"Selenium" matching MCP servers:

Enables agents to drive a persistent real browser on Selenium Grid through MCP or HTTP, performing multi-step actions like navigation, clicking, typing, scripting, and screenshots while retaining session state.

Enables AI agents to control legacy web applications running in Microsoft Edge's IE Mode via MCP, using Selenium WebDriver and IEDriverServer for browser automation.

Enables AI clients to control the user's already-open, logged-in browser pages in real time over a local WebSocket channel, without Playwright, Puppeteer, Selenium, or any browser driver. Exposes tools for navigation, semantic page snapshots, clicking, form filling, JavaScript evaluation, screenshots, network monitoring, cookie handling, and tab management via the CDP.

Empowers AI agents to perform web browsing, automation, and scraping tasks with minimal supervision using natural language instructions and Selenium.

A unified browser automation protocol that connects AI agents to multiple automation backends including Selenium, Playwright, and Puppeteer. It provides a centralized interface for agents to navigate websites, execute JavaScript, and manage web interactions across various browser engines.

基于MCP架构的微信公众号文章爬虫系统，支持AI智能体通过Selenium自动抓取微信公众号文章内容和图片，实现文章内容的智能分析。