ListingGood MCP

io.github.ryanyang828由 GitHub 帳號 ryanyang828 發布v1.0.0更新於 Oct 24, 2026

Get recommended by Amazon's AI. Hosted MCP server for Amazon listing compliance & generation.

已驗證Streamable HTTP可網頁執行效率與工作流商業與電商

概覽

AI 產生的概覽

託管型 MCP 伺服器，為 Amazon 商品 listing 評分、稽核並生成文案，涵蓋 AI 推薦就緒度、合規與申訴。

可以做什麼
評估 listing 的 AI 推薦就緒度與 Agent 就緒度，並提供排序後的改善建議（免費檢查）。執行快速合規預檢，或基於知識庫的深度合規稽核並產出書面報告。依站點生成 A9 最佳化的標題、要點與描述，或把一句話產品描述擴充為結構化欄位。依 Amazon 違規通知起草行動計畫（POA），並分析負評的根本原因與回覆角度。
適用情境
適合 Amazon 賣家與代操團隊：在發布前確認 listing 是否易被機器讀取且合規、生成或在地化 listing 文案，或處理下架與負評。
執行需求
遠端 Streamable HTTP 端點，無需本機安裝。需要服務商開發者頁面提供的 API key，以 apikey 查詢參數放在端點 URL 中。兩項免費檢查（AI 就緒度、Agent 就緒度）據稱不需 API key。付費工具需要點數。
安裝前請注意
多個工具會消耗點數：深度合規掃描 2 點、listing 生成每站點 1 點、行動計畫 4 點、負評分析 2 點。API key 透過 URL 查詢字串傳遞，可能出現在用戶端設定與日誌中。listing 文案、違規通知與評論會傳送到服務商的託管服務。生成的 listing 與申訴稿需人工審閱後再提交。

安裝

在 SourceWeft 中

  1. 開啟 儀表板中的 ListingGood MCP，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.ryanyang828%2Flistinggood/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": {
    "listinggood": {
      "type": "http",
      "url": "https://listinggood.com/mcp"
    }
  }
}

README

ListingGood — AI Recommendation Engine (Skills + MCP)

Make AI recommend your products. ListingGood is the engine that helps Amazon's AI — Rufus, COSMO, and agentic shopping agents — find, trust, and recommend your listings. It does this through three things: compliance, AI writing, and appeal rescue.

[Website] [MCP] [Free check]

Installation

ListingGood runs as a hosted, remote Streamable HTTP MCP server — there is nothing to install locally. Just point your MCP client at the endpoint with your API key.

Endpoint:

https://listinggood.com/mcp?apikey=YOUR_API_KEY

Get your free API key at listinggood.com/developers (signup grants 10 permanent stars).

Claude Desktop / Cursor / VS Code / Windsurf / Cline

json
{  "mcpServers": {    "listinggood": {      "type": "streamable-http",      "url": "https://listinggood.com/mcp?apikey=YOUR_API_KEY"    }  }}

No Docker build, no npx command, no local Python runtime — the API key is passed as a URL query parameter (?apikey=...) exactly as shown above.

Why this exists

Amazon's discovery front-door has moved to AI. A listing that is not machine-readable and compliance-clean is far less likely to be cited inside Rufus answers, COSMO-driven recommendations, or agentic buying flows. Traditional seller tools tell you what to sell — they don't tell you whether your listing will be recommended.

ListingGood closes that gap:

  • Compliance pre-check — flags risky claims and category issues before you publish (free, no login).
  • AI readability — scores how well Amazon's AI surfaces can parse and cite your listing.
  • AI writing — generates compliant titles, bullets, and descriptions.
  • Appeal rescue — drafts a Plan of Action (POA) when a listing is suppressed.

The combined result is an AI Recommendation Readiness Score = compliance × 0.55 + AI readability × 0.45.

Available Tools

ai_readiness_check

Score how likely Amazon's AI (Rufus, COSMO) is to recommend a listing. Returns a combined AI Recommendation Readiness Score with actionable fixes. Free, no API key required.

agent_ready_check

Score whether a product listing is Agent-Ready for AI shopping agents (OpenAI ACP / Google UCP era). Platform-agnostic: Amazon, Shopify, Walmart, TikTok Shop or any storefront. Returns four dimensions — structured attributes, entity clarity, trust & compliance, agent actionability — plus ranked fixes. Free, no API key required, runs fully locally in the MCP server (no credits).

compliance_check

Fast pre-publish compliance gate: scans for red-line words and category risks before you generate or publish. Free with API key.

compliance_scan

Deep, knowledge-base-driven compliance audit across prohibited terms, IP risk, category rules, and GPSR. Returns a written report. 2 credits.

generate_listing

Generate optimized title + bullets + description for selected marketplaces. 1 credit per marketplace.

fill_from_sentence

Turn a one-sentence product description into structured listing fields. Free with API key.

generate_poa

Draft a submission-ready Plan of Action from an Amazon violation or suspension notice. 4 credits.

analyze_review

Analyze a negative review for root cause and a suggested response or POA angle. 2 credits.

