Puppeteer
Summary
The Puppeteer project is a Model Context Protocol server designed for browser automation using Puppeteer. It allows large language models (LLMs) to interact with web pages by providing functionalities such as navigating to URLs, taking screenshots, clicking, hovering over elements, filling forms, and executing JavaScript code in a real browser environment. This server is particularly useful for tasks that require automated web interactions, such as data scraping, testing web applications, or automating repetitive browser tasks. It also offers resources for monitoring browser console logs and accessing screenshots, making it a comprehensive tool for developers needing to automate and interact with web pages programmatically.
Available Actions(7)
puppeteer_navigate
Navigate to any URL in the browser. Inputs: url (string, required), launchOptions (object, optional), allowDangerous (boolean, optional).
puppeteer_screenshot
Capture screenshots of the entire page or specific elements. Inputs: name (string, required), selector (string, optional), width (number, optional, default: 800), height (number, optional, default: 600), encoded (boolean, optional).
puppeteer_click
Click elements on the page. Input: selector (string).
puppeteer_hover
Hover elements on the page. Input: selector (string).
puppeteer_fill
Fill out input fields. Inputs: selector (string), value (string).
puppeteer_select
Select an element with SELECT tag. Inputs: selector (string), value (string).
puppeteer_evaluate
Execute JavaScript in the browser console. Input: script (string).
社区评论
暂无评论. 成为第一个评论的人！
登录以参与讨论
