Hi everyone,
I’m looking for recommendations on an MCP server that supports browser automation. My goal is to enable an AI to understand the current webpage content—which could include text, images, or a mix of both—from my Chrome browser.
Here are my key requirements:
- Browser Automation: The solution should interact with the Chrome browser to capture the entire webpage content.
- Integration with Claude Desktop: I intend to integrate this with Claude Desktop. I’m particularly interested in whether, if Claude Desktop is installed on a different machine, it can be configured to retrieve the current browser’s webpage content on that machine.
- Primary Objective: My sole focus is on having the AI analyze and comprehend the webpage content.
I’ve come across several browser automation MCP server options (such as those based on Playwright and Puppeteer). I would appreciate any insights or suggestions on which one might best fit this use case and any tips on configuring such a system.
Thank you for your help!