zyte 3 tools

MCP server exposing 3 tools for zyte.

Endpoint

This URL is a JSON-RPC 2.0 endpoint over HTTP. Issue POST requests with a JSON-RPC body. Browsers and search crawlers land here on GET.

POST https://gateway.pipeworx.io/zyte/mcp
Content-Type: application/json

{"jsonrpc":"2.0","id":1,"method":"tools/list"}

zyte_fetch — Fetch a web page through Zyte API and return its content. By default returns the raw HTTP response body (decoded to text). For JS-heavy sites that need a real browser, pass render:true to get browser-rendered HTML instead. Example: zyte_fetch({ url: "https://example.com", _apiKey: "your-key" })
zyte_extract — AI-powered automatic extraction of structured data from a web page. Set type to 'product' for e-commerce product pages (name, price, currency, images, SKU, availability...) or 'article' for news/blog pages (headline, author, date, body text...). Example: zyte_extract({ url: "https://shop.example.com/item/123", type: "product", _apiKey: "your-key" })
zyte_screenshot — Capture a screenshot of a web page via Zyte API (rendered in a headless browser). Returns metadata about the base64-encoded PNG (its length) rather than inlining the full blob. Example: zyte_screenshot({ url: "https://example.com", _apiKey: "your-key" })

Code samples (curl / TypeScript / one-click client install), schemas, and the live playground are on the pack page:
https://pipeworx.io/packs/zyte/

Pipeworx is an open MCP gateway connecting AI agents to live data. pipeworx.io