Darbot Browser MCP

🤖 Your Autonomous Browser Companion - Powered by AI

A Model Context Protocol (MCP) server that provides intelligent autonomous browser capabilities. This server enables AI models to interact with web pages through structured accessibility snapshots, delivering autonomous browsing without requiring vision models. Optimized for Microsoft Edge with comprehensive work profile support.

✨ Key Features

• 🚀 Fast and lightweight - Uses accessibility tree, not pixel-based input
• 🧠 AI-friendly - No vision models needed, operates purely on structured data
• 🎯 Deterministic - Avoids ambiguity common with screenshot-based approaches
• 🔄 Work Profiles - Save and restore complete browser sessions
• 🛠️ 29 Autonomous Tools - Comprehensive autonomous browser capabilities
• ⚡ Multi-Platform - Available as NPM package, VS Code extension, NuGet package, and browser extension

📋 Requirements

• Node.js 18 or newer
• VS Code, Cursor, Windsurf, Claude Desktop or any other MCP client
• Microsoft Edge (recommended) or Chrome/Firefox/WebKit

📦 Installation Options

Darbot Browser MCP is available in multiple package formats:

🔧 NPM Package

# Install globally
npm install -g @darbotlabs/darbot-browser-mcp

# Or use with npx (recommended)
npx @darbotlabs/darbot-browser-mcp@latest

🔌 VS Code Extension

Install the "Darbot Browser MCP" extension from the VS Code marketplace or search for darbotlabs.darbot-browser-mcp.

The extension automatically configures the MCP server when installed - just enable MCP in VS Code settings and start the server!

📥 Install VS Code Extension

Quick Setup:

1. Install the extension from VS Code marketplace
2. The extension will automatically prompt you to enable MCP and configure the server
3. Use Command Palette: "Darbot Browser MCP: Start Server"
4. Start chatting with GitHub Copilot using browser automation tools!

📚 NuGet Package (.NET)

# Install for .NET projects
dotnet add package DarbotLabs.Browser.MCP

🌐 Browser Extension

Install the Browser MCP Bridge extension from the Chrome Web Store to share browser tabs with the MCP server.

🎯 Why Choose Darbot Browser MCP?

| Traditional Browser Automation | 🤖 Darbot Browser MCP | |--------------------------------|------------------------| | ❌ Pixel-based, brittle selectors | ✅ AI-friendly accessibility snapshots | | ❌ Requires vision models | ✅ Pure structured data approach | | ❌ Complex setup and maintenance | ✅ Simple NPM install, ready in seconds | | ❌ Browser-specific code | ✅ Universal MCP protocol | | ❌ No session management | ✅ Advanced autonomous work profiles |

🛠️ Complete Autonomous Toolkit (29 Tools)

• browser_navigate - Autonomously navigate to any URL
• browser_click - Autonomous intelligent element clicking
• browser_type - Autonomous smart text input with submit options
• browser_snapshot - AI-optimized autonomous accessibility snapshots
• browser_wait_for - Autonomous intelligent waiting conditions

• browser_save_profile - Autonomously save complete browser sessions
• browser_switch_profile - Autonomously load saved profiles
• browser_list_profiles - Autonomously manage all your profiles
• browser_delete_profile - Autonomous clean profile management

• browser_take_screenshot - Autonomous high-quality screenshots
• browser_pdf_save - Autonomous PDF generation from pages
• browser_file_upload - Autonomous file upload handling

• browser_tab_new - Autonomously open new tabs
• browser_tab_list - Autonomously get all open tabs
• browser_tab_select - Autonomously switch between tabs
• browser_tab_close - Autonomous clean tab management

• browser_generate_playwright_test - Autonomously auto-generate test code
• browser_console_messages - Autonomous debug with console access
• browser_network_requests - Autonomous network activity monitoring

📖 View All 29 Tools

🚀 Getting Started

The fastest way to get started is with the VS Code extension, which automatically configures everything for you. For other clients, you'll need to manually configure the MCP server.

🔌 VS Code (Automatic Setup)

1. Install the VS Code Extension
2. Extension auto-configures MCP settings
3. Start the server via Command Palette
4. Use with GitHub Copilot Chat!

