MCP Browser Automation Server

MCP server for browser automation with screenshot and console logging capabilities

Catalog onlyCatalog onlySTDIO

Overview

MCP Browser Automation Server is a powerful tool that allows users to automate browser actions, take screenshots, and monitor console logs through a REST API.

To use the server, clone the repository, set up a virtual environment, install dependencies, and start the server. You can then interact with the API to create sessions and perform various browser actions.

Create and manage browser sessions - Navigate to specified URLs - Capture full-page or element-specific screenshots - Interact with web elements (click, fill forms) - Real-time monitoring of console logs via WebSocket - Close browser sessions when done

Automated testing of web applications
Web scraping for data collection
Monitoring website performance and logs
Taking screenshots for documentation or reporting

Add to your AI client

Use these steps to connect MCP Browser Automation Server 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": {
    "mcp-browser-automation-weir1": {
      "command": "npx",
      "args": [
        "-y",
        "@modelcontextprotocol/server-mcp-browser-automation-weir1"
      ]
    }
  }
}

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": {
    "mcp-browser-automation-weir1": {
      "command": "npx",
      "args": [
        "-y",
        "@modelcontextprotocol/server-mcp-browser-automation-weir1"
      ]
    }
  }
}

Claude Code

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

.mcp.json (project root)

{
  "mcpServers": {
    "mcp-browser-automation-weir1": {
      "command": "npx",
      "args": [
        "-y",
        "@modelcontextprotocol/server-mcp-browser-automation-weir1"
      ]
    }
  }
}

VS Code (Copilot)

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

.vscode/mcp.json

{
  "servers": {
    "mcp-browser-automation-weir1": {
      "type": "stdio",
      "command": "npx",
      "args": [
        "-y",
        "@modelcontextprotocol/server-mcp-browser-automation-weir1"
      ]
    }
  }
}

Windsurf

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

~/.codeium/windsurf/mcp_config.json

{
  "mcpServers": {
    "mcp-browser-automation-weir1": {
      "command": "npx",
      "args": [
        "-y",
        "@modelcontextprotocol/server-mcp-browser-automation-weir1"
      ]
    }
  }
}

Cline

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

Cline MCP Settings (via UI)

{
  "mcpServers": {
    "mcp-browser-automation-weir1": {
      "command": "npx",
      "args": [
        "-y",
        "@modelcontextprotocol/server-mcp-browser-automation-weir1"
      ]
    }
  }
}

FAQ

What programming language is used?

The server is built using Python.

Is it necessary to install Playwright?

Yes, Playwright is required to run the browser automation tasks.

Can I run multiple sessions simultaneously?

Yes, you can create multiple sessions to run tasks in parallel.

Browser automation