accueil / serveurs / Dev & Code / io.github.amzscout-corp/amzscout-skill-mcp
io.github.amzscout-corp/amzscout-skill-mcp
serveur MCP (Model Context Protocol) · amzscout-tools 1.0.0
Référencé dans l'annuaire. Seul le pentest comportemental fait foi, et il n'a pas encore été exécuté sur ce serveur.
Est-ce que io.github.amzscout-corp/amzscout-skill-mcp est sûr ?
Au dernier audit MCP Hub, le serveur MCP « io.github.amzscout-corp/amzscout-skill-mcp » est classé « Non encore testé ». Référencé dans l'annuaire. Seul le pentest comportemental fait foi, et il n'a pas encore été exécuté sur ce serveur. Le verdict est réévalué en continu ; consultez la fiche pour l'état à jour.
Méthode : MCP Hub analyse la description de chaque outil (couche 1) et, pour le verdict fort, exécute le serveur dans une micro-VM isolée avec leurres et réseau bloqué (couche 2). On publie des noms et des compteurs, jamais le contenu brut renvoyé par un outil.
Les 13 outils
- amzscout_advanced_product_data≈ 747 tokens
Extra catalog facts about one Amazon ASIN that amzscout_analyze_product does not include: bullet features, materials, included components, ingredients, hazmat info, UPCs and manufacturer; on request also frequently-bought-together / bundle ASINs, listing videos, return rate, brand store link and buy box seller history. No sales, price or review numbers — those come from amzscout_analyze_product. Pure data fetch (no AI analysis). When to call: together with amzscout_analyze_product whenever the user asks about one specific product (same ASIN and marketplace), so the answer carries the listing facts as well as the numbers. Call WITHOUT `sections` by default (returns catalog + identifiers); add relations / media / buybox only when the question is about them. How to use: describe what the product actually is and how it is positioned — key features, materials, what is in the box, compliance flags (hazmat, ingredients) — and point out what a competing listing would need to match or beat. Present facts as written on the listing; do not invent missing ones. Marketplace: if the user has not named a country / Amazon domain in this conversation, ask them once which marketplace they work on and reuse that code for every later call in the chat; do not assume the US. Called without `marketplace`, this tool fetches nothing and answers "MARKETPLACE NEEDED". Money is in that marketplace's local currency.
Paramètres, retour & exemple (3)
Paramètresasin· string · requis
Amazon Standard Identification Numbersections· array · optionnel
Which data to return. Omit for the default (catalog + identifiers). Request others only when the question needs them — relations, media and buybox are slower. Options: "catalog" (bullet features, materials, included components, active / special ingredients, item highlights, hazmat info); "identifiers" (UPC codes and manufacturer); "relations" (frequently-bought-together and bundle ASINs); "media" (listing videos (title, length, creator, link)); "buybox" (return rate (low / high), brand store link, buy box seller-ID history).marketplace· string · optionnel · COM | CO_UK | DE | FR | IT | ES | CA | COM_MX
Amazon marketplace code — the one the user named, or the one they chose earlier in this conversation (ask once, then reuse it for every call). Never assume the US for an ASIN: without it, ASIN tools fetch nothing and answer "MARKETPLACE NEEDED". Money in results is in this marketplace's currency.
Exemple d'appel{"name": "amzscout_advanced_product_data", "arguments": {"asin": "texte"}}Exemple de retour{"content": [{"type": "text", "text": "…"}]} - amzscout_analyze_niche≈ 721 tokens
Market snapshot for an Amazon niche/keyword — top products by revenue plus computed aggregates (price/sales/revenue/review distributions, revenue concentration, brand spread). Pure data fetch (no AI analysis) — reason over the returned data yourself. How to use: judge niche attractiveness — demand concentration (revenueTop5SharePercent: high = winner-takes-all, low = fragmented/open), price bands and where the money sits, review counts as entry moats, brand dominance vs no-name spread, and standout products (high sales + weak rating/reviews = displacement opportunity).
