Browser Automation MCP Repositories

Provides browser automation capabilities for interacting with web pages, capturing screenshots, and executing JavaScript in a real browser environment.

Automates and interacts with web browsers using Playwright, enabling actions such as taking screenshots, generating test code, scraping web pages, and executing JavaScript in real browser environments.

Automate browser interactions to navigate web pages, capture screenshots, and execute JavaScript in a real browser environment. Customize browser automation options using Puppeteer with environment variables for flexibility.

Browser automation capabilities using Puppeteer, both support local and remote browser connection.

Facilitates browser automation through structured accessibility snapshots, enabling interaction with web pages without visual models. Supports web navigation, form-filling, data extraction, and automated testing with a deterministic approach.

A self-hosted browser automation agent that executes natural language commands to control web activities, integrating easily with other AI applications and agents through MCP and A2A support.

Automate interactions with LinkedIn, extract data, and manage profiles, posts, and feeds using browser automation while adhering to LinkedIn's terms and rate limits.

Automates browser interactions through Selenium WebDriver, enabling actions like navigating to URLs, finding elements with various locator strategies, and performing mouse actions such as clicking and dragging.

Automate browser interactions to enhance web automation tasks by leveraging state management and interactive element manipulation. This agent integrates with the Model Context Protocol for seamless browser automation capabilities.

An MCP server for browser automation using Playwright

A browser-based multiplayer RPG that facilitates empire expansion, strategic battles, and resource management among players. It supports the creation and sharing of platformer mini-games, offering rewards and robust community management features.

A self-hostable sandbox for executing commands, reading and writing files, and browsing the web across various platforms like iOS and Android. The server supports executing Linux commands and Python scripts, making it suitable for running complex analyses and generating documents like PDFs and diagrams.

Enables complete control over remote macOS systems with native environment integration and no additional software requirements. Optimized for autonomous AI agents to operate seamlessly on the desktop.

An MCP server that facilitates web automation tasks using Playwright tools and features a note storage system. It allows summarization of stored notes with customizable detail levels.

Provides advanced web browsing capabilities for AI applications, enabling interaction with web content and retrieval of information from online sources.

Automate web interactions by navigating to URLs, taking screenshots, and executing JavaScript in a cloud-based browser environment without local installations.

Automate your local Chrome browser

Connects to BrowserStack's cloud infrastructure for executing manual and automated tests on real devices and browsers. Offers tools for debugging, fixing test failures, and ensuring accessibility compliance within development workflows.

Bridges AI assistants with the Chrome browser for web browsing, interaction, and data collection using a WebSocket-based protocol. Supports automation tasks such as navigating websites, taking screenshots, and managing browser tabs and forms.

A user panel for managing Cloudflare Workers and Pages proxy scripts, featuring ad blocking, IP fixing, and password protection. It offers easy configuration and usage for enhanced online experience.

Automates login, keyword searches, content retrieval, and comment management on Xiaohongshu (Redbook) notes, facilitating context-aware comment posting. Utilizes AI to generate natural comments based on note analysis.

Monitor and interact with browser data, capturing console logs, network activity, and screenshots to facilitate AI applications. Provides a secure, local solution for data privacy while enhancing AI tools with browser insights.

A Windows control server utilizing nut.js and MCP, enabling functionalities like mouse and keyboard control, window management, and screen capture operations.

Automates browser interactions and testing by executing web navigation and element interaction, while capturing screenshots and snapshots. Integrated with Cloudflare Workers for deployment, it enhances LLM-driven workflows with powerful browser automation capabilities.

Enables the integration of Google search capabilities and extraction of webpage content through the Chrome browser.

Enables AI agents to perform web browsing tasks and retrieve information from web pages through a unified API. Enhances language models by providing real-time access to web content.

Automate web interactions, capture screenshots, and execute JavaScript in a browser environment. Enable LLMs to navigate web pages, click on elements, and monitor console logs in real-time.

Automate web browsing tasks using natural language commands to navigate pages, fill forms, and interact with web elements. The server maintains state persistence across sessions for enhanced browsing experience.

Control a headless browser for automated navigation, screenshot capturing, and interaction with web page elements. Facilitates the creation of automation projects using the Multi-Context Protocol framework.

Interact with the browser to execute commands, modify styles, and access browsing history. Enables retrieval of content from the current page in markdown format and customization of page styles directly through an MCP interface.