Amazon Brazil MCP server for AI agents
Let Claude, ChatGPT or your own agent read Amazon Brazil: 2 typed functions through one MCP server. No Amazon Brazil API key needed.
- Site
- amazon.com.br
- Functions
- 2
- Sign-in
- Not needed
- Works with
- MCP, HTTP, Node, Python
Connect
Just Amazon Brazil
An MCP server for Amazon Brazil alone, with one tool per function. Paste it into Claude, ChatGPT, Cursor or any MCP client as a remote server.
https://api.bowmark.ai/mcp/site/amazon_brEvery site
One MCP server for Amazon Brazil and every other site Bowmark covers. Your agent looks up what it needs and calls it.
https://api.bowmark.ai/mcpSet it up in your clientBoth need a Bowmark API key. The quickstart gets you one and a first result in a few minutes.
Functions
Open a function to see its arguments, what it returns and how to call it.
Read 2
getProductGet an amazon.com.br product's title, BRL price, rating and stock text by ASIN or product URL.Arguments
Name Type Required args{ asin?: string; url?: string }Yes Returns
AmazonBrProductDetailinterface AmazonBrProductDetail { asin: string; title: string; url: string; price: number | null; // BRL currency: "BRL"; rating: number | null; ratingCount: number | null; availability: string | null; // Amazon's own labels, read the value off a result, never guess one from prose. inStock: boolean; }HTTP endpoint
POST https://api.bowmark.ai/v1/sites/amazon_br/getProductCall it
import { bowmark } from "@bowmark/web"; const result = await bowmark.providers.amazon_br.getProduct({ asin: "B0DM9944L8" });import asyncio from bowmark_web import bowmark result = asyncio.run(bowmark.providers.amazon_br.getProduct({"asin": "B0DM9944L8"}))curl -X POST https://api.bowmark.ai/v1/sites/amazon_br/getProduct \ -H "Authorization: Bearer $BOWMARK_API_KEY" \ -H "Content-Type: application/json" \ -d '{"args":{"asin":"B0DM9944L8"}}'// The body of a run: the MCP run tool, or POST /v1/run return await bowmark.providers.amazon_br.getProduct({ asin: "B0DM9944L8" });searchProductsSearch amazon.com.br for products by keywords (or a pasted /s?k= URL) with BRL price, rating and rating count.Arguments
Name Type Required args{ keywords?: string; query?: string; url?: string; page?: number }Yes Returns
AmazonBrSearchResultinterface AmazonBrProduct { asin: string; title: string; url: string; price: number | null; // BRL rating: number | null; ratingCount: number | null; sponsored: boolean; } interface AmazonBrSearchResult { products: AmazonBrProduct[]; totalResultCount: number; // Amazon's "mais de N resultados" floor }HTTP endpoint
POST https://api.bowmark.ai/v1/sites/amazon_br/searchProductsCall it
import { bowmark } from "@bowmark/web"; const result = await bowmark.providers.amazon_br.searchProducts({ keywords: "notebook" });import asyncio from bowmark_web import bowmark result = asyncio.run(bowmark.providers.amazon_br.searchProducts({"keywords": "notebook"}))curl -X POST https://api.bowmark.ai/v1/sites/amazon_br/searchProducts \ -H "Authorization: Bearer $BOWMARK_API_KEY" \ -H "Content-Type: application/json" \ -d '{"args":{"keywords":"notebook"}}'// The body of a run: the MCP run tool, or POST /v1/run return await bowmark.providers.amazon_br.searchProducts({ keywords: "notebook" });
Use it from code
- Node
npm i @bowmark/web - Python
pip install bowmark-web - HTTP
POST /v1/sites/amazon_br/<function> - OpenAPI
/v1/sites/amazon_br/openapi.json