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
tinyfish-io/agentql-mcp
AgentQL MCP Server is a small JavaScript MCP server from TinyFish that exposes the hosted AgentQL data-extraction service to MCP clients. It provides one tool, extract-web-data, which takes a url and a prompt describing the wanted data and its fields, fetches and interprets the page through AgentQL, and returns structured data the host can use directly. The documented example asks for the videos on a YouTube search results page, each with title, author name, view count and link, excluding ads, and has the host format the result as a markdown table. Because extraction runs on the AgentQL service rather than in a local browser, the server itself is thin: it is installed globally from npm as agentql-mcp or run on demand with npx, and it requires an AGENTQL_API_KEY obtained from the AgentQL developer portal. The README documents configuration for several hosts. For Claude Desktop, an agentql entry is added to the mcpServers dictionary in claude_desktop_config.json with the key in the env block. For VS Code, the server can be added through one-click install badges or manually in user settings or a workspace .vscode/mcp.json, using a promptString input so the key is typed as a password instead of being stored in the file. Cursor is configured by adding a command-type MCP server that passes the key as an environment variable, and Windsurf through its MCP configuration panel or mcp_config.json. A validation section suggests giving the agent a concrete extraction task and, if the agent claims it cannot open URLs, hinting that it should use the AgentQL tool. For development the repository supports a build step and a watch mode, a configuration that points at the built dist/index.js, and debugging through the MCP Inspector, which is wired up as an npm script.
https://github.com/tinyfish-io/agentql-mcp
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.