Configurable Puppeteer MCP Server

@afshawnlotfi

代码仓库

基本信息

分类

浏览器自动化

传输方式

stdio

作者

afshawnlotfi

关于 Configurable Puppeteer MCP Server

Configurable Puppeteer MCP Server

#puppeteer #browser-automation #mcp-server

Configurable Puppeteer MCP Server 配置

使用下面的配置,将此服务器添加到你的 MCP 客户端。

{
  "mcpServers": {
    "puppeteer": {
      "command": "npx",
      "args": [
        "-y",
        "github:afshawnlotfi/mcp-configurable-puppeteer"
      ],
      "env": {
        "PUPPETEER_ARGS": "{\"browser\": \"firefox\"}"
      }
    }
  }
}

Configurable Puppeteer MCP Server 工具

Navigate to any URL in the browser

Capture screenshots of the entire page or specific elements

Click elements on the page

Hover elements on the page

Fill out input fields

Select an element with SELECT tag

Execute JavaScript in the browser console

概览

What is Configurable Puppeteer MCP Server?

Configurable Puppeteer MCP Server is a Model Context Protocol server that provides browser automation capabilities using Puppeteer with configurable launch options. It enables LLMs to interact with web pages, take screenshots, and execute JavaScript in a real browser environment, with customization through environment variables.

How to use Configurable Puppeteer MCP Server?

Use the NPX command npx -y github:afshawnlotfi/mcp-configurable-puppeteer in your MCP client configuration. Optionally set the PUPPETEER_ARGS environment variable to a JSON string of custom Puppeteer launch options (e.g., to use Firefox or set viewport size).

Key features of Configurable Puppeteer MCP Server

Browser automation for web page interaction
Console log monitoring from the browser
Screenshot capturing of entire pages or elements
JavaScript execution in the browser console
Basic web interaction: navigation, clicking, form filling
Configurable Puppeteer options through environment variables

Use cases of Configurable Puppeteer MCP Server

Navigate to any URL and capture screenshots
Automate form filling and clicking on web pages
Execute JavaScript to extract dynamic content
Monitor browser console logs for debugging or data collection
Interact with web elements via hover, select, and evaluate commands

常见问题

How do I configure custom Puppeteer options?

Set the `PUPPETEER_ARGS` environment variable to a JSON string of Puppeteer launch options, such as `{"browser": "firefox"}` or `{"defaultViewport": {"width": 1280, "height": 800}}`.

What tools are available in this server?

Tools include `puppeteer_navigate`, `puppeteer_screenshot`, `puppeteer_click`, `puppeteer_hover`, `puppeteer_fill`, `puppeteer_select`, and `puppeteer_evaluate`.

How do I access screenshots after capturing them?

Screenshots are accessible via the resource `screenshot://<name>`, where `<name>` is the name provided during capture.

What resources does the server provide?

The server provides console logs at `console://logs` (text format) and screenshots at `screenshot://<name>` (PNG images).

How do I execute JavaScript in the browser?

Use the `puppeteer_evaluate` tool with the `script` input containing the JavaScript code to execute.

浏览器自动化分类下的更多 MCP 服务器

Fetch MCP Server

zcaceres

A flexible HTTP fetching Model Context Protocol server.

797

playwright-server MCP server

blackwhite084

189

Browse Bridge

Share selected Chrome tabs with AI agents. You enable the tab you want to share and maintain the ability to instantly take control. Browse Bridge is a remote MCP server available at https://mcp.browsebridge.com. What c

Nullprint

nullprintai

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.

Fetch MCP

jae-jae

MCP server for fetch web page content using Playwright headless browser.

1.1K