UCP MCP Storefront
A UCP-compliant MCP storefront server that exposes product catalog operations (search, cart, checkout) as MCP tools, following UCP schema version 2026-04-08.
README
UCP MCP Storefront
A UCP-compliant MCP storefront server that exposes a product catalog as MCP tools. Each tool maps to a real UCP capability (Catalog Search & Lookup, Cart Building, Checkout, Order Management), and every tool's output matches the corresponding UCP schema (version 2026-04-08).
UCP is transport-agnostic and explicitly supports MCP as a transport alongside REST and A2A — so "a UCP storefront exposed over MCP" is on-spec.
Key Principles
- All prices are integers in cents (e.g.
1999= $19.99). Never floats for money. - UCP version
2026-04-08— date-based versioning per the UCP spec. - Payment is always mocked — no real credentials, ever.
Quick Start
# Install dependencies
uv sync
# Run tests
uv run pytest
# Start the server (M1+)
uv run python -m ucp_mcp_storefront.server
Project Structure
├── src/ucp_mcp_storefront/ # Server source code
│ ├── server.py # FastMCP app; registers all tools
│ ├── catalog.py # Load + query the fake catalog
│ ├── cart.py # In-memory cart store
│ ├── checkout.py # UCP checkout object (mocked payment)
│ ├── ucp_mapping.py # Internal objects → UCP-shaped dicts
│ └── models.py # Pydantic models mirroring UCP fields
├── data/products.json # Fake catalog (25 items, prices in cents)
├── schemas/resolved/ # Resolved UCP JSON Schemas (for tests)
├── tests/ # pytest test suite
├── scripts/ # Schema resolution and utilities
└── docs/ # Architecture and UCP mapping docs
Milestones
- [x] M0 — Scaffold + fake catalog
- [ ] M1 — Read tools (
search,get_product) - [ ] M2 — Cart tools (
create_cart,add_to_cart,view_cart) - [ ] M3 — UCP conformance for cart/line-item shapes
- [ ] M4 — Checkout tool (UCP checkout object + mock payment)
- [ ] M5 — Polish & proof
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.