About Rod MCP Server
Rod MCP Server is an MCP server built on the Rod browser automation library, enabling LLMs to interact with web pages. It is aimed at developers who want models to operate a browser, offering tools such as clicking, screenshots and PDF export.
Key features
- 01Browser automation powered by Rod
- 02Element clicking
- 03Screenshot capture
- 04PDF generation from pages
- 05Headless and GUI mode support
- 06Configuration through a YAML file
Use cases
- 01Letting an LLM click elements and inspect page content
- 02Capturing screenshots or PDF copies of web pages
- 03Running automated web operations in a headless browser
MCP support
This project is an MCP server that exposes browser operation tools such as clicking, screenshots and PDF generation to MCP clients.
Configuration
Local server config is the same for every client. Copy it into your client’s MCP config file.
We haven’t collected a package or remote endpoint for this server. Follow the instructions in the project README.
Tools
Local servers expose tools only once running on your machine, and the maintainer has not provided a tool list.
Details
From the project READMERod 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
Comments
New to MCP?
From what the protocol is to installing your first server, these answers cover most first questions.
An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.