rod MCP Server

Use This MCP server To

Automate web page interactions like clicking and form filling Capture screenshots of web pages for documentation or analysis Generate PDFs from web pages for offline viewing or sharing Enable LLMs to navigate and manipulate browser content programmatically Run browser automation tasks in headless mode for CI/CD pipelines Extend browser automation capabilities with custom MCP tools Integrate web automation into AI workflows for data extraction Test web applications by simulating user interactions automatically

README

Rod MCP Server

Wow! It's awesome, now you can use the MCP server of Rod!🚀

Rod-MCP provides browser automation capabilities for your applications by using Rod. The server provides many useful mcp tools enable LLMs to interact with the web pages, like click, take screenshot, save page as pdf etc.

Engilsh | 中文

Features

🚀 Browser automation powered by Rod
🎯 Rich web interaction capabilities
- Element clicking
- Screenshot capture
- PDF generation
- And more...
🎨 Headless/GUI mode support
⚡ High performance and stability
🔧 Easy to configure and extend
🤖 Designed for LLMs interaction

Installation

Prerequisites

Go 1.23 or higher
Chrome/Chromium browser

Steps

Clone the repository:

git clone https://github.com/go-rod/rod-mcp.git
cd rod-mcp

Install dependencies:

go mod tidy

Build the project:

go build

Usage

Basic Usage

Clone Repo and Build Self or Go to Download Release
Configure MCP:

{
    "mcpServers": {
        "rod-mcp": {
            "command": "rod-mcp",
            "args": [
                "-c", "rod-mcp.yaml"
            ]
        }
    }
}

Configuration

The configuration file supports the following options:

serverName: Server name, default is "Rod Server"
browserBinPath: Browser executable file path, use system default browser if empty
headless: Whether to run the browser in headless mode, default is false
browserTempDir: Browser temporary file directory, default is "./rod/browser"
noSandbox: Whether to disable sandbox mode, default is false
proxy: Proxy server settings, supports socks5 proxy

Project Structure

rod-mcp/
├── assets/          # Static resources
├── banner/          # Banner resources
├── cmd.go           # Command line processing
├── main.go          # Program entry
├── resources/       # Resource files
├── server.go        # Server implementation
├── tools/           # Tool implementation
├── types/           # Type definitions
└── utils/           # Utility functions

Contribution Guidelines

Welcome to submit Pull Request or create Issue!

License

This project is licensed under the MIT License - see the LICENSE file

rod-mcp FAQ

What browsers does Rod MCP Server support?

Rod MCP Server supports Chrome and Chromium browsers, enabling robust automation.

How do I install Rod MCP Server?

Install Go 1.23+, clone the repository, and ensure Chrome/Chromium is installed.

Can Rod MCP Server run in headless mode?

Yes, it supports both headless and GUI modes for flexible automation.

Is Rod MCP Server extendable with custom tools?

Yes, it is designed for easy configuration and extension to add new capabilities.

What kind of web interactions can Rod MCP Server perform?

It can click elements, take screenshots, save pages as PDFs, and more.

How does Rod MCP Server integrate with LLMs?

It exposes browser automation functions as MCP tools for LLM-driven workflows.

What are the prerequisites for running Rod MCP Server?

Requires Go 1.23 or higher and Chrome/Chromium browser installed.

Is Rod MCP Server suitable for production use?

Yes, it is built for high performance and stability in production environments.