Toast MCP Server
Enables AI assistants to manage restaurant operations by integrating with Toast POS, including orders, menus, employees, payments, inventory, and reporting through 50+ tools and 18 React apps.
README
Toast MCP Server
Complete Model Context Protocol (MCP) server for Toast restaurant POS and management platform integration.
🚀 Features
50+ Tools Across 10 Categories
-
Orders (12 tools) - Complete order lifecycle management
- Get, list, create, void orders
- Search by customer, business date
- Add/void selections, apply discounts
- Update promised times, track status
-
Menus (11 tools) - Full menu and item management
- List/get menus, groups, items
- Search items, update pricing
- 86 management (out of stock)
- Bulk operations
-
Employees (9 tools) - Staff management
- Employee CRUD operations
- Job position management
- Search and filtering
- Time entry tracking
-
Labor (6 tools) - Workforce analytics
- Shift management
- Active shift tracking
- Labor reports and summaries
- Employee hours calculation
-
Restaurant (9 tools) - Configuration and settings
- Restaurant info and access
- Tables and service areas
- Dining options, revenue centers
- Online ordering and delivery settings
-
Payments (6 tools) - Transaction management
- Payment CRUD operations
- Refunds and voids
- Payment summaries by type
-
Inventory (5 tools) - Stock management
- Stock level tracking
- Low stock alerts
- Quantity updates
- Bulk operations
-
Customers (4 tools) - Customer relationship management
- Customer search and profiles
- Order history
- Loyalty program integration
- Top customers analysis
-
Reporting (6 tools) - Analytics and insights
- Sales summaries
- Hourly breakdown
- Item sales reports
- Payment type, discount, and void reports
-
Cash (8 tools) - Cash management
- Cash drawer tracking
- Paid in/out entries
- Deposit recording
- Drawer summaries
18 React Apps (Client-Side UI)
Orders & Service:
- Order Dashboard - Real-time monitoring
- Order Detail - Deep order inspection
- Order Grid - Multi-order management
- Table Map - Visual floor plan
Menu Management:
- Menu Manager - Full menu editing
- Menu Item Detail - Item configuration
- Menu Performance - Sales analytics
Staff & Labor:
- Employee Dashboard - Staff directory
- Employee Schedule - Shift planning
- Labor Dashboard - Cost tracking
- Tip Summary - Earnings distribution
Payments & Finance:
- Payment History - Transaction log
- Sales Dashboard - Comprehensive metrics
- Revenue by Hour - Hourly analysis
Inventory & Operations:
- Inventory Tracker - Stock management
- Restaurant Overview - System config
Customer Management:
- Customer Detail - Profiles and history
- Customer Loyalty - Rewards tracking
📦 Installation
npm install @busybee3333/toast-mcp-server
Or clone and build locally:
git clone https://github.com/BusyBee3333/mcpengine.git
cd mcpengine/servers/toast
npm install
npm run build
🔧 Configuration
Set required environment variables:
export TOAST_CLIENT_ID="your_client_id"
export TOAST_CLIENT_SECRET="your_client_secret"
export TOAST_RESTAURANT_GUID="your_restaurant_guid" # Optional
export TOAST_ENVIRONMENT="production" # or "sandbox"
🎯 Usage
Stdio Mode (MCP Integration)
toast-mcp-server
Or via npx:
npx @busybee3333/toast-mcp-server
HTTP Mode (Web UI + API)
TOAST_MCP_MODE=http TOAST_MCP_PORT=3000 toast-mcp-server
Access UI at: http://localhost:3000/apps/
Claude Desktop Integration
Add to your Claude Desktop config (~/Library/Application Support/Claude/claude_desktop_config.json):
{
"mcpServers": {
"toast": {
"command": "npx",
"args": [
"@busybee3333/toast-mcp-server"
],
"env": {
"TOAST_CLIENT_ID": "your_client_id",
"TOAST_CLIENT_SECRET": "your_client_secret",
"TOAST_RESTAURANT_GUID": "your_restaurant_guid",
"TOAST_ENVIRONMENT": "production"
}
}
}
}
🛠️ Tool Examples
Get Order
{
"name": "toast_get_order",
"arguments": {
"orderGuid": "550e8400-e29b-41d4-a716-446655440000"
}
}
List Orders for Business Date
{
"name": "toast_list_orders",
"arguments": {
"businessDate": 20240215
}
}
Create Order
{
"name": "toast_create_order",
"arguments": {
"source": "ONLINE",
"selections": [
{
"itemGuid": "item-123",
"quantity": 2
}
],
"customer": {
"firstName": "John",
"lastName": "Doe",
"phone": "+15551234567"
}
}
}
Mark Item 86'd
{
"name": "toast_set_item_86",
"arguments": {
"itemGuid": "item-456",
"outOfStock": true
}
}
Get Sales Summary
{
"name": "toast_get_sales_summary",
"arguments": {
"businessDate": 20240215
}
}
🏗️ Architecture
toast/
├── src/
│ ├── clients/
│ │ └── toast.ts # Toast API client with auth
│ ├── tools/
│ │ ├── orders.ts # 12 order tools
│ │ ├── menus.ts # 11 menu tools
│ │ ├── employees.ts # 9 employee tools
│ │ ├── labor.ts # 6 labor tools
│ │ ├── restaurant.ts # 9 restaurant tools
│ │ ├── payments.ts # 6 payment tools
│ │ ├── inventory.ts # 5 inventory tools
│ │ ├── customers.ts # 4 customer tools
│ │ ├── reporting.ts # 6 reporting tools
│ │ └── cash.ts # 8 cash tools
│ ├── types/
│ │ └── index.ts # Comprehensive TypeScript types
│ ├── ui/
│ │ └── react-app/ # 18 React apps (client-side)
│ ├── server.ts # MCP server implementation
│ └── main.ts # Entry point (stdio + HTTP)
├── package.json
├── tsconfig.json
└── README.md
📊 API Coverage
This server implements comprehensive coverage of the Toast API:
- ✅ Orders API v2 (full CRUD)
- ✅ Menus API v2 (read + update)
- ✅ Labor API v1 (employees, shifts, time entries)
- ✅ Configuration API v1 (restaurant settings)
- ✅ Stock API v1 (inventory management)
- ✅ Cash Management API v1
- ✅ Partners API v1 (restaurant access)
🔐 Authentication
Uses OAuth 2.0 client credentials flow with automatic token refresh. Tokens are managed internally and refreshed 5 minutes before expiration.
🎨 UI Theme
All 18 apps use a consistent dark theme optimized for restaurant environments:
- Background:
#0f0f0f - Cards:
#1a1a1a - Accent:
#00bfa5 - Text:
#e0e0e0
🤝 Contributing
Contributions welcome! Please see the main mcpengine repo for contribution guidelines.
📄 License
MIT © BusyBee3333
🔗 Links
🐛 Known Issues
- HTTP mode tool execution not yet implemented (use stdio mode for MCP)
- UI apps currently use client-side demo data (connect to Toast API for live data)
🗓️ Roadmap
- [ ] WebSocket support for real-time order updates
- [ ] Full HTTP mode implementation
- [ ] Additional reporting endpoints
- [ ] Kitchen display system (KDS) integration
- [ ] Multi-location support
Built with ❤️ for the restaurant industry
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。