Open-source B2B and marketplace ecommerce; new stores include an MCP server for AI agents.
Logimu
概览
作者提供的说明(英文原文)
Amazon (11 marketplaces) and Walmart US product data: search, prices, stock, history, sellers.
PopNx MCP 的三大支柱
这三项永远不会合并成一个分数:意见、测量和人气是不同的东西。
- 用户评价i暂无评价评价功能将在后续阶段与账户功能一起开放
- 我们的基础检查i3 项中通过 3 项依据公开信息检查;尚未扫描代码
- 使用情况i尚未统计★ –
它能帮你做什么
我们还没有为它写通俗的介绍。下面是我们从注册中心读取到的事实。
- 连接方式: 在云端运行
- 传输方式: Streamable HTTP
- 分类: 网店与支付
安装
选择你使用的 AI 应用,然后复制设置。
安装之前
- 基础检查:3 项中通过 3 项
- 在作者的服务器上运行:你向它提出的内容会经过他们的服务器。
- 可以做 18 件事(工具) product, shopping, search, seller …
- 注册中心没有列出需要填写的密钥。
你需要
- 在云端运行无需安装任何东西,通过互联网连接
你用的是哪个应用?
在上方选择你的应用。我们会记住它,下次按钮会显示“安装到 …”。
适用于网页版、桌面版和手机版 Claude:
- 打开 Settings → Connectors
- 点击 Add custom connector
- 粘贴下面的地址,然后点击 Add
- 如果要求登录,请登录作者的服务
https://api.logimu.com/mcp在终端中运行这条命令
claude mcp add --transport http shopping https://api.logimu.com/mcp或者自己复制设置
粘贴到项目中的 .cursor/mcp.json,或 ~/.cursor/mcp.json
{
"mcpServers": {
"shopping": {
"url": "https://api.logimu.com/mcp"
}
}
}浏览器会先询问是否打开应用,然后应用会显示设置并请你确认。密钥的值会留空,由你自己填写。
或者自己复制设置
粘贴到项目中的 .vscode/mcp.json
{
"servers": {
"shopping": {
"type": "http",
"url": "https://api.logimu.com/mcp"
}
}
}浏览器会先询问是否打开应用,然后应用会显示设置并请你确认。密钥的值会留空,由你自己填写。
ChatGPT 只能连接互联网上的服务器:
- 打开网页版 ChatGPT → Settings → Connectors (Apps)
- 点击 Create 或 Add(部分套餐需要先在 Advanced 中开启 Developer mode)
- 粘贴下面的地址,起个名字,然后保存
- 如果要求登录,请登录作者的服务
https://api.logimu.com/mcp菜单名称可能因套餐和版本不同而略有差异。
你的选择通过 Cookie 保存在这台设备上,无需账户。
这些设置是根据作者在注册中心的条目生成的。如果 README 的写法不同,请以 README 为准。
它能做什么
工具名称和描述与服务器在 2026年11月7日 报告的完全一致。这些内容由作者撰写,不是我们写的;我们以纯文本形式显示。
productFull dossier for ONE known product: its current snapshot plus its observed history. USE WHEN the user has a specific ASIN, Walmart item ID, product link, or a product_id returned by shopping or search, and asks about price history, historical prices, price changes, 30-day history
shoppingCurated product discovery: a shopping keyword in, a ranked and grouped shortlist out, in under ~100ms. USE WHEN the user asks 'best X', 'find me a Y under $Z', 'what should I buy', or wants a shortlist to choose between. DON'T USE when the product is already identified by ASIN (u
searchFiltered query over the tracked-product warehouse (24M+ Amazon and Walmart products). USE WHEN the user wants a structured list matching explicit criteria: 'well-rated dehumidifiers under $150 with 1000+ reviews', 'everything by brand X sorted by BSR', 'FBA products in this categ
sellerAmazon SELLER profile by seller id, optionally with the products the seller sells. USE WHEN the user asks about a third-party seller / merchant / storefront (who they are, how they are rated, what they sell) - the seller id is the 'A...' code in /sp?seller=... or the seller_id on
serpLIVE Amazon search-results (SERP) fetch: a real browser navigates Amazon's search page RIGHT NOW and returns the parsed organic result grid plus everything around it. USE WHEN the user wants what Amazon's search page shows THIS MINUTE for a query — current ranking order, who is o
bestsellersLIVE Amazon Best Sellers list for one category: up to 100 products in Amazon's rank order, the category's full breadcrumb name, and its subcategories with their URLs. Given a marketplace's root best-sellers URL (or just a country) it returns the top-level categories instead, so y
offersLIVE Amazon offers page for one product: every seller offering it right now, read from Amazon's 'All offers' view at request time, every page of it (up to 10). Each offer has the seller and seller_id, price, shipping_cost, condition, buy box, FBA / FBM / Amazon, Prime, ships-from
