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.
@Larsbuilds
基本信息
Configured Puppeteer Vision MCP server for website scraping with specific settings for specify4it.com
使用下面的配置,将此服务器添加到你的 MCP 客户端。
{
"mcpServers": {
"puppeteer-vision-mcp-specify4it": {
"command": "npx",
"args": [
"-y",
"puppeteer-vision-mcp-server"
]
}
}
}工具列表暂未提供
当前收录暂时没有可展示的工具列表,不代表服务没有工具。请查阅项目文档了解支持的能力。
点击上方按钮,在临时沙箱中运行此服务器并实时获取工具列表。
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.
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.
npx without manual installation.API_BASE_URL).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.
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.
Set `DISABLE_HEADLESS=true` in the environment to run the browser in visible mode.
The server supports stdio (default) and SSE mode. Set `USE_SSE=true` to enable HTTP/SSE communication on the configured port (default 3001).
It returns a structured response with `content` (array containing markdown text) and `metadata` (including `success`, `message`, and `contentSize` on success).
MCP server for fetch web page content using Playwright headless browser.
This MCP server provides browser automation capabilities through Puppeteer, allowing interaction with both new browser instances and existing Chrome windows.
The Apify MCP server enables your AI agents to extract data from social media, search engines, maps, e-commerce sites, or any other website using thousands of ready-made scrapers, crawlers, and automation tools available on the Apify Store.

Give your AI agent its own proxies. QuantumProxies exposes residential, mobile, datacenter, ISP and IPv6 endpoints as MCP tools: list your plans, generate ready-to-use proxy strings with credentials, target by country, s
Let Claude Code, Claude Desktop, OpenAI Codex, Kimi and any MCP-capable AI agent create, launch, check and drive browser profiles in Nullprint, the AI antidetect browser. Install with one command.
评论