Paramètres, retour & exemple (4)
Paramètrescount· integer · optionnel
How many top products to pull from Amazon (5–100).filters· object · optionnel
Filter products by price / sales / revenue / reviews / ratingkeyword· string · requis
Niche, category, or product search keywordmarketplace· string · optionnel · COM | CO_UK | DE | FR | IT | ES | CA | COM_MX
Amazon marketplace code — the one the user named, or the one they chose earlier in this conversation (ask once, then reuse it for every call). Never assume the US for an ASIN: without it, ASIN tools fetch nothing and answer "MARKETPLACE NEEDED". Money in results is in this marketplace's currency.
Exemple d'appel{"name": "amzscout_analyze_niche", "arguments": {"keyword": "texte"}}Exemple de retour{"content": [{"type": "text", "text": "…"}]} - amzscout_analyze_product≈ 478 tokens
Full raw data for a single Amazon product by ASIN — price, estimated sales/revenue, reviews, rating, listing quality, sellers, plus sales/price/revenue history when available. Pure data fetch (no AI analysis) — reason over the returned data yourself. How to use: audit the product like a sourcing analyst — demand trend & seasonality from sales history, pricing direction & margin risk from price history and FBA fees, competition from sellers/reviews, listing quality from LQS, then conclude whether a new seller should enter (GO / NO-GO and what it would take). Listing facts (features, materials, ingredients, UPC, videos) are NOT here — they come from amzscout_advanced_product_data (call both for the same ASIN). Marketplace: if the user has not named a country / Amazon domain in this conversation, ask them once which marketplace they work on and reuse that code for every later call in the chat; do not assume the US. Called without `marketplace`, this tool fetches nothing and answers "MARKETPLACE NEEDED". Money is in that marketplace's local currency.
Paramètres, retour & exemple (2)
Paramètresasin· string · requis
Amazon Standard Identification Numbermarketplace· string · optionnel · COM | CO_UK | DE | FR | IT | ES | CA | COM_MX
Amazon marketplace code — the one the user named, or the one they chose earlier in this conversation (ask once, then reuse it for every call). Never assume the US for an ASIN: without it, ASIN tools fetch nothing and answer "MARKETPLACE NEEDED". Money in results is in this marketplace's currency.
Exemple d'appel{"name": "amzscout_analyze_product", "arguments": {"asin": "texte"}}Exemple de retour{"content": [{"type": "text", "text": "…"}]} - amzscout_analyze_product_set≈ 455 tokens
Raw data across an explicit set of 2–100 ASINs — product rows plus computed aggregates (price/sales/revenue/review distributions, revenue concentration, brand spread). Pure data fetch (no AI analysis) — reason over the returned data yourself. To discover products from a keyword instead, analyzeNiche is the equivalent. How to use: treat the set as a mini-market — segment products into groups, spot where demand concentrates, flag outliers (price, sales, review anomalies), and summarize group-level signals. Marketplace: if the user has not named a country / Amazon domain in this conversation, ask them once which marketplace they work on and reuse that code for every later call in the chat; do not assume the US. Called without `marketplace`, this tool fetches nothing and answers "MARKETPLACE NEEDED". Money is in that marketplace's local currency.
Paramètres, retour & exemple (2)
Paramètresasins· array · requis
2–100 ASINs to fetch as a set (B0XXXXXXXX). 0/O-swapped prefixes are auto-corrected.marketplace· string · optionnel · COM | CO_UK | DE | FR | IT | ES | CA | COM_MX
Amazon marketplace code — the one the user named, or the one they chose earlier in this conversation (ask once, then reuse it for every call). Never assume the US for an ASIN: without it, ASIN tools fetch nothing and answer "MARKETPLACE NEEDED". Money in results is in this marketplace's currency.
Exemple d'appel{"name": "amzscout_analyze_product_set", "arguments": {"asins": []}}Exemple de retour{"content": [{"type": "text", "text": "…"}]} - amzscout_compare_niches≈ 431 tokens
Raw head-to-head data for 2–5 Amazon niches / category keywords — per-niche product sets plus computed aggregates (price/sales/revenue distributions, revenue concentration, brand spread). Pure data fetch (no AI analysis) — do the comparison yourself. For ASINs, compareProducts is the equivalent. How to use: weigh demand (total est. revenue/sales) against competition (review levels, brand concentration) and price levels per niche, then give a verdict on which niche is the better opportunity for a new seller and under what conditions.
