SF Cleaning Service
Enables booking cleaning services in San Francisco by collecting customer details and automatically sending booking requests via email to service partners.
README
IRL - SF Cleaning Service
IRL - A Model Context Protocol (MCP) server for booking cleaning services in San Francisco. Can be deployed locally or to Vercel for remote access.
Setup
1. Install Dependencies
npm install
2. Set Up Resend API
-
Create Resend Account: Go to https://resend.com and sign up
-
Get API Key:
- Navigate to your Resend Dashboard
- Go to "API Keys" section
- Create a new API key or copy your existing one
- It will look like:
re_BcASVtoX_Bj4QhZei4xSjyyLr21vhMbVd
-
Verify Domain (Required for custom email):
- To send from gwen@irl-concierge.com
- Go to "Domains" in Resend Dashboard
- Add domain: irl-concierge.com
- Follow DNS verification steps (add TXT, MX records)
- Once verified, you can send from gwen@irl-concierge.com
3. Configure Email Credentials
Edit .env file with your Resend credentials:
RESEND_API_KEY=re_xxxxxxxxxxxxxxxxxx
FROM_EMAIL=gwen@irl-concierge.com
PARTNER_EMAILS=partner1@example.com,partner2@example.com
Note: You must verify the domain irl-concierge.com in Resend before you can send from gwen@irl-concierge.com. Until verified, use onboarding@resend.dev for testing.
4. Configure Claude Desktop
Add to your Claude Desktop configuration file:
macOS: ~/Library/Application Support/Claude/claude_desktop_config.json
Windows: %APPDATA%\Claude\claude_desktop_config.json
{
"mcpServers": {
"sf-cleaning": {
"command": "node",
"args": ["/absolute/path/to/mcp-sf-cleaning/index.js"]
}
}
}
Replace /absolute/path/to/mcp-sf-cleaning/index.js with the actual path to your index.js file.
5. Restart Claude Desktop
After configuration, restart Claude Desktop to load the MCP server.
Vercel Deployment (For Remote Access)
1. Install Vercel CLI
npm install -g vercel
2. Set Environment Variables
cd /Users/rana/Downloads/IRL/mcp-sf-cleaning
# Set up Vercel environment variables
vercel env add RESEND_API_KEY
# Enter: re_BcASVtoX_Bj4QhZei4xSjyyLr21vhMbVd
vercel env add FROM_EMAIL
# Enter: gwen@irl-concierge.com
vercel env add PARTNER_EMAILS
# Enter: ranadaytoday@outlook.com
3. Deploy to Vercel
vercel --prod
Follow the prompts:
- Set up and deploy? Y
- Which scope? (select your account)
- Link to existing project? N
- Project name? irl
- Directory? ./
- Want to modify settings? N
4. Get Your MCP Server URL
After deployment, you'll get a URL like:
https://mcp-sf-cleaning.vercel.app
5. Add to Claude Desktop as Custom Connector
- Open Claude Desktop
- Go to Settings → Connectors
- Click "Add custom connector"
- Enter:
- Name: SF Cleaning Service
- Remote MCP server URL:
https://mcp-sf-cleaning.vercel.app/api/mcp
- Save and restart Claude
Testing the Remote Server
You can test the API directly:
# List tools
curl -X POST https://mcp-sf-cleaning.vercel.app/api/mcp \
-H "Content-Type: application/json" \
-d '{"method":"tools/list"}'
# Request cleaning (SF address)
curl -X POST https://mcp-sf-cleaning.vercel.app/api/mcp \
-H "Content-Type: application/json" \
-d '{
"method": "tools/call",
"params": {
"name": "request_cleaning",
"arguments": {
"name": "John Doe",
"phone": "415-555-1234",
"address": "123 Market St, SF 94105"
}
}
}'
Test Conversation Examples
Example 1: San Francisco Address (Accepted)
You: Can you book a cleaning service for me?
Claude: I'll help you book a cleaning service. I'll need your name, phone number, and address.
You: Name is John Doe, phone is 415-555-0123, address is 123 Market St, San Francisco, CA 94105
Claude: [Uses request_cleaning tool]
Result: ✅ Sent! John Doe, they'll call 415-555-0123 within 1 hour.
Example 2: Non-SF Address (Rejected)
You: Book cleaning for Sarah Smith, 510-555-9876, 456 Broadway, Oakland, CA 94607
Claude: [Uses request_cleaning tool]
Result: Sorry, we only serve San Francisco currently. We're expanding - stay tuned!
Example 3: SF Zip Code Detection
You: I need cleaning at 789 Pine Street, 94108. Name: Alice Wong, Phone: 415-555-3456
Claude: [Uses request_cleaning tool]
Result: ✅ Sent! Alice Wong, they'll call 415-555-3456 within 1 hour.
Usage
The server provides one tool:
request_cleaning: Books cleaning service for SF addresses only
Parameters:
name: Customer namephone: Contact phone numberaddress: Service address (must be in San Francisco)
Responses:
- SF Address: "✅ Sent! [name], they'll call [phone] within 1 hour."
- Non-SF Address: "Sorry, we only serve San Francisco currently. We're expanding - stay tuned!"
How It Works
- Checks if address contains "sf", "san francisco", or SF zip codes (940xx, 941xx)
- If in SF: Sends email via Resend API to partners and confirms booking
- If not in SF: Returns polite rejection message
Why Resend?
- Simple API: Clean, modern email API designed for developers
- No SMTP hassles: No need for app passwords or complex SMTP settings
- Better deliverability: Built-in SPF, DKIM, and DMARC support
- Free tier: 3,000 emails/month free, perfect for small projectsTest auto-deployment
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。