Amazon is an MCP server with 20 tools an agent can call, among them ai_search, filter_categories, filter_niches. It answers at https://mcp.pangolinfo.com/mcp?api_key={api_key} over streamable HTTP, and it listed its tools to an anonymous client, so no sign-in was needed for that. Our probes reached it 10 of 10 times since 5 September 2026; the last check, on 18 October 2026, succeeded.
Amazon data MCP: products, reviews, niches, WIPO design/IP + US litigation, AI search & trends.
Description as the publisher wrote it.
| Tool | What it does |
|---|---|
ai_search | [AI Search via Google SERP] Scrape publicly-available Google search results (data source: Google; use must comply with Google Terms of Service) with top AI Overview, organic results, and related searches. Two modes: overview (standard SERP) Inputs: query, mode, followups, screenshot, clientSource |
filter_categories | [Amazon category commercial-metrics filter] Filter categories by dozens of metrics (sales, GMS, search volume, conversion, return rate, price tier, competitor density, …) — or use as a "category detail" endpoint by passing a single category Inputs: marketplaceId, timeRange, sampleScope, categoryId, page, size |
filter_niches | [Amazon niche filter] Filter Amazon Niches (a finer-grained "demand cluster" than categories) by 50+ commercial metrics, or use as a "niche detail" endpoint for one niche. Use when: user says "find blue ocean" / "high search volume + low co Inputs: marketplaceId, nicheId, nicheTitle, page, size, sortField |
get_amazon_delivery_time | [Amazon Delivery Time] Return the full listing detail for one ASIN plus address-dependent delivery estimates. Use when: the user explicitly needs estimated arrival, free vs paid delivery timing, the fastest option, handling lead time, or th Inputs: asin, site, zipcode, clientSource |
get_amazon_product | [Amazon single-product detail] Scrape the full PDP for one ASIN. Use when: user supplies a specific ASIN ("look at B0XXXXXXXX" / "check this product's price/rating/seller" / "analyse this competitor"); or as a SOP step after candidate ASINs Inputs: asin, site, zipcode, format, clientSource |
get_amazon_reviews | [Amazon review batch scrape] Page-fetch real buyer reviews for an ASIN. Filterable by star / sort / media type. Use when: user says "look at X's negative reviews" / "mine pain points" / "analyse competitor reviews" / "do VOC" / "find user c Inputs: asin, site, pageCount, filterByStar, sortBy, mediaType |
get_category_children | [Amazon category tree drilldown] List direct children from any node (or omit parent to start at the roots). Use when: user says "show me Amazon's category tree" / "subcategories under X" / "list top-level departments" / "drill to level 3"; Inputs: parentBrowseNodeIdPath, page, size, clientSource |
get_category_paths | [Amazon category breadcrumb resolver] Batch-resolve categoryId list to full paths (e.g. 'Electronics > Headphones > Over-Ear Headphones'). Use when: a report needs readable category context (not bare IDs); user has a list of numeric IDs and Inputs: categoryIds, site, clientSource |
keyword_trends | [Keyword Trends via Google Trends] Keyword popularity (data source: Google Trends; use must comply with Google Terms of Service). Time series + per-region heatmap + rising related queries (with 'Breakout' tags). Compare up to 5 keywords on Inputs: keywords, timeRange, region, language, clientSource |
list_bestsellers | [Amazon Best Sellers] Top-50 ranking for a category with 24h rank deltas. Use when: user says "X category bestsellers" / "who's #1 in X" / "any new entrants climbing" / "benchmark top sellers"; setting baseline products during niche scoutin Inputs: categorySlug, site, zipcode, format, clientSource |
list_category_products | [Amazon category listing] List concrete on-sale products under a Browse Node ID (paginated, 24 rows/page). Use when: user says "what's selling in category X" / "list products in node 12345" / "show me what's in this category"; after picking Inputs: nodeId, site, zipcode, format, page, clientSource |
list_new_releases | [Amazon New Releases] Best-selling Top-50 ASINs that hit the market within the last 30 days for a category (backend cap; not 100). Use when: user says "new arrivals in X" / "any breakout new products" / "newly-launched that sell well" / "tr Inputs: categorySlug, site, zipcode, format, clientSource |
list_seller_products | [Amazon seller storefront] List all listings under a merchant ID, paginated (24 rows/page). Use when: user says "show me this seller's products" / "how many SKUs does store X carry" / "competitor storefront category breadth" / "what is this Inputs: sellerId, site, zipcode, format, page, pageCount |
