AI Storefront Readiness Grader

io.github.theharrisontruong-web由 GitHub 账号 theharrisontruong-web 发布v1.0.0更新于 Oct 24, 2026

Grades any storefront URL A-F on 20 weighted conversion checks. $1.00/call via x402.

已验证Streamable HTTP可网页运行网页搜索与抓取商业与电商

概览

AI 生成的概览

一个远程 MCP 服务器，按 20 项加权 AI 代理购物就绪度检查为电商店铺网址评级 A–F，并返回未通过的检查项。

可以做什么
审计店铺：由服务器端抓取指定网址，运行 20 项加权检查，涵盖商品信息（schema.org Product/Offer 的价格、库存、变体、GTIN/MPN）、AI 可发现性（robots.txt、llms.txt、agents.md、sitemap.xml、UCP 清单、MCP 端点）以及结账摩擦、信任信号、移动端适配和商品陈列完整性等转化就绪度，最后返回 A–F 评级和未通过的检查项。
适用场景
适合快速、自动地判断一个店铺对 AI 代理是否可读、可购，或在修复转化与可发现性问题前后做对比检查。它只是一次性付费审计调用，不是持续监控服务。
运行要求
远程 MCP 端点，无需账号或 API 密钥。每次调用通过 x402 协议在 Base 主网以 USDC 支付 1.00 美元：首次调用返回 HTTP 402 及付款信息，需用 x402 客户端付款后携带凭证重试。需要能访问该端点的网络。
安装前请注意
每次调用都会花费真实资金（Base 主网 1.00 美元 USDC），且付款即唯一认证，代理若重试可能重复付费。服务器会在服务端抓取你提供的网址，只提交你有权扫描的店铺。款项经外部 facilitator 支付给第三方收款地址。

安装

在 SourceWeft 中

  1. 打开 控制台中的 AI Storefront Readiness Grader，将其添加到工作区。
  2. 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.theharrisontruong-web%2Fstorefront-grader/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": {
    "ai-storefront-readiness-grader": {
      "type": "http",
      "url": "https://grader-al6bxcngia-ue.a.run.app/mcp"
    }
  }
}

README

Paid Agent APIs

Pay-per-call MCP APIs for AI agents. Every call is settled in USDC via the x402 protocol on Base — no accounts, no API keys, no subscriptions. Payment is the auth: your agent pays per call and gets the result.

Operated by Harrison Truong · Contact: [email protected]

Products

ServiceWhat it doesMCP toolPriceStatus
AI Storefront Readiness GraderGrades any storefront URL A–F across 20 weighted conversion-readiness checks (checkout friction, trust signals, mobile readiness, merchandising completeness) and returns the failing checksgrade_storefront$1.00 / call✅ LIVE
GEO AuditScores any URL's visibility to AI search engines (ChatGPT, Perplexity, Claude, Google AI Overviews) across 20 weighted checks and returns concrete fixes. Free tier: audit_geo_lite, rate-limitedaudit_geo$1.50 / call✅ LIVE
A11y AuditAccessibility lawsuit-risk scan: 20 weighted WCAG checks plus a lawsuit-risk level, framed as risk reduction for US businesses. Automated triage, not a certificationaudit_a11y$1.50 / callCode complete — deploys with the next release
Feed AuditProduct-feed hygiene audit: flags the feed errors that get listings disapproved or suppressed before they cost sales—$1.00 / callCode complete — deploys with the next release

Live endpoints

ServiceMCP endpointHTTP endpoint
Storefront GraderPOST https://grader-al6bxcngia-ue.a.run.app/mcpPOST https://grader-al6bxcngia-ue.a.run.app/grade
GEO AuditPOST https://geo-al6bxcngia-ue.a.run.app/mcpPOST https://geo-al6bxcngia-ue.a.run.app/geo · free: POST /geo-lite

Both take { "url": "https://your-site.example" }. Source for every service lives in this repo (grader/, geo/, a11y/).

Add either live service to any MCP client as a remote server:

json
{  "mcpServers": {    "storefront-grader": { "url": "https://grader-al6bxcngia-ue.a.run.app/mcp" },    "geo-audit": { "url": "https://geo-al6bxcngia-ue.a.run.app/mcp" }  }}

For agents: how payment works

  1. Call the tool or endpoint without payment → you get an HTTP 402 with the full payment requirements (amount, network, pay-to address).
  2. Pay in USDC on Base mainnet (eip155:8453) with any x402 client (@x402/fetch, the x402 Python package, CDP or PayAI wrappers) and retry with the payment proof.
  3. The call runs and returns the result. No signup, no key management, no invoice.

Discovery documents (/.well-known/x402):

Both services also declare the Bazaar discovery extension (extensions.bazaar) in their 402 responses, so catalog crawlers can index the paid routes from the 402 alone.

Payment terms: x402 exact scheme · asset USDC (0x833589fCD6eDb6E08f4c7C32D4f71b54bdA02913) · pay to 0xd702C8A8Ee30F6950A2a663010d12FC195D5348e · facilitator PayAI (https://facilitator.payai.network), with Coinbase CDP facilitator support built in.

Listed on

Registry metadata in this repo

  • server.json — Official MCP Registry manifest for the Storefront Grader (remote).
  • server-geo.json — Official MCP Registry manifest for GEO Audit (remote).
  • server-a11y.json — Official MCP Registry manifest for A11y Audit (publishes on deploy).
  • glama.json — Glama maintainer claim for this repository.

License

MIT — see LICENSE. The license covers this documentation/metadata repo; the hosted services themselves are pay-per-call as described above.

来源：README.md，提交 b566a56

工具

1

grade_storefront

Audit an ecommerce storefront for AI-agent shopping readiness. Fetches the store server-side and runs 20 weighted checks across product intelligence (schema.org Product/Offer price, availability, variants, GTIN/MPN), AI discovery (robots.txt, llms.txt, agents.md, sitemap.xml, UCP manifest, MCP endpoint), conversation readiness (contact info, FAQ/returns, site search), transaction readiness (HTTPS, checkout signals, tax/shipping as values), and trust (business identity, policies). Returns a machine-readable JSON report: 0-100 score, A-F grade, per-check pass/partial/fail/unknown with evidence, and the top 3 prioritized fixes. Cost: $1.00 USDC on Base per call, paid via x402 — the caller's agent pays from its owner's approved wallet; no API key needed. Use this to decide whether a store is ready for AI shopping agents, or to generate the audit behind a readiness report for a merchant.

输入参数url必填

版本历史

1
  1. v1.0.0最新Oct 16, 2026

评分

已满足适用检查项的 100%

该评分衡量此收录条目的完整程度，依据注册中心条目、端点与公开来源计算得出。它不是对服务器本身的评价，也不表示服务器安全或当前可用：可连通性是带日期的检查结果，评分也不包含安装量或用户评价。

  • 近 30 天内可连通必需25 分
  • 已声明认证方式必需10 分
  • 已列出工具必需15 分
  • 描述必需15 分
  • 图标10 分
  • 文档15 分
  • 许可证10 分