browser-use/browser-use
Open-source browser automation agent for LLMs, usable as a Python library, CLI, hosted cloud service, or MCP server exposing browser-control tools.
Awesome MCP › Browser Automation
just-every/mcp-read-website-fast
mcp-read-website-fast is a Model Context Protocol server for turning web pages into clean Markdown that an LLM can read cheaply. Its stated motivation is that existing MCP crawlers are slow and return whole pages, forcing the model to spend tokens parsing noise. This server fetches pages locally, strips boilerplate with Mozilla Readability, the same extraction engine behind Firefox Reader View, and converts the remaining content to Markdown using Turndown with GitHub Flavored Markdown support, preserving links so the output can feed knowledge graphs. The core crawling and conversion logic now lives in the separate @just-every/crawl package. The MCP surface is small: one tool, read_website, takes a required HTTP or HTTPS url and an optional pages count controlling how many pages to crawl, defaulting to one and capped at 100. Two resources are exposed, read-website-fast://status for cache statistics and read-website-fast://clear-cache to empty the cache directory. Operationally it caches responses on disk under SHA-256 hashed URL keys, respects robots.txt and rate limits by default, fetches concurrently with configurable depth, and uses a stream-first design to keep memory low; optional chunking prepares output for downstream processing. The server starts quickly through the official MCP SDK with lazy loading, and wraps itself in an auto-restart supervisor that handles crashes, unhandled exceptions and rejected promises with exponential backoff, up to ten attempts per minute, while shutting down cleanly on SIGINT and SIGTERM. A CLI mirrors the same functionality with flags for pages, concurrency, robots.txt bypass, cross-origin crawling, user agent, cache directory, timeout and output as markdown, JSON or both. Installation is a single command for Claude Code, VS Code, Cursor and JetBrains IDEs, or raw JSON for any MCP client. JavaScript-rendered sites are not supported. MIT licensed.
https://github.com/just-every/mcp-read-website-fast
Also in Browser Automation
unclecode/crawl4ai
Open-source async web crawler and scraper that converts websites into clean, LLM-ready Markdown for RAG pipelines and AI agents, with an official MCP server for AI assistants.
microsoft/playwright-mcp
Playwright MCP is an MCP server that enables LLMs to automate and interact with web browsers using structured accessibility snapshots for efficient and deterministic browser automation.
alibaba/page-agent
Page Agent is an in-page JavaScript GUI agent that enables natural language control of web interfaces, offering easy integration without browser extensions or headless browsers.
Skyvern-AI/skyvern
Skyvern automates browser-based workflows using large language models and computer vision, providing a robust and scalable web automation solution that integrates with the Model Context Protocol (MCP).
browser-use/browser-harness
MCP-compatible harness that lets coding agents drive a user's real, logged-in Chrome browser over the DevTools Protocol, writing new helper scripts as it works.
apify/actors-mcp-server
Apify MCP Server is an MCP protocol server implementation that enables AI assistants to interact with Apify Actors for data extraction, web scraping, and automation tasks through a standardized protocol.
firecrawl/firecrawl-mcp-server
Firecrawl MCP Server is an MCP server implementation that adds advanced web scraping, crawling, and search capabilities to LLM clients like Cursor and Claude, enabling enhanced data extraction and research functionalities.