This directory contains sample implementations and client scripts for the Universal Commerce Protocol (UCP).
A reference implementation of a UCP Merchant Server using Python and FastAPI.
-
Server: Documentation
- Located in
rest/python/server/. - Demonstrates capability discovery, checkout session management, payment processing, and order lifecycle.
- Includes simulation endpoints for testing.
- Located in
-
Client: Happy Path Script
- Located in
rest/python/client/. - A script demonstrating a full "happy path" user journey (discovery -> checkout -> payment).
- Located in
A reference implementation of a UCP Merchant Server using Node.js, Hono, and Zod.
- Server: Documentation
- Located in
rest/nodejs/. - Demonstrates implementation of UCP specifications for shopping, checkout, and order management using a Node.js stack.
- Located in
A reference implementation using the Model Context Protocol for AI agent integration.
-
Server & Client: Documentation
- Located in
mcp/python/. - Exposes UCP shopping capabilities as MCP tools and resources.
- Enables AI agents (Claude, GPT, etc.) to perform commerce operations.
- Includes example client demonstrating complete shopping flow.
- Located in
Key Features:
- Tools for product discovery, checkout, payment, and order management
- Resources for read-only access to catalogs, sessions, and orders
- Prompts for reusable conversation patterns
- Support for stdio, HTTP, and SSE transports
An example Business A2A Agent implementing the UCP Extension.
- Agent & Client: Documentation
- Located in
a2a/. - Demonstrates agent-to-agent communication for commerce operations.
- Includes chat client for interactive testing.
- Located in
| Binding | Use Case | Transport | Best For |
|---|---|---|---|
| REST | Traditional APIs | HTTP | Web/mobile apps, service integration |
| MCP | AI Agents | stdio/HTTP/SSE | LLM integration, conversational commerce |
| A2A | Agent Communication | HTTP | Multi-agent systems, automated workflows |
Please refer to the specific README files linked above for detailed instructions on how to set up, run, and test each sample.