--- title: "Ecommerce MCP server and product data API for AI agents" url: https://www.datawebot.com/ description: "Give your agent product search across the world's shops, in local languages and currencies, plus extraction Jobs for Amazon, Walmart and brand stores. Free to try." author: datawebot team --- [**New:** paste any product link to check its store →](https://www.datawebot.com/endpoints) # PRODUCT SEARCH FOR AI AGENTS The world's shops. One MCP server. - search in any country, in its own language - every seller's price for a product - store catalogues, as structured data You get the data. Give this to your agent `set up https://mcp.datawebot.com/setup.md` Or connect it yourself - - - - - - - - - [Using Claude.ai or ChatGPT? Add it as a connector →](https://www.datawebot.com/docs/agents#connect-chatgpt) Shopee Flipkart eBay Walmart AliExpress Tokopedia Etsy Rakuten Target Mercado Libre Taobao Blibli ASOS Otto ![datawebot](https://www.datawebot.com/images/commerce/brand-icon.png) datawebot Brooks Revel 8 Running $84.97 ★ 4.6 Amazon Shopee Flipkart eBay AliExpress Etsy Rakuten Shopee Flipkart eBay AliExpress Etsy Rakuten Shopee Flipkart eBay AliExpress Etsy Rakuten Tokopedia Target Blibli Mercado Libre Walmart ASOS Taobao Otto Target Blibli Mercado Libre Walmart ASOS Taobao Otto Target Blibli Mercado Libre Walmart ASOS Taobao Otto Real results ## Ask in plain words. Get products from real shops. Find running shoes under $100 that I can buy in the US. Show them as cards with price and shop. `search_products({"query":"running shoes under $100","country":"US"})` 1. adidas Men's Adizero Pacer Running Shoes **$80.00** · adidas 2. Brooks Men's Revel 8 Running **$84.97** · DICK'S Sporting Goods 3. Merrell Men's Agility Trail **$49.00** · Sierra 4. Nike Men's Revolution 8 Running Shoe **$52.49** · Famous Footwear `search_products({"query":"4 person camping tent","country":"GB"})` 1. Eurohike Sendero 4 Family Tent **£100.00** · Amazon.co.uk 2. Pro Action 4 Person 1 Room Tunnel Camping Tent **£80.00** · Argos 3. Halfords 4 Person Vis A Vis Tent XL **£50.00** · Halfords 4. Decathlon 4 Man Tent **£119.99** · Decathlon UK `search_products({"query":"電動歯ブラシ 本体","country":"JP"})` 1. ライオン 電動アシストブラシ 電池式 歯ブラシ 本体 +フロス付き **¥2,078** · Amazon公式サイト 2. Braun ブラウン オーラルB プラックコントロール DB5010N **¥1,728** · Yahoo!ショッピング - サンドラッグe-shop 3. 本体 ライオン **¥1,980** · カインズ 4. ブラウン BRAUN 電動歯ブラシ Oral-B プロ600 ブラック D165131UBK **¥6,980** · ソフマップ・ドットコム Real result · retrieved 23 Oct 2026 · [See all prompts](https://www.datawebot.com/prompts) Works where you build ## In your agent today. In your product tomorrow. Same tools, two ways in. No new SDK to learn. Agent session ``` You I need a 4 person camping tent from a UK shop. Show a few options with prices. Agent search_products {"query":"4 person camping tent","country":"GB"} → Eurohike Sendero 4 Family Tent · £100.00 · Amazon.co.uk → Pro Action 4 Person 1 Room Tunnel Camping Tent · £80.00 · Argos → Halfords 4 Person Vis A Vis Tent XL · £50.00 · Halfords → Decathlon 4 Man Tent · £119.99 · Decathlon UK (retrieved 23 Oct 2026) ``` Connect once with the setup prompt above. Your agent calls the tools when your request needs them. ``` # pip install mcp import asyncio, os from mcp import ClientSession from mcp.client.streamable_http import streamablehttp_client async def main(): headers = {"Authorization": f"Bearer {os.environ['DATAWEBOT_API_KEY']}"} async with streamablehttp_client("https://mcp.datawebot.com/mcp", headers=headers) as (read, write, _): async with ClientSession(read, write) as session: await session.initialize() result = await session.call_tool("search_products", {"query":"4 person camping tent","country":"GB"}) print(result.content[0].text) asyncio.run(main()) ``` Create a key on the [dashboard](https://www.datawebot.com/dashboard?view=api-keys). LangChain, the OpenAI Agents SDK, the Vercel AI SDK and n8n work the same way: point their MCP client at the server with your key. ``` curl https://api.datawebot.com/v1/jobs \ -H "Authorization: Bearer $DATAWEBOT_API_KEY" \ -H "Idempotency-Key: amazon-coffee-0001" \ -H "Content-Type: application/json" \ -d '{"blueprint_id":"amazon.search_items","url":"https://www.amazon.com/s?k=coffee","parameters":{"max_pages":1}}' # Then poll GET /v1/jobs/{job_id} until it finishes, # and read GET /v1/jobs/{job_id}/results, following next_cursor. ``` One Job is one URL. See the [API reference](https://www.datawebot.com/docs/api/reference) for statuses, errors and limits. Jobs ## When you need whole pages, not a few results. Extraction Jobs return every product on a store's page as structured records, from Amazon and Walmart to brand stores. Run them from your agent or the REST API. **Search results** Amazon and Walmart search pages for your keyword; brand stores return up to 10 matching products. **Store catalogues** A brand store's products with variants and prices, up to 250 a Job. **Product pages** One product in full, with