Configured for deployment as serverless functions on Netlify's platform, allowing the MCP server to run in a production environment
Uses OpenStreetMap's Nominatim service for geocoding to enable location-based restaurant search and discovery
Provides mock integration with Square's commerce platform, demonstrating restaurant catalog management and order processing workflows for agentic commerce experiences
Integrates with Unsplash for menu item images to enhance the visual presentation of restaurant menus and food items
Agentic Commerce MCP Demo (Goose + MCP UI)
A small Model Context Protocol (MCP) server that showcases agentic commerce UX using MCP UI blocks inside Goose. It returns rich, interactive HTML UI for a simple “find restaurants → view menu → fake order → receipt” flow.
Important notes:
Demo only. No real sellers, data, payments, or money movement. Everything is synthetic or mocked.
Not production code. This exists to demonstrate how MCP UI can drive a click-first agent experience.
Features
Streamable HTTP MCP server with multiple tools:
find_restaurants
– search nearby synthetic restaurants by city/state and queryview_restaurant
– details card for a restaurantview_menu
– menu with images and pricing (mock catalog if “Square” is detected; otherwise a generic menu fallback)order_takeout
– interactive order page (edit quantities, remove items)view_receipt
– playful, fake receipt
Click-first MCP UI: UI dispatches tool calls back to the agent on user actions.
Dev HTML previews for local testing at http://127.0.0.1:8000/dev
Large, synthetic dataset you can regenerate via scripts
What this is not
No live Square API calls, no money movement, no real sellers or PII
No persistent storage; no auth; no production hardening
Repo layout
src/server.ts
– MCP server with tools that render UIsrc/ui/*
– HTML shell, styles, and view builderssrc/lib/restaurants.ts
– local search over synthetic sellers + geocoding via OpenStreetMap Nominatimsrc/lib/square.ts
– tiny mock for “Square detection” and sample catalogssrc/data/*
– generated JSON for restaurants and category menussrc/scripts/*
– generators for the data abovescenarios.md
– example conversational flows and UX notes
Prerequisites
Node.js 20+
pnpm (bundled with Node) or ppnpm/yarn
Setup
Install dependencies
Generate demo data (optional; the repo includes prebuilt JSON)
Run the MCP server (dev)
Environment variables you can set:
MCP_HOST (default: 127.0.0.1)
MCP_PORT (default: 8000)
MCP_GEOCODE_USERAGENT (default: "mcp-agentic-commerce/1.0 (+https://squareup.com)")
Try the local UI previews in a browser
Use with Goose
This project is designed to be consumed as an MCP extension by Goose.
Option A — Add manually in Goose settings:
Open Goose Desktop → Settings → Extensions → Add MCP server
Type: HTTP (streamable)
Name: Agentic Commerce MCP Demo
Save. Start a new chat and ask something like:
“Find coffee around Austin”
“Show pizza near Toronto”
“Order two lattes from Midtown Bean at 9:15 under Sam.”
Option B — Use the MCP Inspector (handy for testing tools and UI):
Tip: If your model/agent supports MCP UI, it will render the HTML cards, menus, and receipts inline and dispatch tool calls on button clicks.
Tool reference
find_restaurants
args: city (string, default "Austin"), state (optional), query (optional), limit (1..25, default 10)
returns: UI list of nearby sellers; buttons to “Details” and “Order Now”
view_restaurant
args: business_id (string)
returns: UI card with address, hours, phone, website; CTA buttons
view_menu
args: business_id (string)
behavior: if mock "Square" is detected -> use mock catalog; else generic menu by primary category
order_takeout
args: business_id (string), items (array of { name, qty, price })
returns: interactive order table with totals and a Place Order button
view_receipt
args: business_id (string), items (same as above)
returns: playful demo receipt UI
Data notes
Restaurants are synthetic and based on seeded generators across many US/CA cities. You can regenerate or reduce the dataset density via env vars on the generator script.
Menu images are hotlinked from Unsplash and used only for illustrative purposes in this demo.
Safety and disclaimers
For demonstration only; do not treat any information as factual.
No money movement occurs. The “Place order” flow only renders a confirmation UI.
Deployment
Deploy to Netlify
This project is configured to deploy as a serverless function on Netlify:
Connect to Netlify:
Go to Netlify
Click "Add new site" → "Import an existing project"
Connect your GitHub repository
Build Settings (auto-detected from netlify.toml):
Build command:
pnpm run build
Publish directory:
dist
Deploy:
Netlify will automatically deploy on push to main
Your MCP server will be available at:
https://your-site-name.netlify.app/mcp
Dev preview available at:
https://your-site-name.netlify.app/dev
Use with Goose (Production):
Once deployed, use your Netlify URL in Goose settings
Type: HTTP (streamable)
URL:
https://your-site-name.netlify.app/mcp
License
This project is licensed under the MIT License - see the LICENSE file for details.
This server cannot be installed
hybrid server
The server is able to function both locally and remotely, depending on the configuration or use case.
Enables interactive restaurant discovery and ordering through a synthetic commerce flow with rich HTML UI. Demonstrates agentic commerce UX with tools to find restaurants, view menus, place mock orders, and generate receipts.
Related MCP Servers
- AsecurityAlicenseAqualityAllows AI assistants to seamlessly interact with Terminal.shop to browse products, manage shopping carts, place orders, and handle subscriptions through Terminal.shop's API.Last updated -19121MIT License
- AsecurityAlicenseAqualityAn AI-powered server that helps users discover and book restaurants based on location, cuisine preferences, mood, and event type, with integration to Google Maps Places API for accurate recommendations.Last updated -55MIT License
- -securityFlicense-qualityProvides grocery price and nutritional information search capabilities, allowing AI agents to search for food products, compare prices, and analyze nutritional content across different grocery stores.Last updated -
- -securityFlicense-qualityEnables interaction with e-commerce storefronts through a standardized API. Provides access to product catalogs, inventory management, and customer operations for online retail platforms.Last updated -