What it can do

Search Products: Search products using natural language across ~8.5M products from 2,500+ Central European e-shops. Returns a dict with 'results' (list of product objects) and 'total_found' (int). Eac

Lookup By Gtin: Look up products by exact GTIN/EAN/UPC barcode across all indexed e-shops. Returns a dict with 'results' (list of product objects) and 'total_found' (int). Each product contains: title

Search Products By Text: Search products by exact keyword matching in titles across ~8.5M products from 2,500+ e-shops. Returns a dict with 'results' (list of product objects) and 'total_found' (int).

Shoptera Product Intelligence Search product catalogs across thousands of Central European e-shops. Semantic search, keyword matching, GTIN/EAN lookup — via REST API or MCP.

~2,500 e-shops | ~8.5M products | 7 countries (CZ, SK, PL, HU, RO, DE, AT)

Live stats: GET /stats/global

Quickstart No authentication required. Base URL: https://shoptera.ai/api

Semantic search — natural language, understands intent:

curl "https://shoptera.ai/api/v1/search?q=dárek+pro+zahradníka+do+500+Kč&max_price=500&currency=CZK&origin_country=CZ" Keyword search — exact title matching, fast:

curl "https://shoptera.ai/api/v1/search/text?title=Nike+Air+Max+90&brand=Nike" GTIN/EAN lookup — find e-shops by barcode:

curl "https://shoptera.ai/api/v1/search/gtin/5901234123457" Saving tokens: Add fields to return only what you need (up to 70% smaller response):

curl "https://shoptera.ai/api/v1/search?q=boty&limit=5&fields=title,price,product_url,cart_action" Quick Install Claude Code (one command) claude mcp add --transport http shoptera https://shoptera.ai/api/mcp Cursor Add to Cursor Settings → Features → MCP → Add New MCP Server, or edit ~/.cursor/mcp.json:

{ "mcpServers": { "shoptera": { "url": "https://shoptera.ai/api/mcp" } } } Windsurf Add via Cascade → MCP Servers → Add Server, or edit ~/.codeium/windsurf/mcp_config.json:

{ "mcpServers": { "shoptera": { "url": "https://shoptera.ai/api/mcp" } } } VS Code (Copilot / Continue) Edit .vscode/mcp.json in your workspace:

{ "mcpServers": { "shoptera": { "url": "https://shoptera.ai/api/mcp" } } } Any tool (universal installer) npx add-mcp https://shoptera.ai/api/mcp -n shoptera -g -y All Platforms Platform Setup Details Claude Code claude mcp add --transport http shoptera https://shoptera.ai/api/mcp Skill guide Cursor MCP config Settings → Features → MCP Windsurf MCP config Cascade → MCP Servers VS Code MCP config .vscode/mcp.json OpenAI Codex AGENTS.md Agent config reference ChatGPT OpenAPI spec Custom GPT actions. Instructions Gemini GEMINI.md Tool definitions and endpoints Any HTTP client Examples curl, Python, JavaScript MCP Details Endpoint: https://shoptera.ai/api/mcp (streamable HTTP, stateless, no auth)

3 tools: search_products, search_products_by_text, lookup_by_gtin

Capabilities Product Search — semantic vs keyword vs GTIN, when to use which, filters, scoring Cart Actions — three action types, how to handle each Data Coverage — countries, data freshness, live stats API Reference Full documentation: api/reference.md

OpenAPI spec: api/openapi.yaml

Endpoints Method Path Description GET /api/v1/search?q=... Semantic search (natural language) GET /api/v1/search/text?title=... Keyword search (exact title match) GET /api/v1/search/gtin/{gtin} GTIN/EAN barcode lookup GET /stats/global Catalog statistics Code Examples Semantic search — curl, Python, JavaScript Keyword search — curl, Python, JavaScript GTIN/EAN lookup — curl, Python, JavaScript Cart actions — handling all three action types

Shoptera

What it can do

What data it sees

Do you need an account

search_products	Search products using natural language across ~8.5M products from 2,500+ Central European e-shops. Returns a dict with 'results' (list of product objects) and 'total_found' (int). Each product contains: title, description, price, currency, brand, category, gtin, image_url, product_url, availability, eshop_name, eshop_domain, origin_country, target_countries, score (0-1 relevance), and cart_action. The cart_action object tells you how to add the product to cart: - method="GET": navigate to cart_action.url — product is added automatically. - method="browser_click": navigate to cart_action.url, then click the button matching cart_action.button_text. - method="view_product": show the product page URL to the user. Use 'fields' parameter to return only needed fields and save tokens. Prefer this tool for open-ended queries. Use search_products_by_text when you know the exact product name, or lookup_by_gtin when you have a barcode number.
lookup_by_gtin	Look up products by exact GTIN/EAN/UPC barcode across all indexed e-shops. Returns a dict with 'results' (list of product objects) and 'total_found' (int). Each product contains: title, description, price, currency, brand, category, gtin, image_url, product_url, availability, eshop_name, eshop_domain, origin_country, target_countries, and cart_action. The cart_action object tells you how to add the product to cart: - method="GET": navigate to cart_action.url — product is added automatically. - method="browser_click": navigate to cart_action.url, then click the button matching cart_action.button_text. - method="view_product": show the product page URL to the user. Use this tool when you have a barcode number and want to compare prices across e-shops. For natural language queries, use search_products instead.
search_products_by_text	Search products by exact keyword matching in titles across ~8.5M products from 2,500+ e-shops. Returns a dict with 'results' (list of product objects) and 'total_found' (int). Each product contains: title, description, price, currency, brand, category, gtin, image_url, product_url, availability, eshop_name, eshop_domain, origin_country, target_countries, and cart_action. The cart_action object tells you how to add the product to cart: - method="GET": navigate to cart_action.url — product is added automatically. - method="browser_click": navigate to cart_action.url, then click the button matching cart_action.button_text. - method="view_product": show the product page URL to the user. Faster and more deterministic than semantic search. Use this when you know the exact product name. For open-ended natural language queries, use search_products instead.