accueil / serveurs / Productivité / io.github.nathangrotticelli/searchshopai
io.github.nathangrotticelli/searchshopai
serveur MCP (Model Context Protocol) · SearchShopAI 0.3.0
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.nathangrotticelli/searchshopai est sûr ?
Au dernier audit MCP Hub, le serveur MCP « io.github.nathangrotticelli/searchshopai » 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 11 outils
- compare_products≈ 195 tokens
Compare two or more products side by side. Use when the user asks to compare, says 'X vs Y', or wants to decide between options. Do not use for single product lookup — use get_product instead. Returns structured comparison with shared attributes, differences, tradeoffs, and a decision hint.
Paramètres, retour & exemple (1)
Paramètresproducts· array · requis
Product titles or SKUs to compare (e.g. ['MIRA', 'CryoSculpt'])
Exemple d'appel{"name": "compare_products", "arguments": {"products": []}}Exemple de retour{"content": [{"type": "text", "text": "…"}]} - create_checkout≈ 526 tokens
Create a checkout URL for one or more products. Pass variant IDs (items) and/or product URLs (product_urls). When a product URL is provided (e.g. https://laluer.com/products/mira), the tool resolves it to a variant ID automatically — no catalog import needed. Supports discount codes, cart notes, and selling plans. Do not use unless the user wants to buy — use search_products or skincare_recommend first. Returns a direct Shopify checkout link the user can click to buy.
Paramètres, retour & exemple (5)
Paramètresnote· string · optionnel
Cart note visible to the merchantitems· array · optionnel
Products to add to cart by variant IDdecision_id· string · optionnel
Optional — leave unset unless an earlier create_checkout error asked for it.product_urls· array · optionnel
Products to add to cart by URL — resolved to variant IDs automaticallydiscount_code· string · optionnel
Discount code to apply (e.g. 'WELCOME10')
Exemple d'appel{"name": "create_checkout", "arguments": {"note": "texte", "items": [], "decision_id": "texte", "product_urls": [], "discount_code": "texte"}}Exemple de retour{"content": [{"type": "text", "text": "…"}]} - get_product≈ 194 tokens
Get full details for a specific product by SKU or title. Use when the user asks about a specific product by name (e.g. 'tell me about MIRA', 'show me the serum'). Do not use for browsing or recommendations — use search_products or skincare_recommend. Returns a widget card with the product details, image, price, and checkout button.
Paramètres, retour & exemple (2)
Paramètressku· string · optionnel
Exact product SKU (e.g. 'LL-4632379916336')title· string · optionnel
Product title to search for (fuzzy match)
Exemple d'appel{"name": "get_product", "arguments": {"sku": "texte", "title": "texte"}}Exemple de retour{"content": [{"type": "text", "text": "…"}]} - get_research_note≈ 131 tokens
Get the summary and URL of a specific SearchShopAI Research Note by its slug (returned by search_research_notes).
Paramètres, retour & exemple (1)
Paramètresslug· string · requis
The note slug, e.g. 'the-ai-attribution-blind-spot'
Exemple d'appel{"name": "get_research_note", "arguments": {"slug": "texte"}}Exemple de retour{"content": [{"type": "text", "text": "…"}]} - recommend≈ 232 tokens
Get a personalized product recommendation with domain-expert scoring. Use when the user wants advice, has a concern, or asks what to buy. Returns scored products with checkout URLs.
Paramètres, retour & exemple (4)
Paramètresbrand· string · optionnel
Filter to a specific brandquery· string · requis
Natural language query about product needsdomain· string · optionnel
Product domain (e.g. 'skincare', 'beauty_devices'). Auto-detected from merchant if omitted.strategy· string · optionnel
Optional offer strategy override
Exemple d'appel{"name": "recommend", "arguments": {"query": "texte"}}Exemple de retour{"content": [{"type": "text", "text": "…"}]} - search_products≈ 408 tokens
Browse and search the product catalog. Use when the user wants to see what's available, look up specific products, browse by category, compare options, or asks 'show me' / 'what do you have.' Do not use when the user needs personalized recommendations based on skin concerns — use skincare_recommend instead. Returns all matching products with prices, images, and checkout. Unlike skincare_recommend, this does not score or filter — it shows everything that matches so the user can decide.
Paramètres, retour & exemple (4)
Paramètresquery· string · requis
Search query (e.g. 'vitamin c serum', 'anti-aging', 'moisturizer under $50')category· string · optionnel
Filter by exact product category from the catalog (e.g. 'serum', 'treatment', 'cleanser', 'moisturizer'). Do not guess categories — only use this if the user explicitly mentions a catalog category. For general queries like 'devices' or 'bundles', use the query parameter instead.max_price· number · optionnel
Filter to products at or below this pricemax_results· integer · optionnel
Maximum products to return (default 10). Only set this if the user specifies a count — e.g. 'show me 2 devices' → 2. Otherwise leave it unset and the default will return all relevant matches up to 10.
