Why WebMCP matters: Shopify engineer makes the case for co-browsing in the agentic web
rseroter · x · 2026-10-14
Shopify engineer Yoav Weiss explains why WebMCP matters, having shipped Shopify's storefront WebMCP tools to production. OpenAI added support in ChatGPT Desktop and ran a WebMCP Challenge; Cloudflare supports it in Kitesurf and for customers. He outlines three agent-web interaction models—direct backend API calls (MCP servers), embedding web experiences in chat (MCP Apps), and co-browsing via DOM/a11y-tree and screenshots—and argues co-browsing is the only model where developers and users keep control and users can take over anytime, calling WebMCP 'Agentic WebPerf'.
More from coding & agent
- Open-source project's PRs grow exponentially after adding an auto-research.md prompt for AI contributors — IgorCarron · 2026-10-14
- NetworkChuck monitors his Hermes agents with CheckMK: model subs, cron jobs, memory health — alexcovo_eth · 2026-10-14
- One Postgres cluster, many previews: Alchemy custom resources give each PR its own database — samgoodwin89 · 2026-10-14
- Arena Fighter: a programming ladder game built for humans and AI coding agents — tristanbob · 2026-10-14
- Gusto launches multi-client MCP and AI-assisted workflows for accountants — dunkhippo33 · 2026-10-14
- Claude Code workflow: Sonnet builds, Haiku scouts, Opus reviews in parallel worktrees — Arindam_1729 · 2026-10-14