⚙️ Manual Configuration (Other Clients)

For Claude Desktop, Cursor, Windsurf, etc., add this configuration:

{
  "mcpServers": {
    "browser": {
      "command": "npx",
      "args": [
        "@darbotlabs/darbot-browser-mcp@latest"
      ]
    }
  }
}

📱 Quick Install Buttons

🔌 VS Code (Automatic):

⚙️ Manual Configuration:

🚀 Recommended: Use the VS Code Extension for automatic setup!

The Darbot Browser MCP Extension automatically handles all configuration:

1. Install from marketplace: Search "Darbot Browser MCP" in VS Code extensions
2. Auto-configuration: Extension prompts to enable MCP and configures the server
3. Start & Use: Use Command Palette → "Darbot Browser MCP: Start Server"
4. Chat with Copilot: Ask GitHub Copilot to "browse to example.com"

Manual CLI installation (if you prefer):

# For VS Code
code --add-mcp '{"name":"browser","command":"npx","args":["@darbotlabs/darbot-browser-mcp@latest"]}'

After installation, the Browser MCP server will be available for use with your GitHub Copilot agent in VS Code.

Click the button to install:

Or install manually:

Go to Cursor Settings -> MCP -> Add new MCP Server. Name to your liking, use command type with the command npx @darbotlabs/darbot-browser-mcp. You can also verify config or add command like arguments via clicking Edit.

{
  "mcpServers": {
    "browser": {
      "command": "npx",
      "args": [
        "@darbotlabs/darbot-browser-mcp@latest"
      ]
    }
  }
}

Follow Windsuff MCP documentation. Use following configuration:

{
  "mcpServers": {
    "browser": {
      "command": "npx",
      "args": [
        "@darbotlabs/darbot-browser-mcp@latest"
      ]
    }
  }
}

Follow the MCP install guide, use following configuration:

{
  "mcpServers": {
    "browser": {
      "command": "npx",
      "args": [
        "@darbotlabs/darbot-browser-mcp@latest"
      ]
    }
  }
}

Use the Claude Code CLI to add the Browser MCP server:

claude mcp add browser npx @darbotlabs/darbot-browser-mcp@latest

Open Qodo Gen chat panel in VSCode or IntelliJ → Connect more tools → + Add new MCP → Paste the following configuration:

{
  "mcpServers": {
    "browser": {
      "command": "npx",
      "args": [
        "@darbotlabs/darbot-browser-mcp@latest"
      ]
    }
  }
}

Click Save.

Configuration

Browser MCP server supports following arguments. They can be provided in the JSON configuration above, as a part of the "args" list:

> npx darbot-browser-mcp@latest --help
  --allowed-origins <origins>  semicolon-separated list of origins to allow the
                               browser to request. Default is to allow all.
  --blocked-origins <origins>  semicolon-separated list of origins to block the
                               browser from requesting. Blocklist is evaluated
                               before allowlist. If used without the allowlist,
                               requests not matching the blocklist are still
                               allowed.
  --block-service-workers      block service workers
  --browser <browser>          browser or chrome channel to use, possible
                               values: msedge, chrome, firefox, webkit.
  --browser-agent <endpoint>   Use browser agent (experimental).
  --caps <caps>                comma-separated list of capabilities to enable,
                               possible values: tabs, pdf, history, wait, files,
                               install. Default is all.
  --cdp-endpoint <endpoint>    CDP endpoint to connect to.
  --config <path>              path to the configuration file.
  --device <device>            device to emulate, for example: "iPhone 15"
  --executable-path <path>     path to the browser executable.
  --headless                   run browser in headless mode, headed by default
  --host <host>                host to bind server to. Default is localhost. Use
                               0.0.0.0 to bind to all interfaces.
  --ignore-https-errors        ignore https errors
  --isolated                   keep the browser profile in memory, do not save
                               it to disk.
  --image-responses <mode>     whether to send image responses to the client.
                               Can be "allow", "omit", or "auto". Defaults to
                               "auto", which sends images if the client can
                               display them.
  --no-sandbox                 disable the sandbox for all process types that
                               are normally sandboxed.
  --output-dir <path>          path to the directory for output files.
  --port <port>                port to listen on for SSE transport.
  --proxy-bypass <bypass>      comma-separated domains to bypass proxy, for
                               example ".com,chromium.org,.domain.com"
  --proxy-server <proxy>       specify proxy server, for example
                               "http://myproxy:3128" or "socks5://myproxy:8080"
  --save-trace                 Whether to save the Playwright Trace of the
                               session into the output directory.
  --storage-state <path>       path to the storage state file for isolated
                               sessions.
  --user-agent <ua string>     specify user agent string
  --user-data-dir <path>       path to the user data directory. If not
                               specified, a temporary directory will be created.
  --viewport-size <size>       specify browser viewport size in pixels, for
                               example "1280, 720"
  --vision                     Run server that uses screenshots (Aria snapshots
                               are used by default)

User profile

You can run Browser MCP with persistent profile like a regular browser (default), or in the isolated contexts for the testing sessions.

