One request. Turn web pages into context for your agent.
Lexmount Web Fetch brings cloud-based web extraction to agents and applications. From static pages to JavaScript-powered websites, retrieve text, links, page HTML, and more in a single request.

Go deeper into dynamic pages.
Get more content.
Web content goes beyond static HTML.
Lexmount Web Fetch supports JavaScript rendering to retrieve information generated by scripts, giving agents access to more content. Choose from multiple fetching engines to suit the way each website loads.
Structured content and page HTML,
on demand.
Lexmount Web Fetch provides the Extract API and Dump DOM API. Supply a URL and choose an endpoint to get structured content or page HTML for agents and applications to read, analyze, and process.
A few commands.
Give your agent Web Fetch.
Install the CLI and Skill, or use the HTTP API to connect Web Fetch to your existing agents and applications.
// Node.js 18+ · Read credentials from environment variables
const response = await fetch(
'https://api.lexmount.com/v1/extract',
{
method: 'POST',
headers: {
'Content-Type': 'application/json',
'X-API-Key': process.env.LEXMOUNT_API_KEY!,
'X-Project-Id': process.env.LEXMOUNT_PROJECT_ID!,
},
body: JSON.stringify({
extract: { url: 'https://example.com' },
}),
},
);
if (!response.ok) {
throw new Error(`Web Fetch HTTP ${response.status}`);
}
const { result, error } = await response.json();
if (error || !result) {
throw new Error(JSON.stringify(error ?? 'Missing result'));
}
console.log(result.main_text);# Python 3 · Standard library only
import json
import os
from urllib.request import Request, urlopen
request = Request(
"https://api.lexmount.com/v1/extract",
data=json.dumps({
"extract": {"url": "https://example.com"}
}).encode("utf-8"),
headers={
"Content-Type": "application/json",
"X-API-Key": os.environ["LEXMOUNT_API_KEY"],
"X-Project-Id": os.environ["LEXMOUNT_PROJECT_ID"],
},
method="POST",
)
with urlopen(request, timeout=60) as response:
payload = json.load(response)
if payload.get("error") or not payload.get("result"):
raise RuntimeError(payload.get("error") or "Missing result")
print(payload["result"].get("main_text", ""))