dealsLIVE Amazon Today's Deals: the deals page of one marketplace, read from Amazon at request time and filtered the way Amazon's own page filters it - department (category_id), deal collection (deal_types: lightning_deal, trending, coupons, started_today, ending_today; or any collect
brandAmazon BRAND dossier from Logimu's own buy-box observations (derived intelligence, not estimates): catalog size, how many sellers win the buy box, control score (share of buy-box days won by FBA offers), winner diversity, Amazon's own retail share, FBA penetration, seller concent
categoryAmazon CATEGORY landscape from Logimu's observations: size (ASINs, brands, sellers), pricing and rating averages, Amazon's own retail share, FBA penetration, Amazon private-label share, seller concentration (HHI top-5), heat (competitive intensity), 30-day catalog churn, demand s
market_listsRanked LISTS from Logimu's observations, 25 per page: kind=brand_movers (brands gaining or losing distinct buy-box sellers fastest over 30 or 90 days), seller_movers (sellers whose buy-box footprint grew or shrank most), top_brands (brands ranked by observed buy-box days / seller
keywordsAmazon's OWN autocomplete suggestion lists for a seed term, from Logimu's continuous harvest (since Aug 2026, 11 marketplaces): up to 6 lists - one per crawled prefix / department - each term with its position 1-10 WITHIN that list, when it was first and last observed and the mar
keyword_rankingsPage 1 of Amazon search for a keyword, as Logimu last OBSERVED it (head search terms taken from Amazon's own autocomplete, each observed about once a week, all departments; amazon.com from one US delivery ZIP): the organic order with product facts (title, brand, price, rating) an
product_keywordsREVERSE ASIN on Amazon (11 marketplaces, country): every observed keyword (head search terms taken from Amazon's own autocomplete, page 1 observed about once a week) whose latest page 1 shows the product, organically with its rank or in a sponsored unit present in the page HTML,
track_productTRACK a product: pin an Amazon ASIN into our hot lane so its all-offers page is re-read every hour or every 2, 4, 12 or 24 hours, for as long as the plan is active (or a ttl_days you set), with e-mail and webhook alerts on the thresholds you give; every read lands in the product'
list_trackedLIST the products this API key tracks (track_product): each with its status, interval, read (offers or product_page), expiry, whether the hot lane has picked it up, the lane's last and next read, plus the plan's tracking allowance (snapshots a day: total, used, remaining). USE WH
batchBATCHES: run any Logimu endpoint over a whole list in one job and come back for the results - the same batch API as REST /v1/batches (see https://api.logimu.com/docs#batch). action=estimate prices a list before anything is billed (free); action=create makes a named, re-runnable b
accountACCOUNT: the account's balance, plan, 30-day usage by endpoint and its product-tracking allowance (snapshots a day: total, used, remaining) - the same as REST GET /v1/account. USE WHEN the user asks how many credits are left, what a job will leave, what the key has been used for,
基础检查i
我们检查的是任何人都能看到的信息;我们没有阅读代码。不适用的检查项不计入总数。 · 检查于 2026年11月8日
- ✓ 通过
作者与仓库一致
注册名称已通过域名 logimu.com 验证(注册中心会核实域名所有权)
- … 尚未检查
仍在维护
我们还没有从 GitHub 读取这个仓库
- … 尚未检查
有许可证
我们还没有从 GitHub 读取这个仓库
- ✓ 通过
端点有响应
在 132 毫秒内响应(HTTP 200)
- – 不适用
使用 OAuth 登录
无需登录
- ✓ 通过
工具描述中没有隐藏指令
已读取 18 个工具描述,未发现针对 AI 的隐藏指令
与“网店与支付”中的其他服务器比较i
- 星标数多于此分类中其他 2550 个服务器的 0%
- 发布到注册中心的时间比此分类中其他 2550 个服务器的 59% 更新
- 基础检查结果等于或优于此分类中其他 2550 个服务器的 100%
与注册中心里这个分类中所有活跃的服务器比较。只有当发布者拥有该仓库时,星标数才计入。
常见问题
Logimu 安全吗?
它在 3 项适用的基础检查中通过了 3 项。我们没有阅读代码。在添加密钥或令牌之前,请先看看这个服务器要求哪些权限,并使用只具备所需权限的密钥。
它需要哪些密钥或代码?
注册中心没有列出必需的密钥,不过有些服务器会在首次使用时要求你登录。
它在我的电脑上运行还是在云端?
它在作者的云端运行。通过互联网连接,无需安装,但你发送的内容会经过作者的服务器。
它还在维护吗?
