How do I install the Ucp Checkout MCP skill?

Run npx skillmds@latest add orcaqubits/ucp-checkout-mcp in your terminal (requires Node.js), paste this page's agent-chat prompt into Claude, Cursor, or any MCP-connected agent, or download the SKILL.md file and copy it into your agent's skills directory.

Is Ucp Checkout MCP safe to use?

This skill has not completed SkillMD's automated safety review yet. Capability flags: makes network calls. SkillMD never runs a skill's scripts for you; review the SKILL.md before installing.

Which AI agents work with Ucp Checkout MCP?

This skill is tagged as working with Claude Code, Claude.ai, OpenAI Codex. SKILL.md is an open format, so most agents that read a skills directory can load it too.

Is Ucp Checkout MCP free to use?

Yes. Installing skills from SkillMD is free, and the skill stays under its author's original license.

Who published Ucp Checkout MCP?

OrcaQubits (@orcaqubits) published this skill. Their other Agent Skills are listed on their SkillMD profile.

Ucp Checkout MCP by orcaqubits — Agent Skill

Name: Ucp Checkout MCP
Rating: 4.2 (5 reviews)
Author: OrcaQubits

Ucp Checkout MCP

Implement UCP Checkout over the MCP (Model Context Protocol) binding — expose checkout operations as MCP tools for AI agents. Use when building an MCP server that AI agents like Claude or Gemini can call for commerce, or when integrating with Shopify's MCP endpoint.

OrcaQubits Updated Sep 10, 2026

File contents

UCP Checkout — MCP Binding

Before writing code

Fetch live spec: Web-search site:ucp.dev specification checkout-mcp and fetch the page for exact tool definitions, JSON-RPC envelope format, and _meta requirements.

For Shopify's production MCP server, fetch https://shopify.dev/docs/agents/checkout/mcp for auth flow and endpoint details.

Conceptual Architecture

How MCP Maps to UCP

UCP over MCP is a 1:1 mapping of checkout operations to MCP tools using JSON-RPC 2.0. The same data model as REST, different envelope.

Five MCP Tools

MCP Tool Name	Maps To	Key Inputs
`create_checkout`	POST /checkout-sessions	checkout object + idempotency_key
`get_checkout`	GET /checkout-sessions/{id}	id
`update_checkout`	PUT /checkout-sessions/{id}	id + checkout object
`complete_checkout`	POST .../complete	id + payment_data + idempotency_key
`cancel_checkout`	POST .../cancel	id + idempotency_key

Meta Requirements

Every MCP tool call MUST include _meta.ucp.profile pointing to the platform's UCP profile URI. This replaces the UCP-Agent HTTP header from the REST binding.

Error Mapping

UCP errors embed inside JSON-RPC 2.0 error responses:

JSON-RPC error.code: -32603 (Internal Error)
JSON-RPC error.data: Contains an errors[] array, where each error has code, message, severity, and details fields

When to Use MCP Binding

You're building a merchant MCP server that AI agents (Claude, Gemini, etc.) call via tool use
You're integrating with an existing MCP server (e.g., Shopify's)
You want AI agents to autonomously browse and purchase without REST client code

Implementation Guidance

Building a Business MCP Server:

Implement the 5 tools using your MCP framework (e.g., @modelcontextprotocol/sdk for Node, mcp for Python)
Extract _meta.ucp.profile from every tool call for negotiation
Return checkout objects as JSON in the MCP tool result
Return errors using JSON-RPC error format with UCP data payload
Implement idempotency on create and complete tools

Connecting to an existing MCP server (e.g., Shopify):

Authenticate (Shopify uses OAuth2 client_credentials for access tokens)
Connect to the MCP endpoint
Call tools with proper _meta.ucp.profile and checkout payloads
Parse tool results for checkout status and messages

Shopify MCP Integration

Shopify provides a production MCP server for UCP checkout. Before implementing:

Fetch https://shopify.dev/docs/agents/checkout/mcp for the latest auth flow, endpoint URL format, and error codes
Authentication uses POST https://api.shopify.com/auth/access_token with client credentials
MCP endpoint is POST https://{shop-domain}/api/ucp/mcp

---name: ucp-checkout-mcpdescription: Implement UCP Checkout over the MCP (Model Context Protocol) binding — expose checkout operations as MCP tools for AI agents. Use when building an MCP server that AI agents like Claude or Gemini can call for commerce, or when integrating with Shopify's MCP endpoint.---# UCP Checkout — MCP Binding## Before writing code**Fetch live spec**: Web-search `site:ucp.dev specification checkout-mcp` and fetch the page for exact tool definitions, JSON-RPC envelope format, and `_meta` requirements.For Shopify's production MCP server, fetch https://shopify.dev/docs/agents/checkout/mcp for auth flow and endpoint details.## Conceptual Architecture### How MCP Maps to UCPUCP over MCP is a **1:1 mapping** of checkout operations to MCP tools using JSON-RPC 2.0. The same data model as REST, different envelope.### Five MCP Tools| MCP Tool Name | Maps To | Key Inputs ||---------------|---------|------------|| `create_checkout` | POST /checkout-sessions | checkout object + idempotency_key || `get_checkout` | GET /checkout-sessions/{id} | id || `update_checkout` | PUT /checkout-sessions/{id} | id + checkout object || `complete_checkout` | POST .../complete | id + payment_data + idempotency_key || `cancel_checkout` | POST .../cancel | id + idempotency_key |### Meta RequirementsEvery MCP tool call MUST include `_meta.ucp.profile` pointing to the platform's UCP profile URI. This replaces the `UCP-Agent` HTTP header from the REST binding.### Error MappingUCP errors embed inside JSON-RPC 2.0 error responses:- JSON-RPC `error.code`: `-32603` (Internal Error)- JSON-RPC `error.data`: Contains an `errors[]` array, where each error has `code`, `message`, `severity`, and `details` fields### When to Use MCP Binding- You're building a **merchant MCP server** that AI agents (Claude, Gemini, etc.) call via tool use- You're integrating with an existing MCP server (e.g., Shopify's)- You want AI agents to autonomously browse and purchase without REST client code### Implementation Guidance**Building a Business MCP Server:**1. Implement the 5 tools using your MCP framework (e.g., `@modelcontextprotocol/sdk` for Node, `mcp` for Python)2. Extract `_meta.ucp.profile` from every tool call for negotiation3. Return checkout objects as JSON in the MCP tool result4. Return errors using JSON-RPC error format with UCP data payload5. Implement idempotency on create and complete tools**Connecting to an existing MCP server (e.g., Shopify):**1. Authenticate (Shopify uses OAuth2 client_credentials for access tokens)2. Connect to the MCP endpoint3. Call tools with proper `_meta.ucp.profile` and checkout payloads4. Parse tool results for checkout status and messages### Shopify MCP IntegrationShopify provides a production MCP server for UCP checkout. Before implementing:- Fetch https://shopify.dev/docs/agents/checkout/mcp for the latest auth flow, endpoint URL format, and error codes- Authentication uses `POST https://api.shopify.com/auth/access_token` with client credentials- MCP endpoint is `POST https://{shop-domain}/api/ucp/mcp`

Frequently asked questions