Data Collection
apiguru.app
Provides tools to fetch Amazon product data including details, reviews, search results, and stock offers.
ENDPOINT 1
https://mcp.apiguru.app/mcp
MCP server metadata
- Name
- apiguru
- Version
- 1.0.0
Apiguru returns live, structured Amazon marketplace data across 20 country marketplaces. Data is fetched at request time, not served from a cache. Choosing a tool: - One ASIN, full record -> product_details - Many ASINs (up to 20) -> product_details_batch (cheaper per item) - Reviews and rating breakdown -> product_reviews - Keyword discovery -> search - Offers, buy box, live stock -> offers_stock - Category rankings -> best_sellers - Discounted items -> deals - Seller storefront / reputation -> seller_products, seller_reviews, seller_profile_batch Rules that will save you money and failed calls: - ASINs must be 10 UPPERCASE alphanumeric characters. Normalise before calling. - Prefer the batch tools over looping single-item tools. - A 404 means the item is genuinely absent from that marketplace. It IS billed and retrying will not help - try a different geo instead. - A 503 is an Apiguru-side failure. It is NOT billed and should be retried. - Call list_capabilities first if you need prices or the marketplace list; it is free and makes no network request.
Known tools 11
product_detailsFetches the complete product record for one ASIN on one marketplace: title, price, star rating, rating count, images, description, feature bullets, variations and category.
Inferred read-onlyproduct_reviewsReturns the review block for one ASIN: overall star rating, total rating count, Amazon's 'customers say' AI summary, and the individual review list.
Inferred read-onlysearchKeyword search with pagination, sorting, and filtering by category, price range, condition, brand or seller.
Inferred read-onlyoffers_stockReturns the current offer list per ASIN (seller, price, condition, buy-box winner) and, optionally, the actual purchasable stock quantity.
Inferred read-onlybest_sellersReturns the current Amazon best-seller list for a category, with optional subcategory drill-down and pagination.
Inferred read-onlydealsReturns active Amazon deals, filterable by category, brand, minimum star rating, price band, discount band, and Prime early access.
Inferred read-onlyseller_profile_batchReturns the storefront profile for each seller id: business name, rating, feedback counts, address and marketplace presence.
Inferred read-onlyseller_productsReturns the paginated catalogue of products offered by a given seller storefront.
Inferred read-onlyseller_reviewsReturns paginated seller feedback, optionally filtered to a star-rating window.
Inferred read-onlylist_capabilitiesList every Apiguru endpoint with its price, required parameters and supported marketplaces.
Inferred read-onlyCONNECT WITH APPROVAL
Client installation
Review this server and its permissions before adding it. Secret placeholders must be set locally.
Codex
~/.codex/config.toml
[mcp_servers.apiguru]
url = "https://mcp.apiguru.app/mcp"
enabled = true
Claude Code
.mcp.json
{
"mcpServers": {
"apiguru": {
"type": "http",
"url": "https://mcp.apiguru.app/mcp"
}
}
}
Claude Desktop
Settings → Connectors → Add custom connector
Name: apiguru
Remote MCP URL: https://mcp.apiguru.app/mcp
Add this remote URL as a custom connector in Claude Desktop. Availability depends on the user plan and workspace policy.
Cursor
.cursor/mcp.json
{
"mcpServers": {
"apiguru": {
"url": "https://mcp.apiguru.app/mcp"
}
}
}
Visual Studio Code
.vscode/mcp.json
Add to Visual Studio Code{
"servers": {
"apiguru": {
"type": "http",
"url": "https://mcp.apiguru.app/mcp"
}
}
}
Generic MCP
Client-specific MCP configuration
{
"name": "apiguru",
"transport": "streamable-http",
"url": "https://mcp.apiguru.app/mcp"
}
MCP Inspector
Run the official MCP Inspector locally and enter the indexed Streamable HTTP endpoint.
TRUST AND VERIFICATION EVIDENCE
Loading Trust v2 evidence…
Checking the associated registrable domain. The BuiltWith key remains server-side.
Evidence is source-attributed and does not guarantee that a third-party server is safe. Risk labels are conservative metadata heuristics.