Persistent profile

All the logged in information will be stored in the persistent profile, you can delete it between sessions if you'd like to clear the offline state. Persistent profile is located at the following locations and you can override it with the --user-data-dir argument.

# Windows
%USERPROFILE%\AppData\Local\ms-playwright\mcp-{channel}-profile

# macOS
- ~/Library/Caches/ms-playwright/mcp-{channel}-profile

# Linux
- ~/.cache/ms-playwright/mcp-{channel}-profile

Isolated

In the isolated mode, each session is started in the isolated profile. Every time you ask MCP to close the browser, the session is closed and all the storage state for this session is lost. You can provide initial storage state to the browser via the config's contextOptions or via the --storage-state argument. Learn more about the storage state here.

{
  "mcpServers": {
    "browser": {
      "command": "npx",
      "args": [
        "@darbotlabs/darbot-browser-mcp@latest",
        "--isolated",
        "--storage-state={path/to/storage.json}"
      ]
    }
  }
}

Configuration file

The Browser MCP server can be configured using a JSON configuration file. You can specify the configuration file using the --config command line option:

npx @darbotlabs/darbot-browser-mcp@latest --config path/to/config.json

{
  // Browser configuration
  browser?: {
    // Browser type to use (chromium, firefox, or webkit)
    browserName?: 'chromium' | 'firefox' | 'webkit';

    // Keep the browser profile in memory, do not save it to disk.
    isolated?: boolean;

    // Path to user data directory for browser profile persistence
    userDataDir?: string;

    // Browser launch options (see Playwright docs)
    // @see https://playwright.dev/docs/api/class-browsertype#browser-type-launch
    launchOptions?: {
      channel?: string;        // Browser channel (e.g. 'msedge')
      headless?: boolean;      // Run in headless mode
      executablePath?: string; // Path to browser executable
      // ... other Playwright launch options
    };

    // Browser context options
    // @see https://playwright.dev/docs/api/class-browser#browser-new-context
    contextOptions?: {
      viewport?: { width: number, height: number };
      // ... other Playwright context options
    };

    // CDP endpoint for connecting to existing browser
    cdpEndpoint?: string;

    // Remote Playwright server endpoint
    remoteEndpoint?: string;
  },

  // Server configuration
  server?: {
    port?: number;  // Port to listen on
    host?: string;  // Host to bind to (default: localhost)
  },

  // List of enabled capabilities
  capabilities?: Array<
    'core' |    // Core browser automation
    'tabs' |    // Tab management
    'pdf' |     // PDF generation
    'history' | // Browser history
    'wait' |    // Wait utilities
    'files' |   // File handling
    'install' | // Browser installation
    'testing'   // Testing
  >;

  // Enable vision mode (screenshots instead of accessibility snapshots)
  vision?: boolean;

  // Directory for output files
  outputDir?: string;

  // Network configuration
  network?: {
    // List of origins to allow the browser to request. Default is to allow all. Origins matching both `allowedOrigins` and `blockedOrigins` will be blocked.
    allowedOrigins?: string[];

    // List of origins to block the browser to request. Origins matching both `allowedOrigins` and `blockedOrigins` will be blocked.
    blockedOrigins?: string[];
  };
 
  /**
   * Do not send image responses to the client.
   */
  noImageResponses?: boolean;
}

Standalone MCP server

When running headed browser on system w/o display or from worker processes of the IDEs, run the MCP server from environment with the DISPLAY and pass the --port flag to enable SSE transport.

npx @darbotlabs/darbot-browser-mcp@latest --port 8931

And then in MCP client config, set the url to the SSE endpoint:

{
  "mcpServers": {
    "playwright": {
      "url": "http://localhost:8931/sse"
    }
  }
}

NOTE: The Docker implementation only supports headless chromium at the moment.

