Microlink

liveTechnologyDeveloper

Extract metadata and take screenshots of any webpage via Microlink

2tools
0msauth
free tier50 calls/day

Tools

get_metadatarequired: url

Extract metadata from any URL to preview page content. Returns title, description, image, author, publisher, logo, and structured data—useful when you need to understand a webpage without visiting it

Parameters
NameTypeDescription
urlreqstringThe URL to extract metadata from.
▶Try it
take_screenshotrequired: url

Capture a screenshot of any webpage. Returns image URL showing the rendered page layout and visual content—use to verify page state or design.

Parameters
NameTypeDescription
urlreqstringThe URL of the webpage to screenshot.
▶Try it

Test with curl

The gateway speaks JSON-RPC 2.0 over HTTP POST. You can test any pack directly from the terminal.

List available tools
bash
curl -X POST https://gateway.pipeworx.io/microlink/mcp \
  -H "Content-Type: application/json" \
  -d '{"jsonrpc":"2.0","id":1,"method":"tools/list"}'
Call a tool
bash
curl -X POST https://gateway.pipeworx.io/microlink/mcp \
  -H "Content-Type: application/json" \
  -d '{"jsonrpc":"2.0","id":2,"method":"tools/call","params":{"name":"get_metadata","arguments":{"url": "https://example.com"}}}'

Use with the SDK

Install @pipeworx/sdk to call tools from any TypeScript/Node project.

TypeScript
import { Pipeworx } from '@pipeworx/sdk';
const px = new Pipeworx();
const result = await px.call("get_metadata", {"url":"example"});
ask_pipeworx
// Or ask in plain English:
const answer = await px.ask("extract metadata and take screenshots of any webpage via microlink");