Configurable Puppeteer MCP Server logo

Configurable Puppeteer MCP Server

by afshawnlotfi

A Model Context Protocol server that provides browser automation capabilities using Puppeteer with configurable options. It enables LLMs to interact with web pages, take screenshots, and execute JavaScript in a real browser environment.

View on GitHub

Last updated: N/A

What is Configurable Puppeteer MCP Server?

This server is a Model Context Protocol (MCP) server that leverages Puppeteer to provide browser automation capabilities. It allows Large Language Models (LLMs) to interact with web pages, capture screenshots, and execute JavaScript code within a real browser environment, all with configurable options.

How to use Configurable Puppeteer MCP Server?

The server can be configured using environment variables, particularly PUPPETEER_ARGS, to customize Puppeteer launch options. It provides tools like puppeteer_navigate, puppeteer_screenshot, puppeteer_click, puppeteer_hover, puppeteer_fill, puppeteer_select, and puppeteer_evaluate to interact with web pages. Resources like console logs and screenshots are accessible via console://logs and screenshot://<name> respectively.

Key features of Configurable Puppeteer MCP Server

  • Browser automation

  • Console log monitoring

  • Screenshot capabilities

  • JavaScript execution

  • Basic web interaction (navigation, clicking, form filling)

  • Configurable Puppeteer options through environment variables

Use cases of Configurable Puppeteer MCP Server

  • Web scraping and data extraction

  • Automated testing of web applications

  • Generating screenshots of web pages

  • Interacting with web-based APIs

FAQ from Configurable Puppeteer MCP Server

What is Puppeteer?

Puppeteer is a Node library which provides a high-level API to control Chrome or Chromium programmatically.

How do I configure Puppeteer options?

You can configure Puppeteer launch options by providing a JSON string in the PUPPETEER_ARGS environment variable.

What are the available tools?

The server provides tools for navigation, screenshot capture, clicking elements, hovering elements, filling forms, selecting elements, and executing JavaScript.

How do I access console logs?

Browser console output is accessible in text format via the console://logs resource.

How do I access screenshots?

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