How to connect Serpdog to Claude

Claude is Anthropic's AI assistant, available on the web, in the desktop app, and on mobile. Cowork is its agent for knowledge work, and it runs on all of those surfaces too. Connected to your apps, Claude can work with your files and services to accomplish complex tasks on your behalf.

This guide walks you through the easiest and most secure way to connect your Serpdog account to Claude via Composio Connect, enabling it to capture full-page screenshot of Google homepage, take screenshot of search results for 'AI news', get mobile view screenshot of a business profile, and more such actions on your behalf without compromising your account security.

Setup is the same on Claude Web, Desktop, and Cowork, and you only need to do it once. The connector is tied to your account, so it's available in all three.

Connecting Serpdog to Claude Web, Desktop, and Cowork

Two ways to add the Composio connector. Pick whichever you prefer.

1. Add with one click

Click the button. Claude opens with the Composio connector filled in. Click Add, then go to step 2.

Add to Claude

Add manually

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

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

The Serpdog MCP server is an implementation of the Model Context Protocol that connects your AI agent and assistants like Claude, Cursor, etc directly to your Serpdog account. It provides structured and secure access to real-time Google web data, so your agent can perform actions like capturing live webpage screenshots, monitoring site changes, and emulating devices on your behalf.

• Instant webpage screenshot capture: Let your agent take high-quality screenshots of any public webpage, perfect for archiving or sharing visual content.
• Full-page and viewport-specific imaging: Choose between capturing the entire page or just the visible area, offering flexibility for your reporting or research needs.
• Device emulation and dark mode support: Have your agent render screenshots as if viewed on different devices or in dark mode for accurate previews and UI testing.
• Automated delay and load handling: Allow your agent to wait for pages to fully load, including dynamic content, before snapping the shot—ensuring complete and up-to-date visuals.
• Website monitoring and change detection: Use the screenshot capability to regularly capture and compare webpages, helping you keep tabs on updates or changes over time.