pangolinfo_capabilities | [Pangolinfo MCP self-introspection] One call to get the full capability catalog, canonical workflows, and usage tips — no backend call, free. Use when: an AI client first connects to pangolinfo-mcp and needs to quickly grasp "what tools exi Inputs: detail, clientSource |
scrape_url | [Generic Amazon scrape — power-user escape hatch] Scrape pages the 5 purpose-built tools don't cover. Two input modes (pick one): ① content=bare fragment (keyword / nodeId / sellerId / ASIN) + site — backend builds a basic URL per parserNam Inputs: parserName, content, url, site, format, zipcode |
search_amazon | [Amazon SERP scrape] Run a real Amazon keyword search and return the first-page ASIN list. Use when: user says "search Amazon for X" / "who sells X" / "top results for keyword X" / "competitors for X"; or you need a list of ASINs for a keyw Inputs: keyword, site, zipcode, format, page, clientSource |
search_amazon_alexa | [Amazon Rufus AI conversational recommendations] Ask Amazon's AI shopping assistant Rufus in natural language, get grouped structured product recommendations + Rufus text reply + follow-up questions. Use when: user says "ask Amazon AI X" / Inputs: prompts, screenshot, clientSource |
search_categories | [Amazon category search] Match Amazon's category tree by keyword (Chinese or English) and return candidate nodes. Use when: user gave a keyword/concept rather than a category id, and a downstream tool needs categoryId / browseNodeId (e.g. f Inputs: keyword, site, clientSource |
search_local_maps | [Local Maps via Google Maps] Local-business search (data source: Google Maps; use must comply with Google Terms of Service). Search local businesses at a given lat/lng — returns name, address, rating, review count, etc. Use when: user says Inputs: query, latitude, longitude, zoom, language, limit |
wipo_search | [Design Patent TRO risk control · WIPO global design / IP search] Query the WIPO design database across 12 sources (USPTO US designs, CNID China, HAGUE international registrations, …), with one-click chaining to US design-patent TRO (tempor Inputs: source, ds, hol, prod, irn, id |
Every block below points at https://mcp.pangolinfo.com/mcp?api_key={api_key}. Pick your client and copy.
claude mcp add --transport http amazon https://mcp.pangolinfo.com/mcp?api_key={api_key}{
"mcpServers": {
"amazon": {
"command": "npx",
"args": ["-y", "mcp-remote", "https://mcp.pangolinfo.com/mcp?api_key={api_key}"]
}
}
}{
"mcpServers": {
"amazon": {
"url": "https://mcp.pangolinfo.com/mcp?api_key={api_key}"
}
}
}{
"servers": {
"amazon": {
"type": "http",
"url": "https://mcp.pangolinfo.com/mcp?api_key={api_key}"
}
}
}{
"context_servers": {
"amazon": {
"url": "https://mcp.pangolinfo.com/mcp?api_key={api_key}"
}
}
}{
"mcpServers": {
"amazon": {
"serverUrl": "https://mcp.pangolinfo.com/mcp?api_key={api_key}"
}
}
}{
"mcpServers": {
"amazon": {
"url": "https://mcp.pangolinfo.com/mcp?api_key={api_key}"
}
}
}name: Amazon
version: 0.0.1
schema: v1
mcpServers:
- name: Amazon
type: streamable-http
url: https://mcp.pangolinfo.com/mcp?api_key={api_key}{
"mcpServers": {
"amazon": {
"httpUrl": "https://mcp.pangolinfo.com/mcp?api_key={api_key}"
}
}
}{
"mcpServers": {
"amazon": {
"type": "http",
"url": "https://mcp.pangolinfo.com/mcp?api_key={api_key}"
}
}
}{
"mcpServers": {
"amazon": {
"url": "https://mcp.pangolinfo.com/mcp?api_key={api_key}"
}
}
}goose://extension?url=https%3A%2F%2Fmcp.pangolinfo.com%2Fmcp%3Fapi_key%3D%7Bapi_key%7D&type=streamable_http&id=amazon&name=Amazon
It answered our last check on 18 October 2026 in 810 ms. Over 10 checks since 5 September 2026 it answered 10. Status here comes from Neuronto's own probes, not from the publisher.
Yes. It is published by pangolinfo.com and served from mcp.pangolinfo.com, the vendor's own domain: https://mcp.pangolinfo.com/mcp?api_key={api_key}.
20, as returned by the server's own tools/list on 31 August 2026: ai_search, filter_categories, filter_niches, get_amazon_delivery_time, get_amazon_product, get_amazon_reviews, get_category_children, get_category_paths, and 12 more.
It answered our last check on 18 October 2026 in 810 ms. Over 10 checks since 5 September 2026 it answered 10.
Put the server under mcpServers in ~/.cursor/mcp.json with the URL https://mcp.pangolinfo.com/mcp?api_key={api_key}. The exact JSON is above, with the same setup for Claude Code, Claude Desktop, VS Code, Windsurf, Zed, Gemini CLI and the rest.
It listed its tools to an anonymous client, so reading the tool list needs no key. Individual tools can still ask for credentials in their own inputs.
Publisher: com.pangolinfo. Endpoint host: mcp.pangolinfo.com. ARD identifier: urn:air:com.pangolinfo:mcp:amazon-mcp.
First indexed 31 August 2026. The tools are exactly what the server returned; nothing on this page
is inferred from its name. Ranking in Neuronto search is never for sale.