drio
Open app

rag-browser

Source

A Browser Automation Tool for Humans and AI - Built with Playwright, optimized for Bun runtime, supporting CLI and MCP Server modes for webpage analysis and automation

Catalog onlyCatalog onlySTDIO

Overview

rag-browser is a browser automation tool designed for both humans and AI, built with Playwright and optimized for the Bun runtime. It allows users to analyze and automate web pages effectively.

To use rag-browser, you can run it in CLI mode or MCP Server mode. In CLI mode, you can execute commands directly in your terminal to analyze web pages or perform actions. In MCP Server mode, it integrates with AI systems for automated tasks.

  • CLI Mode for direct webpage analysis and action execution. - MCP Server Mode for AI integration via Model Context Protocol. - Action support for waiting, clicking, typing, and capturing content. - Stability checks to ensure reliable execution. - Output options for pretty-printed console output or JSON format.
  1. Analyzing webpage structures and interactive elements.
  2. Automating repetitive browser tasks without coding.
  3. Integrating with AI systems for dynamic web interactions.

Add to your AI client

Use these steps to connect rag-browser in Cursor, Claude, VS Code, and other MCP-compatible apps. The same JSON appears in the Use with menu above for one-click copy.

Cursor

Add this to your .cursor/mcp.json file in your project root, then restart Cursor.

.cursor/mcp.json

{
  "mcpServers": {
    "rag-browser-aashari": {
      "command": "npx",
      "args": [
        "-y",
        "@modelcontextprotocol/server-rag-browser-aashari"
      ]
    }
  }
}

Claude Desktop

Add this server entry to the mcpServers object in your Claude Desktop config, then restart the app.

~/Library/Application Support/Claude/claude_desktop_config.json (macOS) or %APPDATA%\Claude\claude_desktop_config.json (Windows)

{
  "mcpServers": {
    "rag-browser-aashari": {
      "command": "npx",
      "args": [
        "-y",
        "@modelcontextprotocol/server-rag-browser-aashari"
      ]
    }
  }
}

Claude Code

Add this to your project's .mcp.json file. Claude Code will detect it automatically.

.mcp.json (project root)

{
  "mcpServers": {
    "rag-browser-aashari": {
      "command": "npx",
      "args": [
        "-y",
        "@modelcontextprotocol/server-rag-browser-aashari"
      ]
    }
  }
}

VS Code (Copilot)

Add this to your .vscode/mcp.json file. Requires the GitHub Copilot extension with MCP support enabled.

.vscode/mcp.json

{
  "servers": {
    "rag-browser-aashari": {
      "type": "stdio",
      "command": "npx",
      "args": [
        "-y",
        "@modelcontextprotocol/server-rag-browser-aashari"
      ]
    }
  }
}

Windsurf

Add this to your Windsurf MCP config file, then restart Windsurf.

~/.codeium/windsurf/mcp_config.json

{
  "mcpServers": {
    "rag-browser-aashari": {
      "command": "npx",
      "args": [
        "-y",
        "@modelcontextprotocol/server-rag-browser-aashari"
      ]
    }
  }
}

Cline

Open Cline settings, navigate to MCP Servers, and add this server configuration.

Cline MCP Settings (via UI)

{
  "mcpServers": {
    "rag-browser-aashari": {
      "command": "npx",
      "args": [
        "-y",
        "@modelcontextprotocol/server-rag-browser-aashari"
      ]
    }
  }
}

FAQ

Can rag-browser be used for any website?

Yes, rag-browser can analyze and automate tasks on any publicly accessible website.

Is rag-browser free to use?

Yes, rag-browser is open-source and free to use under the MIT license.

What are the prerequisites for using rag-browser?

You need Bun (recommended) or Node.js installed to run rag-browser.

Developer tools