GitHub 仓库最后更新于–,最新版本(1.8.0)于20天前进入注册中心。
哪些应用可以使用它?
支持 MCP 的应用,例如 Claude Desktop、Claude Code、Cursor 和 VS Code。它通过 URL 连接,所以接受远程 MCP 服务器的应用也可以使用,例如开启开发者模式的 ChatGPT。
有什么可以替代它?
同一分类中有:Spree Commerce: open-source B2B and marketplace ecommerce, Stripe MCP, MCP Cn Commerce
替代选择
同一分类中其他作者的服务器,按星标数排序。
如何看卡片:★ GitHub 星标i三大支柱:评价 · 检查 · 使用情况i更新 = 最新版本发布到注册中心的时间i
Stripe MCP
MCP server integrating with Stripe - tools for customers, products, payments, and more.
MCP Cn Commerce
8 read-only MCP platform entries; support is operation-specific; merchant live acceptance pending
作者的 README
打开 README
按原文从作者的仓库复制。PopNx MCP 没有审查或背书其内容。HTML、图片和脚本已被移除。链接会离开本站。
Logimu Shopping MCP
Give Claude, ChatGPT, and any MCP client real shopping data.
AI assistants are great at comparing products — and terrible at knowing today's price, what's actually in stock, and which "bestseller" is a relabeled generic. This MCP connector fixes that: your assistant gets observed Amazon (US, UK, DE, CA, AU, FR, IT, ES, JP, MX, BR) and Walmart US data — current prices, live stock, real ratings, price/BSR history, and ranked product shortlists — from a continuously refreshed warehouse of 17M+ tracked products.
Free, no signup: 5 shopping searches per day. Every other tool needs a Logimu plan (from $19/month).
https://api.logimu.com/mcp
Quick start
| Client | How |
|---|---|
| Claude (claude.ai / desktop / mobile) | Settings → Connectors → Add custom connector → paste the URL above. Authentication: *Sign in now* if you have a Logimu plan (every tool, metered on your plan; OAuth, the connector never sees your key), or keep the pre-selected *No sign-in* for the free shopping tool only. OAuth client: keep *Use Claude's published identity*. Claude can't change this choice later: remove the connector and add it again. |
| Claude Code | claude mcp add --transport http logimu https://api.logimu.com/mcp, then /mcp to sign in when a paid tool asks, or --header "Authorization: Bearer sk_live_…" to pass the key directly |
| ChatGPT (developer mode), Cursor, VS Code, anything MCP | Add the same URL as a remote (Streamable HTTP) server. |
Then ask things like:
- *"Find me the best coffee maker under $80"* → ranked shortlists grouped by category or price tier
- *"Is ASIN B0BDHQSZCV a good buy right now?"* → price, stock, buy-box seller, 30-day price/stock changes, brand stats
- *"Well-rated dehumidifiers under $150 with 1,000+ reviews"* → structured warehouse filtering
Tools
| Tool | Use when | Returns | Lane |
|---|---|---|---|
shopping | "best X", "find me Y under $Z" — you want a shortlist | Ranked, grouped products (category or Budget/Mid/Premium tiers) with real ratings, prices, stock, observed_at stamps + brand facets, in ~100ms | Free: 1 of 5 daily, without detail; plan: 2 credits, 5 with detail |
product | You have a specific ASIN/item — "good buy?", "price history?", "who sells this?" | Current snapshot + intelligence blocks: 30-day price/stock change events, all-seller offer table, brand stats, rating history and the rating breakdown by star with its per-day history from 2026-11-05 (percentages as Amazon prints them, counts approximate); full price, rank and buy-box histories with a key (included in the record), or history_only for the series alone (0.05 credit) | Paid plan: 0.5 credit from cache, 1 live |
search | Filtered structured lists — price/rating/review/BSR/FBA filters, sorting | Up to 100 rows, across all 11 Amazon marketplaces plus Walmart US | Paid plan: 1 credit per 25 rows |
serp | The live Amazon search-results page for a query, right now | Organic grid, sponsored and video blocks, refinements, pagination — a real fetch, seconds | API key: 1 credit per page fetched |
bestsellers | What sells best in a category right now; Amazon's best-seller category tree | Up to 100 products in Amazon's rank order, the category's breadcrumb name and its subcategories; a root URL or a country alone returns the top-level categories. A real fetch (seconds), cached up to 30 min | API key: 1 credit per page of 50 (top 100 = 2), root list free |
offers | Who sells a product right now, at what price; the cheapest new or used offer; the buy-box winner this minute | Every offer on Amazon's offers page (every page): seller and seller id, price, shipping, condition, buy box, FBA / FBM / Amazon, Prime, delivery promise and the seller's feedback, by ASIN or barcode. A real fetch (seconds); a no-offers answer is confirmed by a second, independent fetch | API key: 0.5 credit when an offer is listed; no offers, a miss or a failed fetch free |
