WebMCP
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@WebMCPsearch for a 4K monitor and add it to my cart"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
WebMCP Demo Store — one-file server, two modes, one benchmark
Same store, same tools, two delivery modes:
WebMCP mode — the page exposes its catalog through MCP tool calls (MCP-over-HTTP
/mcp, plus Chrome-nativedocument.modelContext), so an agent reads only what the task needs.Plain mode — the same store as an ordinary website; the agent parses full HTML pages, as every agent must today.
Benchmark (150-product catalog, identical tasks): 79% less action bytes, 42% fewer input tokens, 8/8 tasks correct in both modes. DOM mode wins on small catalogs then collapses; WebMCP wins with age. Crossover report: report.html → WebMCP_Comparison_Report.pdf.
Run it
python3 server.py # plain mode → http://localhost:9501
MCP=1 PORT=9502 python3 server.py # WebMCP mode → http://localhost:9502 + /mcpstdlib-only (http.server, json, uuid, threading) — no pip install, no dependencies.
Related MCP server: Commerce MCP Server
Live demos
WebMCP: https://demowithmcp.converso.work (
.well-known/mcpdiscovery,/mcpendpoint)launch package (deck, whitepaper, reports): https://demowithmcp.converso.work/launch.html
Chrome-native WebMCP test (13 Oct 2026)
Chrome 154 + --enable-features=WebMCP exposes document.modelContext on HTTPS origins (about:blank excluded).
Registered the 5-tool store contract via the IMPERATIVE API (
registerTool): search_products, add_to_cart, get_cart, checkout (server-backed; all fetches in-page).Standard client flow verified:
getTools()discovery →executeTool()calls → orders 1017/1018 placed, T2/T4/T8 picks correct (HP Pavilion 14, Razer DeathAdder, OnePlus 12R).154 build quirks found & worked around:
executeTool(tool, args)requires args as a JSON string (object form throws "Failed to parse input arguments"); return values are JSON strings too — JSON.parse both sides.Tools can't be re-registered under the same name (InvalidStateError) — reload the page to reset.
Flag/feature name:
--enable-features=WebMCPworks headless; docs'chrome://flags/#enable-webmcp-testingis the manual path. Note: API isdocument.modelContext(moved from navigator since July 2026 build).
Takeaway: the demo's tool contract is compatible with Chrome's native WebMCP, not just our JSON-RPC shim. When Chrome ships the client agent (Gemini-in-Chrome), the store is already agent-ready.
Repo layout
path | what |
| the whole thing: store + cart + orders + MCP transport ( |
| 150-product / 10-product demo catalogs |
| benchmark harnesses (DOM-mode agent, LLM-token accounting, browser-native flow) |
| regenerates the HTML/PDF reports from |
| strategy + evidence artifacts (launch deck included) |
| counters + live-URL digest (used by the ops cron) |
License
MIT.
This server cannot be deployed
Maintenance
Related MCP Connectors
Hosted MCP for e-commerce: live product catalog, stock, and pricing for AI agents.
AI-agent product catalog: search, lookup & purchase routing over verified merchant data.
Merchant product catalogs for AI agents: price, availability, specs, variants, buy links. Read-only.
Agent-native commerce with trusted catalog, durable carts, and Stripe Checkout via MCP and UCP.
Related MCP Servers
- AlicenseAqualityDmaintenanceA UCP-compliant MCP storefront server that exposes product catalog operations (search, cart, checkout) as MCP tools, following UCP schema version 2026-04-08.5MIT
- FlicenseNot gradedqualityDmaintenanceEnables AI agents to browse product catalogs, search products with filters, and initiate checkouts, generating order summaries and checkout URLs.-
- AlicenseAqualityCmaintenanceEnables AI agents to query tenants, browse catalogue items with pricing, pull recent orders, and add products through the MCP tool-calling interface.4MIT

Unwrangle MCPofficial
AlicenseNot gradedqualityBmaintenanceEnables AI agents to retrieve product details, customer reviews, and search results from retailers like Amazon, Target, Best Buy, Home Depot, and Walmart through a unified MCP interface.10 npmMIT