options, prices and availability. - [Fashion and apparel](https://www.datawebot.com/endpoints?category=fashion#browse-stores) - [Footwear](https://www.datawebot.com/endpoints?category=footwear#browse-stores) - [Bags, jewelry and accessories](https://www.datawebot.com/endpoints?category=accessories#browse-stores) - [Beauty and personal care](https://www.datawebot.com/endpoints?category=beauty#browse-stores) - [Health and wellness](https://www.datawebot.com/endpoints?category=health#browse-stores) - [Home and furniture](https://www.datawebot.com/endpoints?category=home#browse-stores) - [Kitchen, food and drink](https://www.datawebot.com/endpoints?category=food#browse-stores) - [Electronics and gadgets](https://www.datawebot.com/endpoints?category=electronics#browse-stores) - [Sports and outdoors](https://www.datawebot.com/endpoints?category=sports#browse-stores) - [Baby, kids and toys](https://www.datawebot.com/endpoints?category=kids#browse-stores) - [Pets](https://www.datawebot.com/endpoints?category=pets#browse-stores) - [Books, art, music and hobbies](https://www.datawebot.com/endpoints?category=hobbies#browse-stores) - [Automotive, tools and equipment](https://www.datawebot.com/endpoints?category=automotive#browse-stores) - [Other or general merchandise](https://www.datawebot.com/endpoints?category=general#browse-stores) **Export a store's catalogue to CSV:** one Job returns the store's products with their variants and prices, page by page. 5 credits per search or catalogue page, 1 per product page; failed Jobs are free. ### Search the stores your agent can extract Search endpoints Type a store name or domain, e.g. amazon.de. [Browse the store catalogue](https://www.datawebot.com/endpoints) [Browse every store](https://www.datawebot.com/endpoints) · [Jobs API reference](https://www.datawebot.com/docs/api/reference) How it works ## From setup to your next step. Connect your coding agent, approve access, then ask for the product data you need. 1. 01 ### Give your agent the setup prompt. Use a coding agent with a terminal and remote MCP support. The [setup instructions](https://mcp.datawebot.com/setup.md) guide the connection. 2. 02 ### Approve access in your inbox. Check the sign-in code and approve your agent. Sign-up is free and open to anyone; no API keys pasted into chat. 3. 03 ### Ask. Inspect. Put it to work. Ask for products across online shops, compare seller offers with direct links, and keep the retrieval time with each result. Search results are best-effort snapshots, not verified live prices. Amazon in 10 countries, Walmart and brand stores run as extraction Jobs, open to every account with 200 free trial credits. See every [supported store](https://www.datawebot.com/endpoints). Pricing ## Free to try. Pay only for Jobs. Search and seller offers **Free**Within a daily allowance per account. Jobs, to start **200 credits**Free trial credits for every account. Jobs, after that **From $10**Credit packs with no subscription. Credits don't expire. [See pricing](https://www.datawebot.com/pricing) [Catalogue to CSV →](https://www.datawebot.com/solutions/catalog-to-csv) · [Price monitoring →](https://www.datawebot.com/learn/price-monitoring-guide-for-ecommerce) · [Amazon product data →](https://www.datawebot.com/scraper/amazon) · [Agentic commerce →](https://www.datawebot.com/solutions/agentic-commerce) · [All store guides →](https://www.datawebot.com/ecommerce) FAQ ## A few useful answers. Which agents can I connect? Claude Code, Codex, Cursor, opencode, ChatGPT, Claude.ai and any MCP client. Coding agents take the setup prompt; chat apps add https://mcp.datawebot.com/mcp as a connector. From your own code, use any MCP client with an API key. Which shops does search cover? Online shops worldwide, through product search in the country you choose. Coverage differs by country and product. Which sites can my agent extract? Amazon in 10 countries, Walmart and brand stores: more than 11,000 online stores in all. Every one is listed on the endpoints page. Do I need an API key? Not in your agent: sign in by email, free and open to anyone. For your own code, create a key on the dashboard. What does it cost? Search and seller offers are free within a daily allowance per account. Jobs use credits: 200 free, then packs from $10. Does datawebot track prices over time? No. Each call is a dated snapshot; your agent or app keeps the history. Are sponsored results included in search? No. Results the provider marks as sponsored or promoted are left out of search and seller offers. When your query includes a model code, such as WH-1000XM5, results for other models are left out; if nothing matches, all results are shown and the summary says so. Do the logos mean every source is supported? No. The logos illustrate ecommerce breadth, not partnerships or live integrations. Product search returns best-effort listings from online shops. Extraction covers the sites in the endpoint catalogue.