rod-mcp

rod-mcp

17

Rod MCP Server provides browser automation capabilities using Rod, enhancing web interaction for applications. It supports headless/GUI modes, high performance, and is designed for LLMs. Easy configuration and extensibility are key features.

Rod MCP Server

Rod-MCP provides browser automation capabilities for applications using the Rod library. It offers tools to enable LLMs to interact with web pages, such as clicking elements, taking screenshots, and saving pages as PDFs.

Features

  • Browser automation powered by Rod
  • Rich web interaction capabilities, including element clicking, screenshot capture, PDF generation
  • 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

  1. Clone the repository
  2. Install dependencies
  3. Build the project

Usage

  • Clone repo and build or download release
  • Configure MCP with the server name, browser path, headless mode, and more.

Configuration

Options include server name, browser path, headless mode, browser temp directory, sandbox mode, and proxy settings.

Project Structure

  • Various directories for assets, resources, command processing, program entry, server implementation, and more.

Contribution Guidelines

Submit pull requests or create issues.

License

MIT License.