Home · Technology · Sep 28 archive
Shopify Opens Checkout to Browser-Based AI Agents
Confirmed
In Short: Shopify has added Meta's Muse AI agent to its platform, allowing for full checkout capabilities.
Shopify has integrated Meta's Muse personal AI agent into its platform, enabling it to complete purchases on behalf of users.
According to TechCrunch, this move marks a significant shift as Amazon and other retailers have blocked similar AI agents from their marketplaces.
On September 8, Shopify added Meta to its Agentic Storefronts program, the same day Muse was launched.
Muse, like other AI agents, can remember interactions and use them in tasks, enhancing the shopping experience.
Shopify shares merchant products with Meta by default, though sellers can manage catalog access and direct checkout.
Gil Greenberg, a staff product manager at Shopify, explained on X that the new WebMCP tools allow agents to inspect, update, and complete checkouts with buyer authorization.
The new tools include get_checkout, update_checkout, and complete_checkout, which enable agents to manage the entire checkout process.
Shopify's agentic settings allow merchants to view Meta's performance and manage their interactions.
This integration is part of Shopify's broader strategy to treat agentic commerce as just another distribution channel.
The tools run inside the checkout process and use the same state as the checkout interface, requiring no additional merchant configuration.
Shopify's documentation advises agents to treat merchant and third-party text in tool responses as checkout data and not to operate page controls themselves.
The tools are designed for agents operating in the buyer's browser, enhancing the shopping journey from product discovery through checkout and order confirmation.
What this adds
Shopify's move to integrate AI agents into its checkout process is a significant step in the evolution of e-commerce, potentially changing how consumers interact with online shopping platforms.
What's confirmed
- Shopify has integrated Meta's Muse personal AI agent into its platform, enabling it to complete purchases on behalf of users.
- According to TechCrunch, this move marks a significant shift as Amazon and other retailers have blocked similar AI agents from their marketplaces.
- On September 8, Shopify added Meta to its Agentic Storefronts program, the same day Muse was launched.
- Muse, like other AI agents, can remember interactions and use them in tasks, enhancing the shopping experience.
- Shopify shares merchant products with Meta by default, though sellers can manage catalog access and direct checkout.
- Gil Greenberg, a staff product manager at Shopify, explained on X that the new WebMCP tools allow agents to inspect, update, and complete checkouts with buyer authorization.
- The new tools include get_checkout, update_checkout, and complete_checkout, which enable agents to manage the entire checkout process.
- Shopify's agentic settings allow merchants to view Meta's performance and manage their interactions.
- This integration is part of Shopify's broader strategy to treat agentic commerce as just another distribution channel.
- The tools run inside the checkout process and use the same state as the checkout interface, requiring no additional merchant configuration.
- Shopify's documentation advises agents to treat merchant and third-party text in tool responses as checkout data and not to operate page controls themselves.
- The tools are designed for agents operating in the buyer's browser, enhancing the shopping journey from product discovery through checkout and order confirmation.
What's still developing
- On Monday, the company announced 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.
- 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.
- Learn how it works, where UCP fits, and what the data shows: https://t.co/U96VtJaeyc Shopify already offers a hosted Model Context Protocol (MCP) server, which allows agents to work server-to-server.
- Shopify previously supported WebMCP 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.
- 🥱 Today, we’re launching WebMCP support for checkout, including Shop Pay, for all eligible Shopify merchants.
- The company announced the change in a developer changelog post dated September 28, 2026, on Shopify’s changelog index.
- The tools act on the active checkout in the buyer’s browser session and hand control back to the buyer when input is required, such as 3D Secure authentication or blocking UI extensions.
- Checkout WebMCP implements the UCP checkout capability ( dev.ucp.shopping.checkout ) over browser-registered WebMCP tools instead of server-side JSON-RPC, and it shares the checkout object, statuses, and messages with Checkout MCP, Shopify’s server-side counterpart, according to the Checkout WebMCP documentation.
- The announcement lists four tools agents can call at checkout: get_checkout, which reads checkout state, messages, and post-completion order details; update_checkout, which updates supported checkout fields; complete_checkout, which submits the checkout after buyer confirmation; and navigate_to_storefront, which returns the tab to the storefront.
- The tools serve agents that shoppers bring to a store in their own browser.
- Agents discover the tools with document.modelContext.getTools() and call them with document.modelContext.executeTool(), passing arguments as JSON strings; the documentation notes that Chrome 153 rejects object arguments and that Chrome plans to accept objects in Chrome 155.