Skip to content
@scrapeless-ai

Scrapeless

Effortless Web Scraping Toolkit for Business and Developers

Scrapeless — Web Infrastructure for AI Agents. Agent Browser, AI Scraper, Scraping API, Web Unlocker, Proxies.

Scrapeless — Web Infrastructure for AI Agents

Give your agents a browser, bring live web data into your applications, and monitor what AI platforms say about your brand. Scrapeless connects browser automation, AI answer collection, and structured web data in one platform.

$5 Free Credit · No Credit Card Required → Sign Up · Website · Documentation · Examples

What are you building?

Your goal Product Start here
Give an AI agent a browser to navigate, click, and complete multi-step tasks Agent Browser CLI + agent skill
Track brand mentions, answers, and citations across AI platforms AI Scraper ChatGPT product page · Examples
Retrieve content from public websites with anti-bot protection Web Unlocker Agent skill
Collect structured search, social, or e-commerce data Scraping API Google Search API, TikTok & Amazon ↓
Turn websites into content for RAG and data pipelines Crawl SDK examples
Add geo-targeted IPs to your own stack Proxy Solutions Python SDK

Scraping API

Dedicated APIs for structured data from search engines, social platforms, and marketplaces.

API Use it for Resources
Google Search API Search results for research agents, SEO, and competitive monitoring Documentation · Repository
TikTok Scraper Public creator profiles, video lists, and TikTok Shop product data Website
Amazon Scraper Product and search data, pricing, and Amazon Rufus responses Product · Repository

Quick start: open a cloud browser

Get an API key from the Scrapeless dashboard. With Node.js installed, install the browser client and set your key:

npm install puppeteer-core
export SCRAPELESS_API_KEY="YOUR_API_KEY"

Save this as quickstart.mjs, then run node quickstart.mjs:

import puppeteer from 'puppeteer-core';

const key = process.env.SCRAPELESS_API_KEY;
if (!key) throw new Error('Set SCRAPELESS_API_KEY first.');
const browser = await puppeteer.connect({
  browserWSEndpoint: `wss://browser.scrapeless.com/api/v2/browser?token=${encodeURIComponent(key)}&sessionTTL=180&proxyCountry=ANY`,
});
try {
  const page = await browser.newPage();
  await page.goto('https://example.com', { waitUntil: 'domcontentloaded' });
  console.log(await page.title());
} finally {
  await browser.close();
}

This opens a remote browser, prints the page title, and closes the session. For terminal-based agent workflows, use the Agent Browser CLI.

Connect your AI assistant

Use the MCP Server to bring browser actions, web content, search results, and AI Scraper tasks into MCP-compatible clients such as Claude Code and Cursor.

View the MCP configuration

With Node.js installed, add this server entry using your client's MCP configuration format and replace the API key:

{
  "mcpServers": {
    "scrapeless": {
      "command": "npx",
      "args": ["-y", "scrapeless-mcp-server"],
      "env": {
        "SCRAPELESS_API_KEY": "YOUR_API_KEY"
      }
    }
  }
}

Follow the server setup guide for transport options and configuration details.

Prefer agent skills? Explore Agent Browser, Web Unlocker, and AI Scraper. Each repository lists its supported clients and setup requirements.

SDKs

Language Install Repository
Python pip install scrapeless sdk-python
Node.js / TypeScript npm install @scrapeless-ai/sdk sdk-node
Go go get github.com/scrapeless-ai/sdk-go sdk-go

See each SDK's README for supported products and usage examples.

Integrations

Browse all integration guides →

Explore examples

Choose a repository, configure your API key and dependencies, then follow its setup instructions.

Agent Browser & web access

Agent Browser CLI · MCP browser workflows · Web Unlocker skill

AI answers & GEO

Collect answers and citations for brand monitoring and AI search analysis:

ChatGPT · Perplexity · Gemini · Copilot · Grok · Google AI Mode · Google AI Overview · Amazon Alexa · AI Scraper skill

Search & e-commerce

Google Search API · Google Trends example · Amazon Scraper

RAG & data pipelines

MCP RAG server · SDK and workflow examples

Open-source tools

Respondo — A Python library for web scraping, text extraction, and AI-assisted parsing.

Why Scrapeless?

  • Build agent workflows: use cloud browsers with persistent profiles and session visibility.
  • Bring fresh context into AI: collect web content, search data, and AI answers.
  • Reduce infrastructure work: use managed browser, CAPTCHA, and proxy capabilities.
  • Keep your stack: connect through SDKs, browser frameworks, MCP, and workflow integrations.
  • Expand by use case: combine browser actions with dedicated data APIs as your application grows.

Claim Your $5 Free Credit · No Credit Card Required → · Read the docs · Explore the platform

Pinned Loading

  1. scrapeless-mcp-server scrapeless-mcp-server Public

    Scrapeless Mcp Server

    TypeScript 169 28

  2. n8n-nodes-scrapeless n8n-nodes-scrapeless Public

    Official Scrapeless community node for n8n—automate Google Search, Google Trends, Web Unlocker, Crawler, and AI Scraper workflows.

    TypeScript 4 2

  3. sdk-node sdk-node Public

    SDK to access Scrapeless API directly from Node.js. We handle Agent Browser, AI Scraper, Web Unlocker, Scraping API and Proxies for you.

    TypeScript 7 1

  4. sdk-python sdk-python Public

    SDK to access Scrapeless API directly from Python. We handle Proxies, Scraping Browser, Scraping API and Universal Scraping API for you.

    Python 2 1

  5. sdk-go sdk-go Public

    Go 3

  6. scrapeless-cli scrapeless-cli Public

    Go 1

Repositories

Showing 10 of 39 repositories

Top languages

Loading…

Most used topics

Loading…