ubras-storefront
Ubras's international Shopify storefront (ubras.com) exposes two live, provider-published MCP surfaces. (1) The Shopify storefront MCP at https://ubras.com/api/mcp answers JSON-RPC tools/list unauthenticated — the five tools below were captured verbatim from that live response on 2026-07-21. (2) The Universal Commerce Protocol (UCP) shopping service MCP at https://ubras.com/api/ucp/mcp (canonical endpoint https://ubrasofficial.myshopify.com/api/ucp/mcp per the /.well-known/ucp merchant profile), documented in /agents.md and /llms.txt; it requires a UCP agent profile in the request meta (an anonymous tools/list returns JSON-RPC error -32001 "UCP discovery failed: Missing profile uri"). Checkout requires explicit buyer approval per the store's published agent rules.
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.
Endpoint
Hosted endpoint · transport http
Connect
This is a remote MCP server — point an MCP client at the endpoint URL. Clients with native remote support (Claude, Cursor, VS Code, …):
For stdio-only clients (older Claude Desktop, etc.), bridge with mcp-remote:
If the server requires authentication, add the provider's token/header (e.g. an X-API-Key) per its docs. A quick reachability check:
Tools
search_catalog— Search for products from the online store, hosted on Shopify. Natural language queries and/or filter criteria; paginated (UCP dev.ucp.shopping.catalog.search capability).get_cart— Get the cart including items, shipping options, discount info, and checkout url for a given cart id.update_cart— Perform updates to a cart, including adding/removing/updating line items, buyer information, shipping details, discount codes, gift cards and notes.search_shop_policies_and_faqs— Used to get facts about the stores policies, products, or services.get_product_details— Look up a product by ID. Pass the 'options' parameter to select a specific variant for the product card.
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.