Paramètres, retour & exemple (3)
Paramètrescount· integer · optionnel
Products fetched per niche (default 10).keywords· array · requis
2–5 niches / category keywords to compare head-to-head, e.g. ["yoga mat", "resistance bands"].marketplace· string · optionnel · COM | CO_UK | DE | FR | IT | ES | CA | COM_MX
Amazon marketplace code — the one the user named, or the one they chose earlier in this conversation (ask once, then reuse it for every call). Never assume the US for an ASIN: without it, ASIN tools fetch nothing and answer "MARKETPLACE NEEDED". Money in results is in this marketplace's currency.
Exemple d'appel{"name": "amzscout_compare_niches", "arguments": {"keywords": []}}Exemple de retour{"content": [{"type": "text", "text": "…"}]} - amzscout_compare_products≈ 453 tokens
Side-by-side raw data for 2–5 Amazon products by ASIN — price, sales/revenue estimates, reviews, listing quality, plus history when available. Pure data fetch (no AI analysis) — do the comparison yourself. For a single ASIN, analyzeProduct is the equivalent. How to use: compare demand (est. sales), revenue, review moat and rating, price positioning, listing quality, and history trends (growing vs declining), then give a verdict on which product is the stronger opportunity and why. Marketplace: if the user has not named a country / Amazon domain in this conversation, ask them once which marketplace they work on and reuse that code for every later call in the chat; do not assume the US. Called without `marketplace`, this tool fetches nothing and answers "MARKETPLACE NEEDED". Money is in that marketplace's local currency.
Paramètres, retour & exemple (2)
Paramètresasins· array · requis
2–5 ASINs to compare. Each must be a real Amazon ASIN (B0XXXXXXXX). 0/O-swapped prefixes are auto-corrected.marketplace· string · optionnel · COM | CO_UK | DE | FR | IT | ES | CA | COM_MX
Amazon marketplace code — the one the user named, or the one they chose earlier in this conversation (ask once, then reuse it for every call). Never assume the US for an ASIN: without it, ASIN tools fetch nothing and answer "MARKETPLACE NEEDED". Money in results is in this marketplace's currency.
Exemple d'appel{"name": "amzscout_compare_products", "arguments": {"asins": []}}Exemple de retour{"content": [{"type": "text", "text": "…"}]} - amzscout_find_by_brand≈ 706 tokens
List products under a specific Amazon brand. Pre-validates the brand name via cached AI check, then filters keyword-search results to rows whose `brand` field actually matches. On no-match, returns the brands that did appear in the keyword pool so callers can suggest alternatives. How to use: assess the brand's Amazon footprint — lineup breadth, price range, which products carry the revenue, and how strong its review moat is.
Paramètres, retour & exemple (5)
Paramètressort· string · optionnel · revenue | sales | newest | rating | reviewsbrand· string · requis
Amazon brand name to search bycount· integer · optionnel
How many products to return (1–100)filters· object · optionnel
Filter products by price / sales / revenue / reviews / ratingmarketplace· string · optionnel · COM | CO_UK | DE | FR | IT | ES | CA | COM_MX
Amazon marketplace code — the one the user named, or the one they chose earlier in this conversation (ask once, then reuse it for every call). Never assume the US for an ASIN: without it, ASIN tools fetch nothing and answer "MARKETPLACE NEEDED". Money in results is in this marketplace's currency.
Exemple d'appel{"name": "amzscout_find_by_brand", "arguments": {"brand": "texte"}}Exemple de retour{"content": [{"type": "text", "text": "…"}]} - amzscout_get_keywords≈ 634 tokens
Amazon keyword / SEO / PPC data for either a single product (ASIN-scope — terms the product ranks for) or a niche/category (keyword-scope — search data around the term). Pass BOTH `asin` and `keyword` to get the product's position for exactly that keyword (e.g. "organic rank of B0... for standing lamp") — the reply gives the exact-match row as the answer and lists look-alike keywords with extra symbols separately; never report a look-alike's rank for the requested keyword. Every keyword row carries search volume, average sales, CPC and trend; ASIN-scope rows ALSO carry this product's own placement for that term — organic rank + page, sponsored page, and relevance score (rows the product does not rank for are marked "not ranking"). Pure data fetch (no AI analysis). How to use: pick high-volume / low-competition terms for SEO and PPC targeting, use CPC as ad-cost pressure, sum search volumes to gauge niche demand, and for ASIN-scope check organic vs sponsored ranks to spot listing-optimization gaps. Marketplace: if the user has not named a country / Amazon domain in this conversation, ask them once which marketplace they work on and reuse that code for every later call in the chat; do not assume the US. Called without `marketplace`, this tool fetches nothing and answers "MARKETPLACE NEEDED". Money is in that marketplace's local currency.
