Puppeteer Vision MCP Server - Specify4IT Configuration
@Larsbuilds
Configured Puppeteer Vision MCP server for website scraping with specific settings for specify4it.com
Overview
What is Puppeteer Vision MCP Server - Specify4IT Configuration?
A configured version of the Puppeteer Vision MCP server, specifically set up for scraping specify4it.com. It uses AI-powered interaction to automatically handle overlays, cookie banners, CAPTCHAs, and other interactive elements, then extracts main content via Mozilla's Readability and converts it to well-formatted Markdown. It includes custom scripts for extracting page structure, CSS animations, JavaScript interactions, and design assets from the target site.
How to use Puppeteer Vision MCP Server - Specify4IT Configuration?
Run via npx -y puppeteer-vision-mcp-server after setting the required OPENAI_API_KEY environment variable (via .env file or shell export). The server can be integrated as an MCP tool in an orchestrator by adding a configuration block with command: "npx" and args: ["-y", "puppeteer-vision-mcp-server"]. It provides a scrape-webpage tool that accepts url (required), autoInteract, maxInteractionAttempts, and waitForNetworkIdle parameters. The server runs in stdio mode by default; set USE_SSE=true for HTTP/SSE communication.
Key features of Puppeteer Vision MCP Server - Specify4IT Configuration
- Configured specifically for specify4it.com's structure and content.
- Custom scripts to extract CSS animations and JavaScript interactions.
- AI-powered interaction handling for overlays, CAPTCHAs, and paywalls.
- Stealth mode via Puppeteer Extra.
- Content extraction using Mozilla's Readability.
- HTML to well-formatted Markdown conversion with Turndown.
- Runnable via
npxwithout manual installation. - Supports OpenAI-compatible API endpoints (configurable via
API_BASE_URL).
Use cases of Puppeteer Vision MCP Server - Specify4IT Configuration
- Scraping specify4it.com for website recreation or analysis.
- Extracting design elements, animations, and interactive behavior from the target site.
- Automating data collection from pages with complex overlays and consent forms.
- Integrating web scraping capabilities into MCP-compatible LLM orchestrators.
- Creating structured Markdown archives of specify4it.com content.
FAQ from Puppeteer Vision MCP Server - Specify4IT Configuration
What is the required environment variable?
The server requires an OPENAI_API_KEY to access the vision model. It can be set via a .env file or as a shell environment variable.
Can I use a different vision model?
Yes. Set VISION_MODEL to any model with vision capabilities (default is gpt-4.1). Use API_BASE_URL to connect to alternative OpenAI-compatible providers.
How do I see the browser during scraping?
Set DISABLE_HEADLESS=true in the environment to run the browser in visible mode.
What communication modes are supported?
The server supports stdio (default) and SSE mode. Set USE_SSE=true to enable HTTP/SSE communication on the configured port (default 3001).
What does the scrape-webpage tool return?
It returns a structured response with content (array containing markdown text) and metadata (including success, message, and contentSize on success).