Puppeteer MCP Server

Provides browser automation capabilities through the Model Context Protocol using Puppeteer. Enables AI agents to navigate web pages, take screenshots, click elements, fill forms, and execute JavaScript in a browser context. Useful for web scraping, testing, and interacting with web applications programmatically. Originally part of the reference servers, now archived and available in servers-archived.

{
  "mcpServers": {
    "puppeteer": {
      "command": "npx",
      "args": [
        "-y",
        "@modelcontextprotocol/server-puppeteer"
      ]
    }
  }
}

{
  "type": "object",
  "required": [
    "url"
  ],
  "properties": {
    "url": {
      "type": "string",
      "description": "URL to navigate to"
    }
  }
}

{
  "type": "object",
  "required": [
    "name"
  ],
  "properties": {
    "name": {
      "type": "string",
      "description": "Name for the screenshot"
    },
    "width": {
      "type": "integer",
      "description": "Viewport width in pixels"
    },
    "height": {
      "type": "integer",
      "description": "Viewport height in pixels"
    },
    "selector": {
      "type": "string",
      "description": "CSS selector of element to screenshot (captures full page if omitted)"
    }
  }
}

{
  "type": "object",
  "required": [
    "selector"
  ],
  "properties": {
    "selector": {
      "type": "string",
      "description": "CSS selector of the element to click"
    }
  }
}

{
  "type": "object",
  "required": [
    "selector",
    "value"
  ],
  "properties": {
    "value": {
      "type": "string",
      "description": "Value to fill into the field"
    },
    "selector": {
      "type": "string",
      "description": "CSS selector of the input field"
    }
  }
}

{
  "type": "object",
  "required": [
    "script"
  ],
  "properties": {
    "script": {
      "type": "string",
      "description": "JavaScript code to execute in the browser"
    }
  }
}