For Five Coffee MCP Server
The For Five Coffee MCP Server provides programmatic access to For Five Coffee's menu data through both MCP tools for AI assistants and a REST API for applications.
Access full menu data including all categories and items via the
get_full_menutool or/api/menuendpointSearch menu items by name, description, or category using the
search_menu_itemstool or/api/menu/search?q={query}endpointBrowse categories through the
get_menu_categoriestool or/api/menu/categoriesendpointFilter by category using the
get_items_by_categorytool or/api/menu/category/{name}endpointIntegrate with AI assistants like Claude Desktop and Cursor through MCP protocol for natural language queries
Build web applications using the HTTP API with health checks, server info, and menu operations
Use in multiple programming languages with JavaScript and Python client examples
Handle common issues automatically with SSL fallback mechanisms and error handling
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@For Five Coffee MCP Server What coffee drinks does For Five Coffee have?"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
For Five Coffee MCP Server
A Model Context Protocol (MCP) server that provides access to For Five Coffee menu data. Works with Claude Desktop, Cursor, and other MCP clients, plus provides a REST API.
Quick Start
git clone https://github.com/Kong/for-five-mcp.git
cd for-five-mcp
npm install
npm startThis starts both:
MCP Server (stdio) - for AI assistants
HTTP API (port 3000) - for web apps
Related MCP server: @striderlabs/mcp-shakeshack
MCP Client Setup
Claude Desktop
Add to claude_desktop_config.json:
{
"mcpServers": {
"for-five-coffee": {
"command": "node",
"args": ["/path/to/for-five-mcp/server.js"]
}
}
}Cursor
Option 1: Let Cursor start the server
Add to ~/.cursor/mcp.json:
{
"mcpServers": {
"for-five-coffee": {
"command": "node",
"args": ["/path/to/for-five-mcp/server.js"],
"env": {
"PORT": "3000"
}
}
}
}Option 2: Connect to already running server
If you're running npm start separately, add this to ~/.cursor/mcp.json:
{
"mcpServers": {
"for-five-coffee": {
"url": "http://localhost:3000/mcp",
"transport": "http"
}
}
}This connects Cursor to the running MCP server via HTTP JSON-RPC 2.0 transport.
Usage Examples
Ask Your AI Assistant
"What coffee drinks does For Five Coffee have?"
"Search for pastries on the menu"
"What's the cheapest coffee option?"
"Show me all tea varieties"
Use the HTTP API
# Get full menu
curl http://localhost:3000/api/menu
# Search for items
curl "http://localhost:3000/api/menu/search?q=latte"
# Get categories
curl http://localhost:3000/api/menu/categoriesIn Your Code
// Fetch menu data
const response = await fetch('http://localhost:3000/api/menu');
const menu = await response.json();
// Search items
const search = await fetch('http://localhost:3000/api/menu/search?q=coffee');
const results = await search.json();import requests
# Get menu
menu = requests.get('http://localhost:3000/api/menu').json()
# Search
results = requests.get('http://localhost:3000/api/menu/search',
params={'q': 'latte'}).json()Available Endpoints
Endpoint | Description |
| Server info |
| Health check |
| Full menu |
| Search items |
| All categories |
| Items by category |
| MCP JSON-RPC 2.0 endpoint |
MCP Tools
get_full_menu- Get complete menusearch_menu_items- Search by queryget_menu_categories- List categoriesget_items_by_category- Filter by category
Development
npm run dev # Start with auto-restart
npm test # Run all tests
npm run test:unit # Unit tests only
npm run test:http # HTTP API tests only
npm run test:mcp # MCP transport tests only
npm run test:integration # Integration tests only
npm run lint # Check code styleTroubleshooting
MCP not working?
Check the absolute path to
server.jsin your configRestart your MCP client after config changes
Run
npm startmanually to test
HTTP API not responding?
Make sure server is running:
npm startCheck port 3000 isn't in use:
lsof -i :3000Test:
curl http://localhost:3000/health
No menu data?
Check internet connection
The server handles SSL issues automatically
Website structure may have changed (fallbacks included)
License
Apache 2.0
Available Tools
4 toolsget_items_by_categoryB
Get all menu items from a specific category
Inputs: category (required).
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 4 tools
The tools are mostly distinct with clear purposes: get_full_menu retrieves everything, get_items_by_category filters by category, get_menu_categories lists categories only, and search_menu_items searches by name or category. However, get_items_by_category and search_menu_items could potentially overlap if searching by category, but their descriptions clarify the distinction—one lists all items in a category while the other searches within items.
All tool names follow a consistent verb_noun pattern using snake_case: get_full_menu, get_items_by_category, get_menu_categories, and search_menu_items. The verbs 'get' and 'search' are appropriately used and maintain a predictable naming convention throughout the set.
With 4 tools, this server is well-scoped for a coffee shop menu domain. Each tool serves a distinct function in retrieving or filtering menu data, and the count is appropriate—not too sparse or bloated—for the apparent purpose of exploring a menu.
The tool set covers the core read operations for a menu: fetching the full menu, filtering by category, listing categories, and searching items. A minor gap is the lack of tools for updating or managing the menu (e.g., add_item, update_price), but as a read-only surface for menu exploration, it is reasonably complete.
Maintenance
Related MCP Connectors
Foursquare Places MCP — migrated to the 2025 Places API
Restaurant menus, carts, reservations and owner drafts for AI agents (Thmenu MCP).
AI-native restaurant discovery: verified/menu-indexed/discovered tiers + signed allergy-safety data.
Run your restaurant from an AI client: orders, menu, reports, refunds, payouts and staff.
Related MCP Servers
- FlicenseBqualityDmaintenanceAn MCP adapter that maps Coffee Company B2B HTTP APIs to MCP tools, allowing AI agents to query member information, benefits, coupons, and payment statuses. It enables seamless integration for AI assistants to manage coffee-related customer assets and loyalty details through natural language.101-
- AlicenseAqualityDmaintenanceThis MCP server provides tools for interacting with Shake Shack restaurant data, including browsing menus, searching for items, and finding locations. It also enables users to access nutritional information, featured items, and ordering details through natural language.7MIT
- FlicenseNot gradedqualityDmaintenanceEnables coffee shop order management via MCP, including menu lookup, order creation, and status tracking.-
- FlicenseNot gradedqualityDmaintenanceEnables natural language interaction with a coffee shop's inventory and order system, allowing users to check menu items, place orders, and track order status via MCP tools.-