Know what you're buying: brand, white-label, price, fake-discount, review and seller checks
Scored across 3 tools
Each tool targets a clearly distinct scope: check_brands evaluates brand reputation, check_product evaluates a single listing, and check_products evaluates multiple listings for comparison. The boundaries are explicit (single product vs. batch), so an agent can easily select the right tool.
All three tools follow a consistent verb_noun pattern (check_brands, check_product, check_products) with singular/plural distinction used meaningfully. The convention is predictable and readable.
Three tools is well-scoped for this server's purpose: brand checking and product trust-signal checking for single and multiple products. Each tool earns its place, and the batch version is justified for comparison use cases.
The surface covers the core domain of evaluating brand and product trust signals, with both single and batch product checks plus brand checks. Minor gaps include no explicit tool for seller-only checks or historical tracking, but these are not critical for the stated purpose.
Use this when the user asks whether a brand is reputable or what kind of brand it is (an established name, a store's own label, an independent maker, or a generic white-label name), or wants brands compared while shopping. Returns findings on each brand: what kind of brand it is, its reputation for quality and its usual price tier, each with a confidence. Signals only, never a buy or avoid verdict. Does not browse the web and is not for banking, health or email pages. Pass brand names as the user or the listing gave them, up to 50 per call.
Inputs: brands (required), detail. Returns: quota, brands
Use this when the user is looking at a specific product listing on an online store and wants to know whether it looks trustworthy or like a good buy. Pass what you already read from the listing as arguments: title (required) and, when shown, brand, price, listPrice (the seller's "was" price), currency, url, seller, category, rating, reviewCount and key details; each extra field sharpens the read. Returns findings such as generic white-label product, quality, price, questionable discount, review credibility and seller legitimacy, each with a confidence, plus a report on the brand unless includeBrand is false. Signals only, never a buy or avoid verdict. Does not browse: only the domain of url is used. Not for banking, health, government or email pages.
Inputs: title (required), id, url, brand, +10 more. Returns: id, brand, quota, counts, +2 more
Use this when the user is comparing several product listings, such as search results or the same item at different stores, and wants trust signals on each. Pass up to 20 products, each with what you already read from its listing: title (required) and, when shown, brand, price, listPrice, currency, url, seller, category, rating, reviewCount, details, plus your own id to match results. Returns, in input order, the same findings as check_product for each; a product that can't be checked carries an error and message instead. Signals only, never a buy or avoid verdict. Does not browse the web. Not for banking, health, government or email pages.
Inputs: products (required), detail, includeBrand. Returns: quota, products
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
Detect fake or manipulated product reviews from Amazon, Trustpilot, Google and Etsy.
See who gets your money, catch fake holiday discounts, and find independent and local sellers.
Buy or avoid verdict for Taobao, Tmall and 1688 listings: fake brand flag, seller trust, landed cost
Verified deals, store policies & a trust score for thousands of online retailers. No auth.
Add one secure layer between your agents and this server.
