GET/extract

Extract clean content from a URL

Fetches the URL and returns the main article content, with navigation, scripts, styles and boilerplate removed.

Set format to markdown (default) to preserve headings, lists, code blocks and links; text for plain prose with no markup; or html for the cleaned HTML fragment. Page metadata — title, description, author, publication date, site name and language — is returned alongside the content when the page declares it.

$0.002 per call60 req/minFree allowance applies

Request

curl -X GET "https://www.twotic.dev/v1/web-extract/extract" \
  -H "Authorization: Bearer $TWOTIC_KEY"

const res = await fetch("https://www.twotic.dev/v1/web-extract/extract", {
  method: "GET",
  headers: {
    Authorization: `Bearer ${process.env.TWOTIC_KEY}`,
  },
})

if (!res.ok) throw new Error(await res.text())

const data = await res.json()
console.log(res.headers.get("X-Twotic-Cost"))

import os, requests

res = requests.get(
    "https://www.twotic.dev/v1/web-extract/extract",
    headers={"Authorization": f"Bearer {os.environ['TWOTIC_KEY']}"},
)
res.raise_for_status()

data = res.json()
print(res.headers["X-Twotic-Cost"])

package main

import (
	"fmt"
	"io"
	"net/http"
	"os"
)

func main() {
	req, _ := http.NewRequest("GET", "https://www.twotic.dev/v1/web-extract/extract", nil)
	req.Header.Set("Authorization", "Bearer "+os.Getenv("TWOTIC_KEY"))

	res, err := http.DefaultClient.Do(req)
	if err != nil {
		panic(err)
	}
	defer res.Body.Close()

	out, _ := io.ReadAll(res.Body)
	fmt.Println(string(out))
	fmt.Println(res.Header.Get("X-Twotic-Cost"))
}

<?php
$ch = curl_init("https://www.twotic.dev/v1/web-extract/extract");
curl_setopt_array($ch, [
    CURLOPT_RETURNTRANSFER => true,
    CURLOPT_CUSTOMREQUEST  => "GET",
    CURLOPT_HTTPHEADER     => [
        "Authorization: Bearer " . getenv("TWOTIC_KEY"),
    ],
]);

$data = json_decode(curl_exec($ch), true);
curl_close($ch);
print_r($data);

require "net/http"
require "json"

uri = URI("https://www.twotic.dev/v1/web-extract/extract")
req = Net::HTTP::Get.new(uri)
req["Authorization"] = "Bearer #{ENV.fetch('TWOTIC_KEY')}"

res = Net::HTTP.start(uri.hostname, uri.port, use_ssl: uri.scheme == "https") do |http|
  http.request(req)
end

puts JSON.parse(res.body)
puts res["X-Twotic-Cost"]

{
  "mcpServers": {
    "web-extract": {
      "type": "http",
      "url": "https://www.twotic.dev/api/mcp/web-extract",
      "headers": { "Authorization": "Bearer tk_live_your_key" }
    }
  }
}

Parameters

query parameters

Name	Type	Required	Description
url	string	required	The absolute URL to extract. Must be publicly reachable http or https.e.g. https://example.com/blog/post
format	string	optional	Output format. Defaults to markdown.one of: markdown · text · htmle.g. markdown

Response

200The extracted content and page metadata.

{
  "url": "https://example.com/blog/post",
  "title": "How we cut inference cost by 80%",
  "byline": "Dana Whitfield",
  "format": "markdown",
  "content": "## The problem\n\nOur inference bill grew faster than usage did…",
  "language": "en",
  "siteName": "Example Engineering",
  "wordCount": 1840,
  "description": "A write-up of the changes that mattered.",
  "publishedAt": "2026-06-14T09:00:00Z"
}

400The url is missing, malformed, or resolves to a private address.

{
  "error": "blocked_host",
  "message": "That URL resolves to a private or reserved address, which cannot be fetched."
}

422The target returned an error status.

{
  "error": "target_error",
  "message": "The target returned HTTP 404. Check the URL is publicly reachable."
}

As an agent tool

Connect https://www.twotic.dev/api/mcp/web-extract and this endpoint is exposed as the tool web-extract_extract.

Fetch a web page and return its main article content as clean Markdown, stripped of navigation, ads and scripts. Choose this whenever you need to READ the content of a URL — to summarise it, answer questions about it, or store it for retrieval. Requires `url`; optional `format` of markdown, text or html. Returns the content plus title, description, author, published date and word count. Use the links tool instead if you only need the page's outbound URLs.