复测。实现与限制见 可靠性修复说明,远程验证以本次PR的Windows/Ubuntu检查结果为准。
This server cannot be deployed
Maintenance
Related MCP Connectors
Pay-per-use tool marketplace for AI agents. Search, price-check, and call APIs via MCP.
Hosted MCP with 91 agent tools: X, domains, SEO, Maps, Trends, Search, YouTube, TikTok, and more.
214 tools for AI agents over one MCP endpoint: image, video, audio, 3D, data, storage, mail, GPUs.
Free public MCP for AI agents — 193 tools, 44 workflows. No API key.
Related MCP Servers
- AlicenseNot gradedqualityDmaintenanceEnables AI agents to access a unified catalog of tools from various APIs (OpenAPI, GraphQL, MCP, Google Discovery) through the MCP protocol.2 npmMIT
- AlicenseNot gradedqualityBmaintenanceA universal MCP hub that connects any AI agent to any tool, enabling agent interoperability with 50+ pre-built tools, custom tool creation, and tool discovery.315 npmMIT
- AlicenseNot gradedqualityCmaintenanceEnables AI agents to securely discover, invoke, and manage tools through a hardened MCP endpoint with protections like injection detection, circuit breakers, retry backoff, response caching, context-window limiting, and state snapshots.8 npmMIT
- FlicenseNot gradedqualityBmaintenanceEnables AI agents to access unified development tools including code generation, documentation synchronization, test case rendering, and architecture graph queries through a single MCP server.-