Puppeteer Vision MCP Server

MCP Server for scraping webpages and converting to markdown

Local serverstdio

What is the Puppeteer Vision MCP MCP server?

Puppeteer Vision MCP MCP server exists for a simple reason — assistants are far more useful when they can act on Puppeteer Vision MCP directly instead of describing what you should do. MCP Server for scraping webpages and converting to markdown.

What you get

This Model Context Protocol (MCP) server provides a tool for scraping webpages and converting them to markdown format using Puppeteer, Readability, and Turndown. It features AI-driven interaction capabilities to handle cookies, captchas, and other interactive elements automatically.

  • Scrapes webpages using Puppeteer with stealth mode
  • Uses AI-powered interaction to automatically handle:
  • Cookie consent banners
  • Newsletter or subscription prompts
  • Paywalls and login walls
  • Age verification prompts

What the assistant can call

Once Puppeteer Vision MCP is connected, these are the calls the assistant has available:

  • message — Status message
  • success — Boolean indicating success
  • contentSize — Size of the content in characters (on success)

Setting it up

The server ships on npm as The, so your MCP client can launch it on demand — there is no separate build step. Add the server block to your client's configuration, restart it, and the tools register themselves.

Configuration and credentials

You will need 5 environment variables: OPENAI_API_KEY, VISION_MODEL, API_BASE_URL, TRANSPORT_TYPE, DISABLE_HEADLESS. The server will not start without them, which is usually why the tools fail to appear on a first run. Keep credentials in your client's env block or a secrets manager rather than in a file you might commit.

Choosing this one

This sits in the browser automation group, where several servers overlap in what they claim to do but differ sharply once you actually set them up. Puppeteer Vision MCP's toolset — message, success, contentSize — is a fair guide to whether it matches your workflow. It is maintained by djannot; worth a glance at recent repository activity before you build anything load-bearing on it.

This entry was verified against Puppeteer Vision MCP's own documentation before publication; SyncDev keeps the directory reviewed rather than auto-generated.

Before you rely on it

  • It runs with your machine's permissions. That is convenient and also the reason to think about what you point it at before you approve a tool call.
  • Missing credentials fail quietly in some clients — if no tools show up, check the environment block first.
  • MCP clients confirm each tool call by default. Leave that on until you have watched what the puppeteer vision mcp mcp server does with a few real requests.

Available tools

ToolWhat it does
messageStatus message.
successBoolean indicating success.
contentSizeSize of the content in characters (on success).

How to install the Puppeteer Vision MCP MCP server

{
  "mcpServers": {
    "puppeteer-vision": {
      "command": "npx",
      "args": ["-y", "The"],
      "env": {
        "OPENAI_API_KEY": "your-value",
        "VISION_MODEL": "your-value",
        "API_BASE_URL": "your-value",
        "TRANSPORT_TYPE": "your-value",
        "DISABLE_HEADLESS": "your-value"
      }
    }
  }
}

Add to claude_desktop_config.json, then restart Claude Desktop.

Configuration

VariableDescriptionRequired
OPENAI_API_KEYCredential the server authenticates with.Yes
VISION_MODELConfiguration value read at startup.Optional
API_BASE_URLEndpoint or connection string the server talks to.Yes
TRANSPORT_TYPEConfiguration value read at startup.Optional
DISABLE_HEADLESSConfiguration value read at startup.Optional

Example prompts to try

  • Use Puppeteer Vision MCP to message.
  • Use Puppeteer Vision MCP to success.
  • Use Puppeteer Vision MCP to contentSize.

Frequently asked questions

It connects Puppeteer Vision MCP to MCP-compatible AI assistants such as Claude and Cursor, exposing 3 tools (message, success, contentSize) that the assistant can call on your behalf. Instead of copying data back and forth by hand, the assistant works with Puppeteer Vision MCP directly.