Zyte API
live Web ScrapingDeveloper ToolsZyte MCP — single-endpoint web data: HTTP or headless fetch with auto anti-ban, plus automatic product/article structured extraction. BYO Zyte API key.
Tools
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-
No parameters required.
Try it
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
No parameters required.
Try it
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_screensho
No parameters required.
Try it
Test with curl
The gateway speaks JSON-RPC 2.0 over HTTP POST. You can test any pack directly from the terminal.
curl -X POST https://gateway.pipeworx.io/zyte/mcp \
-H "Content-Type: application/json" \
-d '{"jsonrpc":"2.0","id":1,"method":"tools/list"}' curl -X POST https://gateway.pipeworx.io/zyte/mcp \
-H "Content-Type: application/json" \
-d '{"jsonrpc":"2.0","id":2,"method":"tools/call","params":{"name":"zyte_fetch","arguments":{}}}' Use with the SDK
Install @pipeworx/sdk to call tools from any TypeScript/Node project.
import { Pipeworx } from '@pipeworx/sdk';
const px = new Pipeworx();
const result = await px.call("zyte_fetch", {}); // Or ask in plain English:
const answer = await px.ask("zyte mcp — single-endpoint web data: http or headless fetch with auto anti-ban, plus automatic product/article structured extraction"); Related packs
Other Pipeworx packs in the same categories (Web Scraping, Developer Tools):