deals | What is on sale on Amazon right now: today's deals or lightning deals in a department, deals above a discount or under a price, coupon deals, deals ending today | Amazon's Today's Deals page, filtered as Amazon filters it (department, deal collection, % off, price, Prime Exclusive, rating, brand): deal and list price, % off, deal type and state, % claimed, the countdown end, coupon; plus the departments, collections and facets to filter by next and filter_check (did Amazon apply each filter). A real fetch (seconds a page), cached up to 15 min | API key: 1 credit per page fetched (up to 120 deals a page); an empty page or a failed fetch free |
seller | A seller id — rating and feedback history, the storefront, the brands it was observed winning the buy box on, connected sellers | Stored profile (0.5) or live (1), +0.5 history; storefront pages 1 each; brands / network blocks +1 | Paid plan |
brand | Who sells a brand, how contested / Amazon-dominated / FBA-heavy it is, its seller map | Brand dossier from observed buy-box data (1), +0.5 history, +1 per sellers page, +1 for the network of brands sharing sellers | Paid plan |
category | How big / competitive / Amazon-dominated a category is, which brands lead it | Category landscape by id (1, +0.5 history); the name lookup is free | Paid plan |
market_lists | Discover rather than look up — brands gaining or losing sellers, the biggest operators, categories ranked | 25 rows per page, 1 credit per page | Paid plan |
keywords | Amazon's own autocomplete suggestion lists for a seed (positions within each list, first/last observed, marketplaces observed in, related vocabulary), history = each list's observation record, compare = the seed across marketplaces | 1 credit per lookup or compare, +0.5 with history | Paid plan |
keyword_rankings | Page 1 of Amazon US search as last observed (about weekly) for head search terms: the organic order with product facts and each product's latest buy box, the sponsored units in the page HTML, the Overall Pick holder, who holds the page by brand and seller, and what changed since the previous observation; history = the weekly observations. Dated observations, never volume figures | 1 credit a keyword, +0.5 with history | Paid plan |
product_keywords | Reverse ASIN on Amazon US: every observed keyword a product shows up for on page 1, with its rank; asins (up to 10) compares it with competitors and gaps keeps the keywords where they appear and it does not; history = its rank over time. Head search terms and page 1 only | 1 credit per 25 keywords per ASIN, +0.5 with history | Paid plan |
The paid-plan tools (product, search, seller, brand, category, market_lists, keywords, keyword_rankings, product_keywords, track_product, list_tracked) appear in tools/list only for keys on a paid plan; the stub lists the whole catalog so directories can see it. Every derived figure is an observed count or share from Logimu's own data — never an estimate — and "observed since" is the data horizon, not a founding date. Keyword answers are Amazon's own suggestion ranking as observed — positions within one list, never volume figures; the observed page-1 positions of products are keyword_rankings and product_keywords.
Full REST API reference (same engine, same data): api.logimu.com/docs
Free lane and paid plans, honestly stated
| Free (no signup) | Paid plan (API key) | |
|---|---|---|
| Queries | 5 shopping searches / day | Credit-metered — subscriptions from $19/month, one-time credit packs, unconditional 14-day money-back |
| Data | shopping: ranked shortlists from the warehouse (fresh, timestamped), without detail | + product records with history, search, shopping detail, mode=live on-demand fetches, serp, bestsellers, offers, deals, seller profiles, brand / category intelligence and market lists, batch jobs on the REST API |
| Signup | None | api.logimu.com |
- Every record carries an
observed_attimestamp — data is observed from our warehouse, not a live retailer feed. - We have no affiliate or seller relationship with anything the tools return. Nothing is ranked because someone paid for it.
- Failed or empty requests are never billed, on any tier.
What's in this repo
The live server is hosted — this repo carries the tool catalog, an introspection-only stdio stub (logimu-mcp-stub) so directory build harnesses can enumerate the tools without credentials, and the listing metadata. tools/call on the stub returns a pointer to the hosted endpoint.
pip install .
logimu-mcp-stub # stdio MCP: initialize / tools/list work; tools/call points to the hosted server
Links
- Product page: logimu.com/shopping-mcp
- API console & plans: api.logimu.com
- Docs: api.logimu.com/docs
- Privacy: logimu.com/privacy-policy · Terms: logimu.com/terms · Refunds: logimu.com/refund-policy
- Support: support@logimu.com
© 2026 Logimu · A service of CP Development doo · Not affiliated with Amazon or Walmart.