Zenoti MCP Server
Enables AI agents to manage spa/wellness operations via Zenoti API, including appointments, guests, services, and billing.
README
Zenoti MCP Server
A Model Context Protocol (MCP) server that provides intelligent access to the Zenoti spa/wellness management API. Designed for AI agents to efficiently manage appointments, guests, services, and billing workflows.
Features
Workflow-Centric Tools
- Complete Service Booking: Single tool handles the entire 4-step booking flow
- Guest Lifecycle Management: Create, search, update guests with smart defaults
- Appointment Management: Check-in, status updates, and progress tracking
- Invoice & Payment: Retrieve, confirm, and close invoices with proper error handling
- Forms & Feedback: List forms, retrieve data, and submit feedback
Agent-Optimized Design
- Context-Efficient Responses: Returns only essential information by default
- Smart Error Messages: Guides agents toward correct usage patterns
- Workflow Consolidation: Combines related operations into single tools
- Human-Readable Outputs: Uses names over IDs, dates in readable format
Installation
- Clone the repository:
git clone https://github.com/yourusername/zenoti-mcp-server.git
cd zenoti-mcp-server
- Install dependencies:
npm install
- Configure environment variables:
cp .env.example .env
# Edit .env with your Zenoti API credentials
- Build the server:
npm run build
Configuration
Environment Variables
ZENOTI_API_KEY: Your Zenoti API key (required)ZENOTI_API_URL: Zenoti API base URL (default: https://api.zenoti.com)ZENOTI_CENTER_ID: Default center ID for operationsZENOTI_ORG_ID: Your organization ID
Obtaining API Credentials
- Log into Zenoti Admin
- Navigate to: Admin > Setup > Apps (organization level)
- Create a new backend app
- Assign necessary module permissions (avoid global permissions)
- Copy the API key (valid for 1 year)
Usage
Running the Server
# Development mode with auto-reload
npm run dev
# Production mode
npm start
# Test the server with example client
npm test
Connecting from Claude Desktop
Add to your Claude Desktop configuration (claude_desktop_config.json):
{
"mcpServers": {
"zenoti": {
"command": "node",
"args": ["/path/to/zenoti-mcp-server/dist/index.js"],
"env": {
"ZENOTI_API_KEY": "your_api_key",
"ZENOTI_API_URL": "https://api.zenoti.com",
"ZENOTI_CENTER_ID": "your_center_id"
}
}
}
}
Available Tools
Service Booking
book_service
Complete 4-step service booking workflow in a single tool.
Parameters:
guest_id(required): Guest ID or search queryservice_id(required): Service ID or namedate(required): Appointment date (YYYY-MM-DD)time(optional): Preferred time (HH:MM)therapist_id(optional): Therapist ID or namenotes(optional): Booking notespay_later(optional): Skip payment (default: true)
Example:
{
"guest_id": "john.doe@email.com",
"service_id": "Deep Tissue Massage",
"date": "2025-11-15",
"time": "14:00"
}
Guest Management
search_guests
Search for guests by name, email, or phone.
Parameters:
query(required): Search querylimit(optional): Max results (default: 10)
create_guest
Create a new guest profile.
Parameters:
first_name(required)last_name(required)email(optional)phone(optional)gender(optional)date_of_birth(optional)
Appointment Management
list_appointments
List appointments with filters.
Parameters:
start_date(required): Start date (YYYY-MM-DD)end_date(optional): End date (default: start_date)status(optional): Filter by statusguest_id(optional): Filter by guestlimit(optional): Max results (default: 50)
check_in_appointment
Check in a guest for their appointment.
Parameters:
appointment_id(required): Appointment or group ID
update_appointment_status
Update appointment status (confirm, cancel, no-show).
Parameters:
appointment_id(required)status(required): "confirmed", "cancelled", "no_show"reason(optional): Cancellation reason
Invoice & Payment
get_invoice
Retrieve invoice details.
Parameters:
invoice_id(required)include_details(optional): Include line items (default: true)
close_invoice
Process payment and close invoice.
Parameters:
invoice_id(required)payment_method(optional): Payment typeamount(optional): Payment amount
Forms & Feedback
list_appointment_forms
Get forms for an appointment.
Parameters:
appointment_id(required)
submit_feedback
Submit guest feedback for appointment.
Parameters:
appointment_id(required)rating(required): 1-5 or 1-10comments(optional)
Error Handling
The server provides actionable error messages to guide agents:
{
"error": "No available slots found",
"suggestion": "Try a different date or remove therapist preference",
"alternatives": ["2025-11-16", "2025-11-17"]
}
Rate Limiting
The server implements intelligent rate limiting:
- Automatic retry with exponential backoff
- Rate limit status in responses
- Suggestions for reducing API calls
Development
Project Structure
zenoti-mcp-server/
├── src/
│ ├── index.ts # MCP server entry point
│ ├── zenoti-client.ts # Zenoti API client
│ ├── tools/ # Tool implementations
│ │ ├── booking.ts # Service booking tools
│ │ ├── guests.ts # Guest management tools
│ │ ├── appointments.ts # Appointment tools
│ │ └── invoices.ts # Invoice tools
│ ├── utils/ # Shared utilities
│ │ ├── errors.ts # Error handling
│ │ ├── formatters.ts # Response formatting
│ │ └── validators.ts # Input validation
│ └── test-client.ts # Test client
├── package.json
├── tsconfig.json
└── README.md
Testing
Run the test client to verify functionality:
npm test
The test client demonstrates:
- Service booking workflow
- Guest search and creation
- Appointment management
- Error handling
Best Practices
For AI Agents
- Use search before create: Always search for existing guests before creating
- Handle partial matches: Guest search returns fuzzy matches
- Respect rate limits: Use suggested delays between requests
- Check availability first: Query slots before attempting bookings
- Use human-readable inputs: Names work as well as IDs
For Developers
- Environment-specific apps: Create separate Zenoti apps for dev/staging/prod
- Minimal permissions: Grant only necessary module permissions
- Token refresh: Implement token refresh for long-running sessions
- Error logging: Monitor failed requests for API issues
- Webhook integration: Consider webhooks for real-time updates
Troubleshooting
Common Issues
-
API Key Authorization Denied (Error 602)
- Verify API key is correct and not expired
- Check app has necessary permissions in Zenoti
- Ensure using correct center_id
-
No Available Slots
- Check service is bookable online
- Verify therapist works on requested date
- Try without therapist preference
-
Guest Not Found
- Search uses fuzzy matching
- Try partial name or email
- Check guest exists in correct center
License
MIT License - See LICENSE file for details
Support
For issues or questions:
- GitHub Issues: zenoti-mcp-server/issues
- Zenoti API Docs: docs.zenoti.com
- MCP Protocol: modelcontextprotocol.io
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。