Browserless

What is Browserless?

Browserless is an MCP (Model Context Protocol) server that exposes the Browserless.io smart scraper API to LLM clients like Claude Desktop, Cursor, VS Code, and Windsurf. It allows AI agents to scrape, crawl, search, audit, and automate web pages directly.

How to use Browserless?

Obtain an API token from browserless.io (free tier available). Configure your MCP client with the URL https://mcp.browserless.io/mcp?token=your-token-here or use the Authorization: Bearer your-token-here header. No local installation is required; the server is hosted.

Key features of Browserless

• Scrape JavaScript-heavy pages with anti-bot handling automatically.
• Crawl entire websites with depth control and path filtering.
• Search the web and scrape results with geo-targeting filters.
• Run Lighthouse audits for accessibility, performance, and SEO.
• Execute custom Puppeteer JavaScript in the cloud.
• Drive persistent browser sessions via ReAct loop with skill library.

Use cases of Browserless

• Scraping JavaScript-rendered content that static tools miss.
• Mapping all URLs on a website for content audits.
• Searching and scraping multiple results with geo-targeting.
• Running Lighthouse performance audits on any URL.
• Automating complex multi-tab workflows with persistent sessions.

FAQ from Browserless

How do I authenticate with the Browserless MCP server?

Use a Bearer token in the Authorization header (Authorization: Bearer your-token-here) or pass the token as a ?token= query parameter in the URL.

Can I connect to a specific regional Browserless endpoint?

Yes. Add the x-browserless-api-url header or the browserlessUrl query parameter (e.g., https://production-lon.browserless.io). Headers take precedence when both are present.

Does Browserless support residential proxies?

Yes, via the proxy object on the browserless_agent tool. Set "proxy": "residential" and optionally specify country, state, city, or sticky IP. It requires an eligible plan for some options.

What are Skills in the Browserless MCP server?

Skills are on-demand recipes for handling tricky page mechanics like shadow DOM, cookie consent dialogs, modals, captchas, dynamic content, and multi-tab workflows. They auto-inject into agent responses or can be loaded manually via the browserless_skill tool.

Do I need to install anything locally to use this MCP server?

No. The Browserless MCP server is hosted at https://mcp.browserless.io/mcp. You only need an API token and an MCP-compatible client (Claude Desktop, Cursor, VS Code, Windsurf, etc.).