{
  "mcpServers": {
    "playwright": {
      "command": "docker",
      "args": ["run", "-i", "--rm", "--init", "--pull=always", "mcr.microsoft.com/playwright/mcp"]
    }
  }
}

You can build the Docker image yourself.

docker build -t mcr.microsoft.com/playwright/mcp .

import http from 'http';

import { createConnection } from '@darbotlabs/darbot-browser-mcp';
import { SSEServerTransport } from '@modelcontextprotocol/sdk/server/sse.js';

http.createServer(async (req, res) => {
  // ...

  // Creates a headless Browser MCP server with SSE transport
  const connection = await createConnection({ browser: { launchOptions: { headless: true } } });
  const transport = new SSEServerTransport('/messages', res);
  await connection.sever.connect(transport);

  // ...
});

Tools

The tools are available in two modes:

1. Snapshot Mode (default): Uses accessibility snapshots for better performance and reliability
2. Vision Mode: Uses screenshots for visual-based interactions

To use Vision Mode, add the --vision flag when starting the server:

{
  "mcpServers": {
    "browser": {
      "command": "npx",
      "args": [
        "@darbotlabs/darbot-browser-mcp@latest",
        "--vision"
      ]
    }
  }
}

Vision Mode works best with the computer use models that are able to interact with elements using X Y coordinate space, based on the provided screenshot.

• browser_snapshot
  • Title: Page snapshot
  • Description: Capture accessibility snapshot of the current page, this is better than screenshot
  • Parameters: None
  • Read-only: true

• browser_click
  • Title: Click
  • Description: Perform click on a web page
  • Parameters:
    • element (string): Human-readable element description used to obtain permission to interact with the element
    • ref (string): Exact target element reference from the page snapshot
    • doubleClick (boolean, optional): Whether to perform a double click instead of a single click
  • Read-only: false

• browser_drag
  • Title: Drag mouse
  • Description: Perform drag and drop between two elements
  • Parameters:
    • startElement (string): Human-readable source element description used to obtain the permission to interact with the element
    • startRef (string): Exact source element reference from the page snapshot
    • endElement (string): Human-readable target element description used to obtain the permission to interact with the element
    • endRef (string): Exact target element reference from the page snapshot
  • Read-only: false

• browser_hover
  • Title: Hover mouse
  • Description: Hover over element on page
  • Parameters:
    • element (string): Human-readable element description used to obtain permission to interact with the element
    • ref (string): Exact target element reference from the page snapshot
  • Read-only: true

• browser_type
  • Title: Type text
  • Description: Type text into editable element
  • Parameters:
    • element (string): Human-readable element description used to obtain permission to interact with the element
    • ref (string): Exact target element reference from the page snapshot
    • text (string): Text to type into the element
    • submit (boolean, optional): Whether to submit entered text (press Enter after)
    • slowly (boolean, optional): Whether to type one character at a time. Useful for triggering key handlers in the page. By default entire text is filled in at once.
  • Read-only: false

• browser_select_option
  • Title: Select option
  • Description: Select an option in a dropdown
  • Parameters:
    • element (string): Human-readable element description used to obtain permission to interact with the element
    • ref (string): Exact target element reference from the page snapshot
    • values (array): Array of values to select in the dropdown. This can be a single value or multiple values.
  • Read-only: false

• browser_press_key
  • Title: Press a key
  • Description: Press a key on the keyboard
  • Parameters:
    • key (string): Name of the key to press or a character to generate, such as ArrowLeft or a
  • Read-only: false

• browser_wait_for
  • Title: Wait for
  • Description: Wait for text to appear or disappear or a specified time to pass
  • Parameters:
    • time (number, optional): The time to wait in seconds
    • text (string, optional): The text to wait for
    • textGone (string, optional): The text to wait for to disappear
  • Read-only: true

• browser_file_upload
  • Title: Upload files
  • Description: Upload one or multiple files
  • Parameters:
    • paths (array): The absolute paths to the files to upload. Can be a single file or multiple files.
  • Read-only: false

• browser_handle_dialog
  • Title: Handle a dialog
  • Description: Handle a dialog
  • Parameters:
    • accept (boolean): Whether to accept the dialog.
    • promptText (string, optional): The text of the prompt in case of a prompt dialog.
  • Read-only: false

• browser_navigate
  • Title: Navigate to a URL
  • Description: Navigate to a URL
  • Parameters:
    • url (string): The URL to navigate to
  • Read-only: false

• browser_navigate_back
  • Title: Go back
  • Description: Go back to the previous page
  • Parameters: None
  • Read-only: true

