How to connect Scrapingbee to Claude Cowork

Cowork is Anthropic's AI agent for knowledge work. Think of it as Claude Code for everything else. It works autonomously with your computer, local files, and applications to accomplish complex tasks.

This guide walks you through the easiest and most secure way to connect your Scrapingbee account to Cowork via Composio Connect, enabling it to extract product prices from Amazon search results, fetch latest news headlines from BBC homepage, bypass anti-bot protections to scrape booking data, and more such actions on your behalf without compromising your account security.

Connecting Scrapingbee to Claude Cowork

1. Open Customize

In Claude Desktop, click Customize in the left sidebar, then select Connectors and click the + icon at the top.

2. Add the Composio MCP server

Click Add custom connector and paste in the Composio MCP server URL:

Claude Cowork is Anthropic's agent for general knowledge work. It can use your computer, files, and connected applications to complete longer-running tasks across your work tools.

With Composio Connect, Cowork can securely access apps like Scrapingbee through MCP without you sharing account credentials directly with the agent.

The Scrapingbee MCP server is an implementation of the Model Context Protocol that connects your AI agent and assistants like Claude, Cursor, etc directly to your Scrapingbee account. It provides structured and secure access to powerful web scraping tools, so your agent can extract data, fetch HTML, bypass anti-bot measures, and monitor your usage—all without manual code.

• Structured data extraction from any webpage: Let your agent pull tables, lists, or custom data using CSS or XPath selectors with ScrapingBee's extraction rules.
• Fetch full HTML or page screenshots: Ask your agent to retrieve raw page markup or rendered screenshots, including support for JavaScript-heavy sites.
• Proxy and stealth scraping: Enable your agent to scrape sites that block bots by routing requests through ScrapingBee proxies or stealth modes to bypass anti-bot defenses.
• Resource control and custom rendering: Have your agent fine-tune scraping with options to block resources, control JS rendering, and speed up extraction for tricky websites.
• Monitor account usage and limits: Keep track of your remaining ScrapingBee credits and usage statistics directly through your agent for seamless quota management.