What's in this repo

This repository bundles ListingGood's agent skills and MCP server config so AI agents and power users can call ListingGood programmatically:

PackageWhat it does
listinggood-expertAll-in-one Amazon listing expert: write · compliance pre-check · appeal rescue
listinggood-amazon-listing-optimizerHigh-conversion listing generation (title + bullets + description)
listinggood-amazon-compliance-auditorCompliance audit with Critical/Warning/Info grading
listinggood-deep-complianceDeep, knowledge-base-backed compliance report
listinggood-appeal-rescuePOA drafting + negative-review root-cause analysis
listinggood-amazon-title-optimizerA9/A10 title optimization
listinggood-amazon-bullet-writerBenefit-led bullet points
listinggood-amazon-eu-localizationEU marketplace (DE/ES/FR/IT) localization
MCP server8 tools (free check, Agent-Ready score, deep scan, AI generation, POA, …) + vertical MCPs (Electronics / Toys / Beauty / Home)

Quick start

  1. Get a free API key at listinggood.com/developers.
  2. Add the server to your MCP client using the config block in Installation.
  3. Restart your client. ListingGood's tools appear as available MCP tools.

Try it now (no account)

Run a free compliance + AI-readability check at listinggood.com/scan — paste your title and bullets, get a report in seconds.

Links

ListingGood AI Recommendation Engine — make AI recommend your products.

來源：README.md，提交 9249aba

工具

8

ai_readiness_check

Score how likely Amazon's AI (Rufus, COSMO) is to recommend a listing. Free, deterministic, rule-based check on pasted listing copy (title, bullets, description). Returns a compliance health score, an AI-readability score, and a combined AI Recommendation Readiness Score (compliance * 0.55 + readability * 0.45) with actionable suggestions. Use this as a fast baseline BEFORE generating or editing a listing. Do NOT use it for a full compliance report - use compliance_scan for the deep knowledge-base audit. Free, read-only, no API key required, no credits deducted. Args: text: raw listing title + bullets + description (required). marketplace: marketplace code, US/DE/ES/FR/IT/JP/AE/SA/UK (default US). lang: zh or en (default en). email: optional lead email for a confirmation message and lead capture.

輸入參數langtext必填emailmarketplace

agent_ready_check

Score whether a product listing is Agent-Ready for AI shopping agents (ACP/UCP era). Platform-agnostic: works for Amazon, Shopify, Walmart, TikTok Shop or any storefront that AI shopping assistants may read. Use it when a user asks whether their product will be found, recommended, or auto-purchased by an AI agent. Fully local, deterministic rule engine — no API key, no credits, no network call. Returns four dimensions: structured attributes, entity clarity, trust & compliance, and agent actionability, plus ranked fixes. Args: text: raw product copy — title plus bullets/description (required). platform: amazon | shopify | walmart | tiktok | generic | auto (default auto-detected). lang: en or zh for the report language (default en).

輸入參數langtext必填platform

compliance_check

Quick pre-publish compliance gate before generating a listing. Fast, free scan for obvious red-line words and category risks. Returns a shallow pass/fail-style result, not a full audit. Use this as a cheap pre-check right before generation. Do NOT use it for a complete risk report - use compliance_scan for the deep knowledge-base audit. Read-only; requires an API key; no credits deducted. Args: text: listing copy (required). lang: zh or en (default en). category: optional category hint, e.g. electronics or apparel.

輸入參數langtext必填category

compliance_scan

Deep knowledge-base compliance audit (async; 2 credits). Produces a thorough, written risk report covering prohibited words, IP, category mismatches, GPSR and more, backed by a private 15-year compliance knowledge base. Use this when you need a complete, actionable compliance report. Do NOT use it for a quick pre-publish check - use compliance_check for that. Read-only; deducts 2 credits; runs asynchronously, poll for the result. Args: text: listing title/bullets/description (required). marketplace: marketplace code (default US). category: optional category hint. lang: zh or en (default en). images: optional list of up to 5 data:image base64 strings, each < 4MB.

輸入參數langtext必填imagescategorymarketplace

generate_poa

Draft a submission-ready Plan of Action (POA) from an Amazon violation notice (async; 4 credits). Converts a suspension or removal email into a structured POA appeal. Use this when a listing or account is suppressed. Not free - deducts 4 credits and runs asynchronously, poll for the result. Read-only: it drafts text and does not submit anything to Amazon. Args: text: violation notice or removal email text (required). marketplace: marketplace code (default US). lang: zh or en (default en). violation_type: optional, e.g. ip_complaint / authenticity / policy.

輸入參數langtext必填marketplaceviolation_type

analyze_review

Analyze a negative Amazon review for root cause and a suggested response (async; 2 credits). Extracts the underlying issue from a critical review and drafts a brand-appropriate response angle. Use this after a negative review appears, to decide how to reply. Do NOT use it to generate a listing or an appeal - use generate_listing or generate_poa for those. Read-only; deducts 2 credits; runs asynchronously, poll for the result. Args: text: the negative review text (required). marketplace: marketplace code (default US). lang: zh or en (default en).

輸入參數langtext必填marketplace

fill_from_sentence

Expand a one-sentence product description into structured listing fields (free; API key; no credits). Turns casual, spoken product copy into structured fields (title, bullets, features) that feed the listing generator. Use this as a low-friction starting point when you only have a rough sentence. Do NOT use it to produce a final optimized listing - use generate_listing for that. Read-only; free; no credits deducted. Args: sentence: one-sentence product description, 4-1000 characters (required). lang: zh or en (default en).

輸入參數langsentence必填

generate_listing

Generate a high-conversion Amazon listing - title + bullets + description (async; 1 credit per marketplace). Produces A9-optimized copy that respects per-marketplace character limits. Use this to create a full listing from product facts. Not free - deducts 1 credit per selected marketplace and runs asynchronously, poll for the result. Read-only: it drafts text and does not publish. Args: cn_name: product Chinese name (required). sku: product SKU (required). marketplaces: optional list of marketplace codes; defaults to all 9. price: optional product price. lang: zh or en (default en).

輸入參數sku必填langpricecn_name必填marketplaces

版本歷史

1
  1. v1.0.0最新Sep 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