Exemple d'appel{"name": "search_products", "arguments": {"query": "texte"}}Exemple de retour{"content": [{"type": "text", "text": "…"}]} - search_research_notes≈ 182 tokens
Search SearchShopAI's Research Notes blog — data studies, playbooks, and field notes on agentic commerce (AI attribution, MCP, AI catalog accuracy, ChatGPT ads). Returns matching articles with titles, summaries, and URLs. Use when asked what SearchShopAI has written or published about a topic.
Paramètres, retour & exemple (1)
Paramètresquery· string · requis
Topic or keywords, e.g. 'attribution', 'MCP', 'hallucinated prices'
Exemple d'appel{"name": "search_research_notes", "arguments": {"query": "texte"}}Exemple de retour{"content": [{"type": "text", "text": "…"}]} - shop≈ 403 tokens
Start here for any shopping request. Pass the shopper's COMPLETE request in their own words and this tool will understand it and route to the right capability (personalized recommendation, catalog search, product lookup, or comparison), preserving every qualifier — concerns, skin type, budget, brand. Prefer this tool whenever the request is conversational or carries any nuance. The granular tools (search_products, get_product, compare_products, create_checkout) remain available as precise follow-ups.
Paramètres, retour & exemple (5)
Paramètresbrand· string · optionnel
Secondary hint only — brand filter if stated.intent· string · optionnel · advice | browse | product | compare | buy | question
Secondary hint only — the primary signal is `request`.request· string · requis
The shopper's complete request in their own words. Include every detail: concern, skin type, budget, brand, product names, questions. Do not summarize or drop qualifiers.budget_max· number · optionnel
Secondary hint only — maximum budget if stated.product_refs· array · optionnel
Secondary hint only — exact product titles/SKUs when already known.
Exemple d'appel{"name": "shop", "arguments": {"request": "texte"}}Exemple de retour{"content": [{"type": "text", "text": "…"}]} - skincare_cart≈ 260 tokens
Create a buyable shopping cart with a real checkout URL. Two modes: (1) Pass 'products' array with specific product names. (2) Pass 'query' string to auto-recommend and cart. Do not use for browsing or recommendations — use search_products or skincare_recommend first. Returns a widget with the cart items and a working checkout link.
Paramètres, retour & exemple (3)
Paramètresquery· string · optionnel
Natural language query to auto-recommend products. Only used if products array is not provided.products· array · optionnel
Specific product titles to add to the cartstrategy· string · optionnel
Optional offer strategy override when using query mode
Exemple d'appel{"name": "skincare_cart", "arguments": {"query": "texte", "products": [], "strategy": "texte"}}Exemple de retour{"content": [{"type": "text", "text": "…"}]} - skincare_recommend≈ 290 tokens
(Deprecated: use 'recommend' instead. Works identically.) Get a personalized skincare recommendation with ingredient-aware scoring and routine building. Use when the user wants advice, has a skin concern, or asks what to buy. Do not use for browsing or listing products — use search_products instead. Returns scored products with checkout URLs.
Paramètres, retour & exemple (3)
Paramètresbrand· string · optionnel
Filter to a specific brand only (e.g. 'Glossier', 'CeraVe', 'The Ordinary'). Use when the user asks for products from a specific brand.query· string · requis
Natural language query about skin concerns (e.g. 'I have oily acne-prone skin, under $30')strategy· string · optionnel
Optional offer strategy override: starter, gentle, budget, glow_safe, minimal, strong, fallback
Exemple d'appel{"name": "skincare_recommend", "arguments": {"query": "texte"}}Exemple de retour{"content": [{"type": "text", "text": "…"}]} - skincare_report_issue≈ 342 tokens
Report when a tool result was unhelpful, incomplete, or wrong. Call this whenever you override a recommendation, skip a cart result, or notice the engine output doesn't match what the user needs. Do not use proactively — only when you observe an actual issue. This helps improve the engine.
Paramètres, retour & exemple (5)
Paramètrestool_name· string · requis
Which tool had the issue (skincare_recommend, skincare_cart, skincare_report_issue)issue_type· string · requis · wrong_products | too_few_products | too_expensive | ignored_concern | ignored_budget | bad_recommendation | cart_mismatch | missing_product
Type of issueuser_query· string · optionnel
The original user query if availabledescription· string · requis
What went wrong and what you expected insteadexpected_products· array · optionnel
What products should have been recommended
Exemple d'appel{"name": "skincare_report_issue", "arguments": {"tool_name": "texte", "issue_type": "wrong_products", "description": "texte"}}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 ».