Shopify opens checkout to browser-based AI agents Shopify announced Monday that browser-based AI agents can now complete purchases on Shopify merchants' sites, extending agent capabilities beyond product search and cart-building to checkout, including Shop Pay. The update adds three WebMCP tools — get_checkout, update_checkout, and complete_checkout — that let agents read and modify a checkout screen and place an order after buyer authorization, without screenshots or webpage scraping, according to Gil Greenberg, a staff product manager working on agentic commerce at Shopify. The feature is rolling out to all eligible Shopify merchants, and Shopify said top AI agents Muse and Instinct already hold direct agentic-commerce partnerships with the platform. While some retailers, like Amazon https://www.bloomberg.com/news/articles/2026-09-21/amazon-blocks-meta-s-muse-ai-agent-from-its-retail-site and Adidas https://x.com/kesslerIO/status/2104397316673462339 , apparently , are blocking https://x.com/kesslerIO/status/2104397316673462339 AI agents from making purchases on users’ behalf on their respective platforms, e-commerce platform Shopify has moved in the other direction. On Monday, the company announced https://x.com/gilgNYC/status/2104583942728822998 that browser-based AI agents can now complete purchases on Shopify merchants’ sites, extending their capabilities beyond just searching for products and adding items to carts. Shopify previously supported WebMCP https://shopify.dev/docs/api/web-mcp for its storefronts and carts, allowing browser-based AI agents to comb through a Shopify retailer’s inventory, search for products, and add them to a cart. The addition of WebMCP support for checkout, including Shop Pay, means these agents can now read the checkout screen, update it, and submit the transaction with the buyer’s authorization, without relying on screenshots or scraping webpages, the company said. This update introduces three new tools — get checkout, update checkout, and complete checkout — that allow agents to inspect a checkout, change things like the customer’s address or delivery option, and then place an order after the buyer authorizes it. The feature is rolling out to all eligible Shopify merchants, said Gil Greenberg https://www.linkedin.com/in/gilgreenberg/ , a staff product manager who works on agentic commerce at Shopify, in a post on X https://x.com/gilgNYC/status/2104583942728822998 . Shopify already offers a hosted Model Context Protocol MCP https://modelcontextprotocol.io/docs/2026-07-28/getting-started/intro server, which allows agents to work server-to-server. The proposed standard WebMCP https://shopify.dev/docs/api/web-mcp , meanwhile, is designed for agents that work inside the buyer’s browser. Both leverage Shopify’s Universal Commerce Protocol https://www.shopify.com/ucp UCP , which provides a common way to search for and discover products, build carts, and check out. Top AI agents like Muse https://www.wsj.com/tech/shopify-to-use-metas-muse-for-agentic-checkout-d23947c0 and Instinct https://x.com/noahrshinn/status/2104628465488306183 already have direct partnerships with Shopify for agentic commerce. The Instinct partnership was announced https://x.com/noahrshinn/status/2104628465488306183 today. “If your agent is operating in the buyer’s browser, use WebMCP tools provided on storefront and checkout to efficiently complete order placement, instead of navigating HTML built for humans,” Greenberg wrote on X. “These WebMCP tools provide structured and efficient APIs, purposely designed — via UCP — to ensure accurate commerce facts, required disclosures, and handoff requirements.”