Pyppeteer Browser Automation

by devalexandre

Not rated
GitHub

About

Enables AI assistants to control headless browsers for web automation tasks including navigation, screenshot capture, element interaction, and dynamic page information access.

Details

Author
devalexandre
Repository
devalexandre/mcp-servers
License
Apache License 2.0
Categories
Productivity, Design, Developer Tools, AI, Automation, API
Tags
#web

- Automated Navigation: Navigate to specific URLs.
- Screenshot Capture: Take screenshots of visited pages.
- Element Interaction: Click on page elements using CSS selectors, XPath, or class names.
- Dynamic Resources: Access dynamic page information, such as the current URL.
- Server Lifecycle Management: Controlled initialization and shutdown of the browser.

---

Setting up with Highlight

This MCP is not yet compatible with Highlight’s one-click setup. However, you can still use it with Highlight by following these steps:

  1. Download and install Highlight from highlightai.com/download
  2. Navigate to the plugins tab and select "Add Custom Plugin"
  3. Configure the plugin with the settings below
    Plugin Name Pyppeteer Browser Automation
    Command (node, npx, python, etc.) npx
    Arguments
    • Argument 1 -y
    • Argument 2 @highlight/mcp-server

    Please refer to the README for specific instructions on how to obtain API keys or other required environment variables.

  4. Enable "Start Automatically" if you want the plugin to start when Highlight launches

From the repository

To install MCP Servers for Claude Desktop automatically via Smithery:

npx -y @smithery/cli install @devalexandre/mcp-servers --client claude

Claude Desktop / Cursor

Paste into your MCP client config file to install this server.

{
    "mcpServers": {
        "pyppeteer browser automation": {
            "env": {},
            "args": [
                "-y",
                "@highlight/mcp-server"
            ],
            "command": "npx"
        }
    }
}

Linux

{
    "env": [],
    "args": [
        "-y",
        "@highlight/mcp-server"
    ],
    "command": "npx"
}

Macos

{
    "env": [],
    "args": [
        "-y",
        "@highlight/mcp-server"
    ],
    "command": "npx"
}

Windows

{
    "env": [],
    "args": [
        "/c",
        "npx",
        "-y",
        "@highlight/mcp-server"
    ],
    "command": "cmd"
}

smithery badge

MCP Servers

smithery badge

Description

The MCP Servers with Pyppeteer is a tool that allows you to control a headless browser using Pyppeteer, enabling automated navigation, screenshot capturing, interaction with page elements, and more. This project was developed to facilitate the creation of automation servers based on the MCP (Multi-Context Protocol) framework.

---

Features

- Automated Navigation: Navigate to specific URLs.
- Screenshot Capture: Take screenshots of visited pages.
- Element Interaction: Click on page elements using CSS selectors, XPath, or class names.
- Dynamic Resources: Access dynamic page information, such as the current URL.
- Server Lifecycle Management: Controlled initialization and shutdown of the browser.

---

Prerequisites

Make sure you have the following installed before getting started:

1. Python 3.7+: The project has been tested with Python 3.12, but earlier versions (3.7+) should also work.
2. pip: Python package manager.
3. Git: To clone the repository.

---

Installation

Installing via Smithery

To install MCP Servers for Claude Desktop automatically via Smithery:

npx -y @smithery/cli install @devalexandre/mcp-servers --client claude

Via Pip GitHub

1. Install the Package:

   pip install -e git+https://github.com/devalexandre/mcp-servers.git#egg=mcp-servers
   

Via Git

1. Clone the Repository:

   git clone https://github.com/devalexandre/mcp-servers.git
   cd mcp-servers

2. Create a Virtual Environment (Optional):

bash
python -m venv venv
source venv/bin/activate # On Windows, use venv\Scripts\activate
pip install -r requirements.txt

3. nstall the Package in Editable Mode:

bash
pip install -e .
```

No reviews yet — be the first

Sign in to leave a review

Use Google, GitHub, or an email account so ratings stay tied to real people.

Email sign in

No reviews posted yet.