Browser Automation Servers

Playwright Browser Automation

Official

Enables web browser control for navigating websites, capturing page snapshots, interacting with elements, and taking screenshots through Playwright's automation capabilities. Playwright empowers LLMs to interact with web pages through structured accessibility snapshots, eliminating the need for screenshots or visually-tuned models. It provides a fast, lightweight, and deterministic approach to browser automation, operating on structured data rather than relying on pixel-based input. This enables LLMs to perform tasks like web navigation, form-filling, and data extraction with greater efficiency and reliability.

Firecrawl

Official

Empowers LLMs with advanced web scraping capabilities for content extraction, crawling, and search functionalities. Firecrawl integrates seamlessly with LLM clients like Cursor and Claude, providing powerful web scraping features. It supports scraping, crawling, searching, and extracting content with JavaScript rendering and efficient batch processing. The server includes features like URL discovery, web search with content extraction, automatic retries, credit usage monitoring, and comprehensive logging. It supports both cloud and self-hosted Firecrawl instances, offering flexible configuration options for various use cases.

Puppeteer

Official

A Model Context Protocol server that provides browser automation capabilities using Puppeteer. This server enables LLMs to interact with web pages, take screenshots, and execute JavaScript in a real browser environment.

Browserbase

Official

The Browserbase MCP Server implements the Model Context Protocol to provide Claude with web automation capabilities powered by Playwright. This allows Claude to interact with websites, perform searches, fill forms, click buttons, and extract information—all without leaving the conversation.