walabot-storefront-ucp
Vayyar's Walabot DIY storefront (walabot.com, a Shopify store) operates a live agent-commerce MCP endpoint as part of its Universal Commerce Protocol (UCP) implementation. The UCP merchant profile at https://walabot.com/.well-known/ucp (saved at well-known/vayyar-imaging-ucp.json) declares the dev.ucp.shopping service with an MCP transport at https://walabot2.myshopify.com/api/ucp/mcp, fronted on the merchant domain as https://walabot.com/api/ucp/mcp. The endpoint was probed live on 2026-07-21: it answers JSON-RPC (tools/list returned a -32001 "UCP discovery failed / Missing profile uri" error, meaning it requires a UCP agent-profile handshake before listing tools). The tool list below is captured verbatim from the store's published /llms.txt agent instructions, not invented. This is a Shopify-operated commerce surface for the Walabot store, not an API over Vayyar's radar-sensor products.
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— Find products matching the buyer's intent (documented in /llms.txt)create_cart— Add desired items to a cart (documented in /llms.txt)create_checkout— Start the purchase flow (documented in /llms.txt)update_checkout— Set shipping address and method (documented in /llms.txt)complete_checkout— Finalize the purchase; buyer must approve payment (documented in /llms.txt)
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.