PRIME Storefront UCP Shopping MCP Server
One-click install for Cursor, VS Code, Claude, and 20+ other MCP clients, powered by API Commons MCP Install — visit install.apicommons.org for more information.
Descriptor
Candidate descriptor · transport streamable-http (JSON-RPC 2.0 over POST; Accept application/json, text/event-stream)
Tools
search_catalog— Search for products from the online store, hosted on Shopify. Natural-language query, filters, or both; at least one required. Paginated via pagination.cursor. Response conforms to dev.ucp.shopping.catalog.search.lookup_catalog— Look up multiple products or variants by identifier.get_product— Retrieve complete product detail by identifier. Returns a singular product.create_cart— Creates a new cart.get_cart— Get the cart contents.update_cart— Perform updates to a cart.cancel_cart— Cancels a cart.create_checkout— Creates a checkout. Returns checkout details, including line items, totals, and any applicable discounts or taxes.get_checkout— Returns details about the checkout, including line items, totals, and any applicable discounts or taxes.update_checkout— Updates a checkout (shipping address, shipping method, buyer details).complete_checkout— Completes a checkout and returns the checkout result, including order ID, Thank You Page URL, or any errors encountered. Requires meta.idempotency-key AND contemporaneous buyer approval of payment.cancel_checkout— Cancels a checkout.get_order— Get the details of an order.
About MCP
The Model Context Protocol (MCP) is an open protocol Anthropic introduced for connecting LLM-based agents to external tools and data sources. Providers publish MCP servers that expose their API surface as structured, discoverable tools — an MCP-compatible client (Claude Desktop, Cursor, Cline, Continue, etc.) can connect to the server and call its tools without any per-provider integration code.
Browse every MCP server on the APIs.io network or compare with the broader Agent Skill surfaces of the same providers.
Work with this as data
Every MCP server here is available over the APIs.io API and to AI agents over MCP.