AI Storefront Readiness Grader

io.github.theharrisontruong-web由 GitHub 帳號 theharrisontruong-web 發布v1.0.0更新於 Oct 24, 2026

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

已驗證Streamable HTTP可網頁執行網頁搜尋與抓取商業與電商

概覽

AI 產生的概覽

一個遠端 MCP 伺服器，依 20 項加權 AI 代理購物就緒度檢查，為電商店面網址評分 A–F，並回傳未通過的檢查項目。

可以做什麼
稽核店面：由伺服器端抓取指定網址，執行 20 項加權檢查，涵蓋商品資訊（schema.org Product/Offer 的價格、庫存、變體、GTIN/MPN）、AI 可探索性（robots.txt、llms.txt、agents.md、sitemap.xml、UCP 清單、MCP 端點），以及結帳摩擦、信任訊號、行動裝置相容性和商品陳列完整度等轉換就緒度，最後回傳 A–F 評分與未通過的檢查項目。
適用情境
適合快速、自動判斷一個店面對 AI 代理是否可讀、可購買，或在修正轉換與可探索性問題前後做對照檢查。它只是一次性付費稽核呼叫，並非持續監控服務。
執行需求
遠端 MCP 端點，不需帳號或 API 金鑰。每次呼叫透過 x402 協定在 Base 主網以 USDC 支付 1.00 美元：首次呼叫會回傳 HTTP 402 與付款資訊，需以 x402 用戶端付款後帶憑證重試。需要能連線至該端點的網路。
安裝前請注意
每次呼叫都會花費真實金錢（Base 主網 1.00 美元 USDC），且付款即為唯一驗證，代理若重試可能重複付費。伺服器會在伺服器端抓取你提供的網址，只提交你有權掃描的店面。款項經外部 facilitator 支付給第三方收款地址。

安裝

在 SourceWeft 中

  1. 開啟 儀表板中的 AI Storefront Readiness Grader，將其新增到工作區。
  2. 為需要使用其工具的對話啟用該服務。

Web executable，透過 Streamable HTTP。 遠端服務在工作區中設定後即可從網頁執行環境執行。

交給代理程式安裝

把這段提示詞貼上到 Claude Code、Codex、Cursor 等代理程式，或 SourceWeft 對話中。代理程式會讀取該伺服器的安裝指南，先向你展示發布者、端點和登入方式，經你同意後再把它新增到你的客戶端。金鑰不會寫進任何命令。

閱讀 https://sourceweft.com/mcp/io.github.theharrisontruong-web%2Fstorefront-grader/install.md，並按其中說明把這個 MCP 伺服器接入我的客戶端。修改任何設定之前，先告訴我它的發布者、端點和登入方式，等我確認。不要把 API 金鑰寫進命令或我會提交的檔案；問我金鑰應從哪裡取得。

檢視代理程式所依據的安裝指南

其他 MCP 客戶端

把它新增到你客戶端的 mcpServers 設定中。

{
  "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.

來源：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.

輸入參數url必填

版本歷史

1
  1. v1.0.0最新Oct 16, 2026

評分

已滿足適用檢查項的 100%

該評分衡量此收錄條目的完整程度，依據註冊中心條目、端點與公開來源計算得出。它不是對伺服器本身的評價，也不表示伺服器安全或目前可用：可連通性是帶日期的檢查結果，評分也不包含安裝量或使用者評價。

  • 近 30 天內可連通必需25 分
  • 已宣告認證方式必需10 分
  • 已列出工具必需15 分
  • 描述必需15 分
  • 圖示10 分
  • 文件15 分
  • 授權條款10 分