Browser Automation MCP Repositories

Retrieve spoken content subtitles and synchronized text streams from video archives on YouTube for LLM processing.

Server and command-line utility for AI-orchestrated web interaction, facilitating programmatic control over digital browser environments for testing, data acquisition, and digital research workflows.

A specialized MCP service enabling sophisticated web interaction via Playwright, featuring integrated persistent knowledge storage with flexible summarization capabilities.

A Model Context Protocol (MCP) mechanism that leverages the Playwright library to facilitate advanced web page automation. This implementation uniquely integrates full session video capture alongside its core functionality, which relies on structured accessibility data rather than visual raster images for operational control. It empowers agents to conduct navigation, input manipulation, content retrieval, and systematic quality assurance procedures against web interfaces.

A consolidated server component designed to orchestrate and streamline operations across diverse external utilities, including GitHub, GitLab, mapping services (Google Maps), and headless browser automation via Puppeteer, offering an efficient, centralized interface for data acquisition and workflow acceleration. Its adaptable structure facilitates straightforward integration or detachment of specific utility agents.

A server implementation facilitating programmatic interaction with web browser environments, leveraging the Puppeteer library to control both fresh browser sessions and active Chrome instances for advanced web task execution.

Facilitates advanced browser orchestration via the Model Context Protocol (MCP), leveraging Playwright's non-visual accessibility tree to drive web interactions, data retrieval, and automated testing for LLM agents.

Automate cloud browser interactions, extract data, perform web navigation, and capture screenshots. Execute JavaScript within a cloud browser environment for enhanced LLM applications.

A backend service utilizing Python to retrieve and restructure digital document payloads from diverse web addresses, accommodating both static material and dynamically generated HTML via JavaScript execution. This utility enables structured extraction of web assets, including multimedia components.

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

An enhanced protocol adapter interfacing with Brave Search for initial discovery, subsequently employing Puppeteer for exhaustive, full-document content retrieval, facilitating deep analytical synthesis well beyond standard result summaries. It systematically gathers granular insights and recursively processes referenced materials for comprehensive contextual mapping.

Facilitates total command over distant macOS workstations, featuring native system integration without any prerequisite auxiliary software. Highly tuned for deployment by autonomous artificial intelligence entities for desktop operations.

Facilitates rapid, concurrent querying of the Google search engine utilizing multiple specified search terms, incorporating automated defense against verification checks and outputting organized results in JSON structure for downstream consumption.

A self-contained web interaction engine facilitating automated control of digital interfaces via plain language instructions, featuring seamless integration with other AI entities and agents via MCP and A2A communication channels.

Facilitates remote web navigation, automated information retrieval, and execution of sophisticated web workflows via the specialized LAM protocol interface. It automates digital user actions on web interfaces, such as inputting data into forms and manipulating screen elements.

Connects AI assistants to your web application's DOM, enabling the generation of accurate Playwright tests based on real elements instead of textual descriptions. This integration helps to reduce flaky tests and debugging issues related to AI-generated scripts.

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.

A specialized Windows control agent leveraging nut.js and the Model Context Protocol (MCP), engineered to provide high-fidelity programmatic access to system interactions such as cursor manipulation, keyboard input execution, active window administration, and comprehensive screen capture utilities.

Automate browser tasks using Python scripts for operations like capturing screenshots, retrieving HTML content, and executing JavaScript on webpages.

Leverage AI-powered research capabilities by performing web searches, retrieving documentation, and analyzing code through a modular tool architecture. The server facilitates interactions with the Perplexity website without requiring an API key, utilizing browser automation for efficient data retrieval.

Automates login, content retrieval, and commenting on Xiaohongshu posts through keyword searches and URL-based access. Enables tailored interactions with various comment types to enhance user engagement.

Facilitates the conversion of intercepted browser session logs (HAR archives) into formalized Model Context Protocols (MCPs), granting artificial intelligence agents direct, real-time transactional access to external web service capabilities.

An MCP server using Playwright for browser automation and webscrapping

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.

Orchestrates user interface manipulation within a web browser environment utilizing the Selenium WebDriver protocol for automated client-side scripting.

Instantly acquire normalized, structured datasets from any webpage without manual specification of CSS locators. Features straightforward API connectivity for data retrieval workflows.