Paramètres, retour & exemple (3)
Paramètresasin· string · optionnel
ASIN-scope: keywords this product ranks for. Together with `keyword`: this product's position for exactly that keyword.keyword· string · optionnel
Keyword-scope: search data around this niche term. Together with `asin`: the exact keyword to look up for the product (pass it exactly as the user wrote it — no added symbols or words).marketplace· string · optionnel · COM | CO_UK | DE | FR | IT | ES | CA | COM_MX
Amazon marketplace code — the one the user named, or the one they chose earlier in this conversation (ask once, then reuse it for every call). Never assume the US for an ASIN: without it, ASIN tools fetch nothing and answer "MARKETPLACE NEEDED". Money in results is in this marketplace's currency.
Exemple d'appel{"name": "amzscout_get_keywords", "arguments": {"asin": "texte", "keyword": "texte", "marketplace": "COM"}}Exemple de retour{"content": [{"type": "text", "text": "…"}]} - amzscout_locate_asin≈ 338 tokens
Find which Amazon marketplaces list an ASIN, and get its product link on every marketplace (amazon.com, .co.uk, .de, .fr, .it, .es, .ca, .com.mx, .com.br, .in, .co.jp, .com.au, .ae, .sa). For each marketplace where it is listed: title, price in that marketplace's local currency, estimated monthly sales. Paid: 1 000 tokens per marketplace checked, per ASIN (14 000 per ASIN). How to use: call it ONLY when the user asks where / on which Amazon marketplaces a product is sold, or wants its links on other marketplaces. Do NOT call it just to choose a marketplace for analysis — for that, ask the user once which marketplace they work on and reuse it for the whole conversation. Present the result as a list (country, link, local price, sales); if the user then wants analysis, pass the marketplace they pick to amzscout_analyze_product / amzscout_get_keywords.
Paramètres, retour & exemple (1)
Paramètresasins· array · requis
1–5 ASINs to locate (B0 + 8 characters). Pass several only when they will be analyzed together.
Exemple d'appel{"name": "amzscout_locate_asin", "arguments": {"asins": []}}Exemple de retour{"content": [{"type": "text", "text": "…"}]} - amzscout_recommend_tool≈ 181 tokens
Given a user use-case, returns the AMZScout tools & Sellerhook services catalog (with tracking links) so you can recommend the right AMZScout product/feature. Use for "which AMZScout tool should I use for X" questions.
Paramètres, retour & exemple (1)
ParamètresuseCase· string · requis
What the user is trying to do (e.g. "find low-competition products", "validate a supplier", "track BSR").
Exemple d'appel{"name": "amzscout_recommend_tool", "arguments": {"useCase": "texte"}}Exemple de retour{"content": [{"type": "text", "text": "…"}]} - amzscout_reseller_amazon≈ 818 tokens
Buy box, competing offers and price/rank statistics for one Amazon ASIN — who owns the buy box and at what price, how ownership has split between sellers, FBA vs FBM offer counts, the live offer list with seller names and ratings, price levels over 30/90/180/365 days with all-time extremes, sales-rank drops, out-of-stock share, and buy box ownership history. Built for reseller / online-arbitrage questions, not private-label research — for demand and revenue estimates use analyzeProduct instead. Pure data fetch (no AI analysis). IMPORTANT: call it first WITHOUT `sections` — the summary alone answers most questions, and the reply lists which sections hold data for this ASIN. Only request sections when the summary is not enough; asking for all six returns several KB of detail you will rarely need. How to use: judge whether the listing is worth reselling — Amazon in the buy box or a single seller holding most of it means little room, many FBA offers means price competition, high out-of-stock share means supply gaps you could fill, and rank drops indicate how fast it sells. Marketplace: if the user has not named a country / Amazon domain in this conversation, ask them once which marketplace they work on and reuse that code for every later call in the chat; do not assume the US. Called without `marketplace`, this tool fetches nothing and answers "MARKETPLACE NEEDED". Money is in that marketplace's local currency.
