WebMCP Demo Store

io.github.kamatanuj由 GitHub 账号 kamatanuj 发布v1.0.0更新于 Nov 1, 2026

WebMCP demo store: same catalog via MCP tool calls vs DOM scraping. -79% bytes, -42% tokens.

发布方自己的服务：demo.st

已验证Streamable HTTP可网页运行网页搜索与抓取商业与电商

服务详情

标识符: io.github.kamatanuj/webmcp-store
传输: Streamable HTTP
运行时: Web executable
信任: Verified
发布于: Oct 18, 2026

安全提示

MCP 服务会接收对话中的工具调用请求，并可能执行外部操作。启用前请先了解该服务能做什么，并只授予它所需的权限。

注册中心已验证此条目所属的 GitHub 账号 kamatanuj。这并不表明该账号就是产品方。

SourceWeft 的检查只涵盖条目是否完整、端点是否响应；不审查服务器的代码，也不审查其工具的行为。

在 README 中添加徽章

向读者展示该 MCP 服务已收录于 SourceWeft，徽章链接到本页。

[![Listed on SourceWeft](https://sourceweft.com/badge/mcp/io.github.kamatanuj%2Fwebmcp-store.svg)](https://sourceweft.com/mcp/io.github.kamatanuj%2Fwebmcp-store?utm_source=readme&utm_medium=badge)

概览

AI 生成的概览

一个以 MCP 工具形式提供的演示网店，让助手无需抓取 HTML 即可搜索商品目录、管理购物车并下单。

可以做什么: 按分类、最高价格、最低评分或品牌子串搜索商品目录
按商品 id 查看单个商品的完整详情
将商品加入购物车，并查看当前购物车内容与合计金额
为当前购物车下单并返回订单号
适用场景: 适合试用或演示通过 MCP 进行的智能体购物流程，或在同一目录上对比工具调用与 DOM 抓取的效果。它是演示商店，并非真实商家。
运行要求: 需要一个远程 streamable HTTP 端点；未声明认证、环境变量或请求头。README 还说明可在本地以普通模式或 MCP 模式运行自带的 Python 服务器，仅依赖 Python 标准库。

安装前请注意

结账会实际下单并返回订单号，因此演示服务器上的购物车与订单状态会改变，应把订单视为测试数据。README 提到该演示已产生真实订单号，且目录为固定的演示商品集，并非实时库存。

安装

在 SourceWeft 中

打开控制台中的 WebMCP Demo Store，将其添加到工作区。
为需要使用其工具的对话启用该服务。

Web executable，通过 Streamable HTTP。远程服务在工作区中配置后即可从网页运行时运行。

交给智能体安装

把这段提示词粘贴到 Claude Code、Codex、Cursor 等智能体，或 SourceWeft 对话中。智能体会读取该服务器的安装指南，先向你展示发布者、端点和登录方式，经你同意后再把它添加到你的客户端。密钥不会写进任何命令。

阅读 https://sourceweft.com/mcp/io.github.kamatanuj%2Fwebmcp-store/install.md，并按其中说明把这个 MCP 服务器接入我的客户端。修改任何配置之前，先告诉我它的发布者、端点和登录方式，等我确认。不要把 API 密钥写进命令或我会提交的文件；问我密钥应从哪里获取。

查看智能体所依据的安装指南

其他 MCP 客户端

把它添加到你客户端的 mcpServers 配置中。

{
  "mcpServers": {
    "webmcp-demo-store": {
      "type": "http",
      "url": "https://demowithmcp.converso.work/mcp"
    }
  }
}

README

WebMCP Demo Store — one-file server, two modes, one benchmark

[Listed on mcpservers.org]

Same store, same tools, two delivery modes:

WebMCP mode — the page exposes its catalog through MCP tool calls (MCP-over-HTTP /mcp, plus Chrome-native document.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

bash

python3 server.py                    # plain mode      → http://localhost:9501MCP=1 PORT=9502 python3 server.py    # WebMCP mode     → http://localhost:9502 + /mcp

python3 server.py                    # plain mode      → http://localhost:9501MCP=1 PORT=9502 python3 server.py    # WebMCP mode     → http://localhost:9502 + /mcp

stdlib-only (http.server, json, uuid, threading) — no pip install, no dependencies.

Live demos

plain: https://demonomcp.converso.work
WebMCP: https://demowithmcp.converso.work (.well-known/mcp discovery, /mcp endpoint)
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:
1. 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.
2. Tools can't be re-registered under the same name (InvalidStateError) — reload the page to reset.
3. Flag/feature name: --enable-features=WebMCP works headless; docs' chrome://flags/#enable-webmcp-testing is the manual path. Note: API is document.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
`server.py`	the whole thing: store + cart + orders + MCP transport (`MCP=1`) + static/report serving
`catalog.json` / `catalog_10.json`	150-product / 10-product demo catalogs
`compare.py`, `compare_llm.py`, `browser_llm.py`	benchmark harnesses (DOM-mode agent, LLM-token accounting, browser-native flow)
`make_report.py`	regenerates the HTML/PDF reports from `results.json` / `agg_150_vs_30.json`
`whitepaper.html`, `report.html`, `.pdf`, `chart_*.png`	strategy + evidence artifacts (launch deck included)
`weekly_recap.py`	counters + live-URL digest (used by the ops cron)