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.
š 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
š¦ 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
š§ 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"
šÆ 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"
}
}
}
}
š ļø 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
}
}
šļø Architecture
toast/
āāā src/
ā āāā clients/
ā ā āāā toast.ts # Toast API client with auth
ā āāā tools/
ā ā āāā orders.ts # 12 order tools
ā ā āāā menus.ts # 11 menu tools
ā ā āāā employees.ts # 9 employee tools
ā ā āāā labor.ts # 6 labor tools
ā ā āāā restaurant.ts # 9 restaurant tools
ā ā āāā payments.ts # 6 payment tools
ā ā āāā inventory.ts # 5 inventory tools
ā ā āāā customers.ts # 4 customer tools
ā ā āāā reporting.ts # 6 reporting tools
ā ā āāā cash.ts # 8 cash tools
ā āāā types/
ā ā āāā index.ts # Comprehensive TypeScript types
ā āāā ui/
ā ā āāā react-app/ # 18 React apps (client-side)
ā āāā server.ts # MCP server implementation
ā āāā main.ts # Entry point (stdio + HTTP)
āāā package.json
āāā tsconfig.json
āāā README.md
š API Coverage
This server implements comprehensive coverage of the Toast API:
- ā Orders API v2 (full CRUD)
- ā Menus API v2 (read + update)
- ā Labor API v1 (employees, shifts, time entries)
- ā Configuration API v1 (restaurant settings)
- ā Stock API v1 (inventory management)
- ā Cash Management API v1
- ā Partners API v1 (restaurant access)
š Authentication
Uses OAuth 2.0 client credentials flow with automatic token refresh. Tokens are managed internally and refreshed 5 minutes before expiration.
šØ UI Theme
All 18 apps use a consistent dark theme optimized for restaurant environments:
- Background:
#0f0f0f - Cards:
#1a1a1a - Accent:
#00bfa5 - Text:
#e0e0e0
š¤ Contributing
Contributions welcome! Please see the main mcpengine repo for contribution guidelines.
š License
MIT Ā© BusyBee3333
š Links
š 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)
šļø 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 ā¤ļø for the restaurant industry
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.