Paramètres, retour & exemple (3)
Paramètresasin· string · requis
Amazon Standard Identification Numbersections· array · optionnel
Which parts of the data to return. Omit for a compact summary plus the list of sections available — request specific sections only when the summary does not answer the question. Options: "buybox" (who holds the buy box now, at what price, and how ownership split between sellers); "competition" (offer counts by fulfilment, cheapest FBA/FBM sellers, and the live offer list with seller names); "pricing" (current / 30 / 90 / 180 / 365-day price levels plus all-time low and high, per offer type); "rank" (sales rank levels and rank-drop counts, the closest available proxy for sales velocity); "availability" (how often the listing had no buyable offer, and the visible stock of Amazon and the buy box winner); "history" (buy box ownership changes over time, resolved to seller names).marketplace· string · optionnel · COM | CO_UK | DE | FR | IT | ES | CA | COM_MX
Amazon marketplace code — the one the user named, or the one they chose earlier in this conversation (ask once, then reuse it for every call). Never assume the US for an ASIN: without it, ASIN tools fetch nothing and answer "MARKETPLACE NEEDED". Money in results is in this marketplace's currency.
Exemple d'appel{"name": "amzscout_reseller_amazon", "arguments": {"asin": "texte"}}Exemple de retour{"content": [{"type": "text", "text": "…"}]} - amzscout_search_knowledge≈ 192 tokens
TF-IDF search across the AMZScout knowledge base (Amazon-seller tutorials, brand reference, glossary). Returns the top-K relevant chunks with title, source URL and text. Use this to ground answers in factual material.
Paramètres, retour & exemple (2)
ParamètrestopK· integer · optionnel
How many knowledge chunks to return (1–20)query· string · requis
Search phrase. 2-300 chars.
Exemple d'appel{"name": "amzscout_search_knowledge", "arguments": {"query": "texte"}}Exemple de retour{"content": [{"type": "text", "text": "…"}]} - amzscout_search_products≈ 744 tokens
Keyword search against Amazon — returns the top N products with price, sales, revenue, reviews, rating. Pure data fetch (no AI analysis). Best when you need raw product rows (specific sort order or filters); analyzeNiche additionally returns computed market aggregates on top of the rows. How to use: scan the rows for demand leaders, price clusters, and low-review listings that still sell — those are the entry-opportunity signals.
Paramètres, retour & exemple (5)
Paramètressort· string · optionnel · revenue | sales | newest | rating | reviews | price-low | price-high
Result sort order. revenue/sales/rating/reviews descending; price-low ascending; newest by first-listed date.count· integer · optionnel
How many products to return (1–100)query· string · requis
Search keyword / phrase.filters· object · optionnel
Filter products by price / sales / revenue / reviews / ratingmarketplace· string · optionnel · COM | CO_UK | DE | FR | IT | ES | CA | COM_MX
Amazon marketplace code — the one the user named, or the one they chose earlier in this conversation (ask once, then reuse it for every call). Never assume the US for an ASIN: without it, ASIN tools fetch nothing and answer "MARKETPLACE NEEDED". Money in results is in this marketplace's currency.
Exemple d'appel{"name": "amzscout_search_products", "arguments": {"query": "texte"}}Exemple de retour{"content": [{"type": "text", "text": "…"}]} - amzscout_usage≈ 136 tokens
The caller's AMZScout AI-agents token balance — remaining, used, and limit. Free — no tokens are charged for this call. How to use: answer "how many tokens do I have left", "what's my usage / balance / limit", or when a call fails on quota. Report the remaining figure first.
Paramètres, retour & exemple (0)
Exemple d'appel{"name": "amzscout_usage", "arguments": {}}Exemple de retour{"content": [{"type": "text", "text": "…"}]}
C'est votre serveur ?
Revendiquez-le sur l'espace créateur (preuve GitHub, domaine ou npm) pour afficher le badge « propriétaire vérifié » et lancer un pentest comportemental à la demande afin d'obtenir le badge « Vérifié ».