Browser Automation MCP Repositories

Control the Chrome browser for web automation tasks, including navigation, element interaction, and page analysis, while managing features like bookmarks and history. Execute scripts securely and extract detailed page content to enhance automation workflows.

Automate browser tasks such as web navigation, login management, and element manipulation with advanced credential management and intelligent handling of web interactions.

Enables remote web browsing automation using BrowserCat's cloud service, allowing for navigation, form filling, and JavaScript execution. Capture screenshots and monitor browser console logs while interacting with web pages in a real browser environment.

Automates control of the Chrome browser while successfully bypassing anti-bot detection mechanisms using undetected-chromedriver. Provides a comprehensive interface for various automated web interactions.

Provides stealth browser automation capabilities, allowing AI models to browse, interact, extract content, and manage browser sessions while employing advanced anti-detection features. Integrates seamlessly with the Model Context Protocol for efficient command execution and data handling.

A fully functional MCP server and CLI for YouTube to automate YouTube operation

Retrieve web page content using a Playwright headless browser to navigate and extract information efficiently. Designed for easy setup and configuration, it leverages AI to streamline web scraping tasks.

Provides browser automation capabilities, enabling interaction with web pages, taking screenshots, and executing JavaScript in a browser environment.

An MCP server using Playwright for browser automation and webscrapping

Control and manage local browser tabs and history, perform web content reading and searching, and integrate browsing capabilities with AI agents. Offers features such as tab management and text highlighting within web pages.

An MCP server for interacting with Apple Reminders on macOS

Automates complex tasks on Windows systems by interacting with UI elements, capturing screenshots, and controlling browsers. Integrates with Python applications to enhance productivity through advanced AI functions.

Extract structured data from any website. Just prompt and get JSON.

Moling is a local office automation assistant that interacts with the operating system through APIs, facilitating system-level operations.

Scrapes data from popular social media platforms such as Xiaohongshu, Douyin, Kuaishou, Bilibili, and Weibo. Extracts videos, images, comments, likes, and shares using Playwright for efficient data collection.

Control mouse movements, simulate keyboard input, and capture screenshots for automated GUI testing across multiple platforms, including Windows, macOS, and Linux.

Seamlessly interact with the ChatGPT desktop app on macOS, allowing users to ask questions, view conversation history, and continue discussions. This integration facilitates enhanced productivity by bridging Claude and ChatGPT.

Automates browser interactions by taking screenshots, generating test code, and executing JavaScript in real browser environments. Enables interaction with web pages and facilitates web scraping.

Facilitates autonomous browser automation and API interaction, enabling navigation of web pages, manipulation of DOM elements, and execution of JavaScript. It supports features like persistent browser sessions, HTTP requests, and detailed logging for complex web task automation.

Fetch web page content using a headless browser, capable of executing JavaScript to handle dynamic web pages and modern web applications. Extracts the main content intelligently using a Readability algorithm and supports output in both HTML and Markdown formats.

Enables efficient parallel searching on Google using multiple keywords, automatically handling verification challenges and returning structured search results in JSON format for analysis.

Automate web tasks, including actions like browsing, scraping, and interacting with web applications using natural language instructions. Integrates with Selenium to facilitate seamless web interactions within applications.

Interact with Bear note-taking software to manage notes and retrieve information. Provides integration with Bear's API for note creation and manipulation.

Execute browser automation tasks using natural language commands through an API. Utilize OpenAI's GPT models to interpret commands and automate browser actions seamlessly.

Manage and retrieve information about currently open Chrome browser tabs, enabling interactions with the browser's tab content and control functions.

Fetch YouTube subtitles and transcripts for AI analysis

An MCP server for web browsing automation that integrates Azure OpenAI to facilitate interactions with web applications through an automated interface. It utilizes Playwright for end-to-end testing and customizes responses to fit the OpenAI function calling format.

Automate GUI tasks by controlling the mouse and keyboard to interact with desktop applications, enabling AI agents to perform repetitive actions and streamline workflows.

Control and automate browser tasks through integrated AI functionality, facilitating seamless interaction and task execution in web environments.

Enables browser automation with video recording capabilities, allowing interaction with web pages through structured accessibility snapshots. Supports navigation, form-filling, data extraction, and automated testing without relying on visual inputs.