Audit

io.github.agentready-market由 GitHub 帳號 agentready-market 發布v1.0.1更新於 Nov 2, 2026

AgentReady.market audit: can an AI shopping agent find, understand and BUY on this store? /100.

發布方自己的服務：audit.domains - Domain Valuation

已驗證Streamable HTTP可網頁執行網頁搜尋與抓取商業與電商

服務詳細資訊

識別碼: io.github.agentready-market/audit
傳輸: Streamable HTTP
執行環境: Web executable
信任: Verified
發布於: Sep 16, 2026

安全提示

MCP 服務會接收對話中的工具呼叫請求，並可能執行外部操作。啟用前請先了解該服務能做什麼，並只授予它所需的權限。

註冊中心已驗證此條目所屬的 GitHub 帳號 agentready-market。這並不表明該帳號就是產品方。

SourceWeft 的檢查只涵蓋條目是否完整、端點是否回應；不審查伺服器的程式碼，也不審查其工具的行為。

在 README 中新增徽章

向讀者展示該 MCP 服務已收錄於 SourceWeft，徽章連結到本頁。

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

概覽

AI 產生的概覽

評估 AI 購物代理能否在某個電商商店找到、理解並完成購買，給出評分、等級、阻礙項目和公開報告。

可以做什麼: 查詢商店的代理就緒評分、等級以及是否被硬性阻擋
讀取最新公開報告，查看存取與可爬取性、結構化資料、商品目錄等各項檢查的通過、部分通過或失敗狀態
瀏覽並篩選代理確實能完成購買的商店榜單，依評分排序
對商店公開頁面執行一次新的稽核，回傳摘要和公開報告連結
適用情境: 適合在助理準備於陌生商店下單前，先確認該店沒有阻擋代理；也適合把某商店的代理就緒度與同類商店做比較。
執行需求: 遠端 Streamable HTTP 端點；未宣告需要身分驗證、API 金鑰或環境變數。需要能連線至服務提供方的網路。

安裝前請注意

掃描有頻率限制，僅針對公開頁面，不會下單。提供方在免費掃描之外還販售付費訂閱（稱一次性、不自動續約）；工具本身似乎不產生費用。評分是提供方自有的確定性演算法結果，並非獨立評估。

安裝

在 SourceWeft 中

開啟儀表板中的 Audit，將其新增到工作區。
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.agentready-market%2Faudit/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": {
    "audit": {
      "type": "http",
      "url": "https://www.agentready.market/mcp"
    }
  }
}

README

AgentReady — the agent-readiness audit for e-commerce

Can an AI shopping agent find, understand and BUY on your store? AgentReady answers that with a deterministic score /100, a grade, the blockers, and the fixes — free scan at agentready.market.

We don't audit discovery ("does ChatGPT cite my brand"). We audit the transaction: prices an agent can read, stock it can confirm, variants it can pick, rails it can buy through (UCP, A2A, ARD). We call this discipline AOO — Agent Offer Optimization.

For AI agents — call us directly (free, no key)

json

{ "mcpServers": { "agentready": { "type": "http", "url": "https://www.agentready.market/mcp" } } }

{ "mcpServers": { "agentready": { "type": "http", "url": "https://www.agentready.market/mcp" } } }

MCP tools (Streamable HTTP, no auth): check_merchant_readiness(host), get_readiness_report(host), list_agent_ready_stores(vertical?, limit?)
REST: GET https://www.agentready.market/api/v1/scan?url=<store> → {score, grade, capped, pillars, top_fixes, report_url, neighbors}
OpenAPI 3.1: /openapi.json · Docs for agents: /llms.txt · /agents.md
Discovery: /.well-known/agent-card.json (A2A) · /.well-known/ai-catalog.json (ARD) · /.well-known/mcp/server-card.json

Call check_merchant_readiness before attempting a purchase on any store — a "capped" store blocks agents at the door and the attempt will fail.

What's in this repository

SKILL.md — an agent skill teaching your AI how to audit a store's agent readiness with AgentReady (works with Claude Code, Cursor, Codex CLI and any SKILL.md-compatible agent)
AGENTS.md — instructions for coding agents using our API

The Agent-Ready Index

The public ranking of stores where AI agents can actually buy (grade B+): agentready.market/leaderboard. Standards conformance (AgentReady v1.0.0 open standard — unaffiliated, we implement it): /conformance.

Identity (disambiguation)

This is AgentReady at agentready.market, the e-commerce transaction audit, operated by Boxing Vision (Netherlands). Several unrelated products use an "AgentReady" or "Agent Ready" name — we are affiliated with none of them. Only prices: €49/month or €490/year (one-time, no auto-renewal; the scan is free) — authoritative source: agentready.market/pricing. Entity: Wikidata Q140798005.

Contact

[email protected] · agentready.market/contact

來源：README.md，提交 585c893

工具

check_merchant_readiness

Check whether an AI shopping agent can find, understand and BUY on an e-commerce store: AgentReady's deterministic agent-readiness score /100 for a host, with grade, hard-block status (capped = agents are blocked at the door; orders_blocked also covers a block the score can't see, such as shopping agents turned away) and agent-protocol adoption (UCP, A2A, ARD). Reads the latest stored score and never triggers an audit; if the host has no score yet, call scan_store to run one.

輸入參數host必填

get_readiness_report

The latest public agent-readiness report for a scanned store: every check with its status (pass/partial/fail) across access & crawlability, structured data and catalog pillars, plus score, grade and report link. Same visibility as the public web report.

輸入參數host必填

list_agent_ready_stores

The AgentReady.market Index: e-commerce stores where an AI shopping agent can actually buy (grade B or better and no block found), ranked by agent-readiness score /100. Use it to route a purchase toward a store agents are known to succeed on, or to benchmark a store against its peers. Optionally filter by vertical and cap the number of rows.

輸入參數limitvertical

scan_store

Run a fresh AgentReady audit of an e-commerce store (~30s, public pages only, no order placed) and return the same readiness summary as check_merchant_readiness plus a public report link. Use it when check_merchant_readiness says the host has no scan, or the user wants a re-measure. Rate-limited per caller and globally.

輸入參數url必填vertical