- Puppeteer Vision Mcp Server
Puppeteer Vision Mcp Server
What is Puppeteer Vision MCP Server?
Puppeteer Vision MCP Server is a Model Context Protocol (MCP) server designed for scraping webpages and converting them into markdown format using Puppeteer, Readability, and Turndown. It incorporates AI-driven interaction capabilities to automatically manage cookies, captchas, and other interactive elements.
How to use Puppeteer Vision MCP Server?
To use the server, you can run it via npx after ensuring you have Node.js and npm installed. You need to set up an OPENAI_API_KEY in your environment, either through a .env file or shell environment variables, and then execute the command: npx -y puppeteer-vision-mcp-server.
Key features of Puppeteer Vision MCP Server?
- Webpage scraping using Puppeteer with stealth mode.
- AI-powered interaction to handle cookies, CAPTCHAs, and other prompts automatically.
- Extraction of main content using Mozilla's Readability.
- Conversion of HTML to well-formatted Markdown.
- Real-time browser interaction viewing option.
- Easily consumable as an
npxpackage.
Use cases of Puppeteer Vision MCP Server?
- Scraping content from news websites while bypassing paywalls.
- Automating data extraction from interactive web forms.
- Converting complex HTML pages into markdown for documentation purposes.
FAQ from Puppeteer Vision MCP Server?
- Can I run the server without Node.js?
No, Node.js and npm are required to run the server.
- Is there a way to see the browser actions in real-time?
Yes, you can disable headless mode to view browser interactions.
- What should I do if I encounter errors while scraping?
Check the URL and ensure that the interactive elements are being handled correctly by the AI.
Server Config
{
"mcpServers": {
"web-scraper": {
"command": "npx",
"args": [
"-y",
"puppeteer-vision-mcp-serve"
],
"env": {
"OPENAI_API_KEY": "YOUR_OPENAI_API_KEY_HERE"
}
}
}
}