Water Bar Email MCP Server
Enables sending branded wellness booking confirmation emails through Resend integration. Supports multiple email flows including AOI experience bookings with AI-suggested drink pairings and timeline layouts.
README
Water Bar Email# Case File: Hydration
Another late night in the data district.
Supabase had the records.
React wrote the story.
Resend delivered the goods.
This isn't just another email server — it's an MCP crew working together to solve the hydration case.
The Demo
Watch the case unfold (add your video link)
The Evidence
- Supabase MCP → Pulls the booking (neat, precise)
- React Email → Dresses it up sharp (timeline, purple gradient, paired drinks)
- Resend MCP → Slips it into the inbox (no middlemen)
- Supabase logs → Keeps the receipts (sent, delivered, timestamped)
Case closed.
Fork This Case
Prerequisites:
- Node.js 18+
- Windsurf IDE (with MCP support)
- Resend API key
- Supabase project
Setup:
# Clone the case file
git clone https://github.com/yourusername/case-file-hydration
cd case-file-hydration
# Install dependencies
npm install
2. Build
npm run build
3. Configure Windsurf
Add to ~/.codeium/windsurf/mcp_config.json:
{
"mcpServers": {
"waterbar-emails": {
"command": "node",
"args": ["C:\\Users\\azamb\\OneDrive\\Desktop\\THE.WATER.BAR\\mcp-waterbar-emails\\build\\index.js"],
"env": {
"RESEND_API_KEY": "re_your_api_key_here"
}
}
}
}
4. Refresh MCP in Windsurf
Click the hammer icon → Refresh MCP servers
Demo: AOI Booking Confirmation
In Windsurf chat, try:
Use the waterbar-emails MCP. Call send_waterbar_email with this:
{
"flow": "aoi-booking-confirmation",
"to": "azambata.1984@gmail.com",
"data": {
"customerName": "Dr Azam",
"bookingDate": "2025-07-06",
"venue": "AOI - Al Quoz, Dubai",
"totalAmount": "AED 180.00",
"paymentUrl": "https://buy.stripe.com/test_xxx",
"bookings": [
{
"time": "08:30",
"experience": "Ice Bath",
"duration": 10,
"preDrink": "Ginger Shot",
"explanation": "Ice Bath sharply awakens your system through noradrenaline release."
},
{
"time": "09:10",
"experience": "AOI Air PRO Implosion Dome",
"duration": 50,
"duringDrink": "Humantra Electrolytes",
"explanation": "Immersive light and sound enhance cognitive clarity and focus."
},
{
"time": "10:10",
"experience": "Infrared Sauna",
"duration": 30,
"afterDrink": "METÉ Sparkling Water",
"explanation": "Gentle warmth opens circulation, preparing you for integration."
}
]
}
}
Available Flows
aoi-booking-confirmation- AOI experience bookings with timelinewater-bar-order-confirmation- Water Bar order receiptswater-bar-followup- Post-visit thank youwater-bar-missed-you- Event no-show followup
Hackathon Demo Script
Opening:
"I built an AI-orchestrated wellness booking system that chains Supabase + OpenAI + Stripe + Resend to automate multi-venue experience confirmations."
Show:
- User books Ice Bath + Air PRO + Sauna on AOI site
- AI suggests paired drinks based on physiology
- Windsurf calls send_waterbar_email MCP tool
- Beautiful branded email arrives with timeline + drinks
Emphasize:
- Multi-MCP orchestration (4 services)
- Real business value (actual bookings)
- AI-driven content (drink pairings, explanations)
- Repeatable (React Email templates = editable)
?? Planned Future Flows (Beyond Hackathon Demo)
This repo currently showcases Flow 1: AOI Booking Confirmation.
We�ve also designed (not demoed here) additional flows:
- ?? Hydration plan generation (Supabase ? Resend)
- ?? On-venue orchestration (timeline + paired drinks)
- ?? Combined experience recap (Stripe ? Resend ? Supabase)
These are detailed in docs/Confidential/APPENDIX_CASE_NOTES.md,
but only Flow 1 is guaranteed to work out-of-the-box for hackathon judges.
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。