Browser Automation

Provides browser automation for Claude and MCP-compatible assistants, including navigation, interaction, and data extraction.

javascript

GitHub Stars

javascript

Language

4 months ago

First Indexed

3 weeks ago

Catalog Refreshed

Documentation & install

Readme and setup notes from the catalogue, plus a client-ready config you can copy for your MCP host.

Installation

Add the following to your MCP client configuration file.

Configuration

View docs

{
  "mcpServers": {
    "samihalawa-browser-automation-server": {
      "command": "/path/to/node",
      "args": [
        "/path/to/browser-automation-server/build/index.js"
      ],
      "env": {
        "PATH": "/usr/local/bin:/usr/bin:/bin",
        "NODE_PATH": "/path/to/node_modules"
      }
    }
  }
}

You run a local MCP-compatible server that lets you automate browser actions from Claude and other assistants. It can control browsers, take screenshots, interact with page elements, navigate sessions, fill forms, and extract data, all through simple, scriptable commands. This guide walks you through using, installing, and configuring the Browser Automation MCP Server so you can automate web tasks reliably from your AI workflows.

How to use

You integrate the Browser Automation MCP Server with your MCP client to perform common browser actions. Start the server locally, then call the available tools to navigate web pages, capture screenshots, click elements, type text, extract data, and evaluate scripts in the browser context. Each action returns results that you can feed back into your AI prompts or workflows.

How to install

# Clone the repository
git clone https://github.com/samihalawa/browser-automation-server.git
cd browser-automation-server

# Install dependencies
npm install

# Build the server
npm run build

Configuration and usage notes

To run the server locally and expose it to your MCP client, you start the server process using the command shown in the setup example. You can point your MCP client to this local server and use the available tools to automate browser tasks.

npm start

Security and best practices

Keep the server updated and run it behind your usual security boundaries. Limit who can access the local port (default 3008) and consider network restrictions or a reverse proxy if you expose it beyond your trusted environment.

Notes on tools and capabilities

The server exposes the following capabilities to your MCP client: navigate, screenshot, click, type, extract, and evaluate. Use these to automate browsing tasks end-to-end, from visiting a URL to submitting forms and retrieving data.

Available tools

navigate

Navigate the browser to a specified URL and wait for the page to load or reach a defined ready state.

screenshot

Capture a screenshot of the current page, either the viewport or the full page, and save to a path or return as base64.

click

Click a DOM element identified by a CSS selector, with optional waiting for the element to appear.

type

Type text into an input element selected by a CSS selector, with optional keystroke delay.

extract

Extract data from the page by selecting elements and retrieving text or attribute values.

evaluate

Run custom JavaScript in the browser context and return the result.

Built by

VeilStrat

AI signals for GTM teams