• browser_navigate_forward
  • Title: Go forward
  • Description: Go forward to the next page
  • Parameters: None
  • Read-only: true

• browser_take_screenshot
  • Title: Take a screenshot
  • Description: Take a screenshot of the current page. You can't perform actions based on the screenshot, use browser_snapshot for actions.
  • Parameters:
    • raw (boolean, optional): Whether to return without compression (in PNG format). Default is false, which returns a JPEG image.
    • filename (string, optional): File name to save the screenshot to. Defaults to page-{timestamp}.{png|jpeg} if not specified.
    • element (string, optional): Human-readable element description used to obtain permission to screenshot the element. If not provided, the screenshot will be taken of viewport. If element is provided, ref must be provided too.
    • ref (string, optional): Exact target element reference from the page snapshot. If not provided, the screenshot will be taken of viewport. If ref is provided, element must be provided too.
  • Read-only: true

• browser_pdf_save
  • Title: Save as PDF
  • Description: Save page as PDF
  • Parameters:
    • filename (string, optional): File name to save the pdf to. Defaults to page-{timestamp}.pdf if not specified.
  • Read-only: true

• browser_network_requests
  • Title: List network requests
  • Description: Returns all network requests since loading the page
  • Parameters: None
  • Read-only: true

• browser_console_messages
  • Title: Get console messages
  • Description: Returns all console messages
  • Parameters: None
  • Read-only: true

• browser_install
  • Title: Install the browser specified in the config
  • Description: Install the browser specified in the config. Call this if you get an error about the browser not being installed.
  • Parameters: None
  • Read-only: false

• browser_close
  • Title: Close browser
  • Description: Close the page
  • Parameters: None
  • Read-only: true

• browser_resize
  • Title: Resize browser window
  • Description: Resize the browser window
  • Parameters:
    • width (number): Width of the browser window
    • height (number): Height of the browser window
  • Read-only: true

• browser_tab_list
  • Title: List tabs
  • Description: List browser tabs
  • Parameters: None
  • Read-only: true

• browser_tab_new
  • Title: Open a new tab
  • Description: Open a new tab
  • Parameters:
    • url (string, optional): The URL to navigate to in the new tab. If not provided, the new tab will be blank.
  • Read-only: true

• browser_tab_select
  • Title: Select a tab
  • Description: Select a tab by index
  • Parameters:
    • index (number): The index of the tab to select
  • Read-only: true

• browser_tab_close
  • Title: Close a tab
  • Description: Close a tab
  • Parameters:
    • index (number, optional): The index of the tab to close. Closes current tab if not provided.
  • Read-only: false

• browser_save_profile
  • Title: Save Work Profile
  • Description: Save the current browser state as a work profile
  • Parameters:
    • name (string): Name for the work profile
    • description (string, optional): Optional description for the work profile
  • Read-only: false

• browser_switch_profile
  • Title: Switch Work Profile
  • Description: Switch to a saved work profile
  • Parameters:
    • name (string): Name of the work profile to switch to
  • Read-only: false

• browser_list_profiles
  • Title: List Work Profiles
  • Description: List all saved work profiles
  • Parameters: None
  • Read-only: true

• browser_delete_profile
  • Title: Delete Work Profile
  • Description: Delete a saved work profile
  • Parameters:
    • name (string): Name of the work profile to delete
  • Read-only: false

• browser_generate_playwright_test
  • Title: Generate a Playwright test
  • Description: Generate a Playwright test for given scenario
  • Parameters:
    • name (string): The name of the test
    • description (string): The description of the test
    • steps (array): The steps of the test
  • Read-only: true

• browser_screen_capture
  • Title: Take a screenshot
  • Description: Take a screenshot of the current page
  • Parameters: None
  • Read-only: true

• browser_screen_move_mouse
  • Title: Move mouse
  • Description: Move mouse to a given position
  • Parameters:
    • element (string): Human-readable element description used to obtain permission to interact with the element
    • x (number): X coordinate
    • y (number): Y coordinate
  • Read-only: true

• browser_screen_click
  • Title: Click
  • Description: Click left mouse button
  • Parameters:
    • element (string): Human-readable element description used to obtain permission to interact with the element
    • x (number): X coordinate
    • y (number): Y coordinate
  • Read-only: false

• browser_screen_drag
  • Title: Drag mouse
  • Description: Drag left mouse button
  • Parameters:
    • element (string): Human-readable element description used to obtain permission to interact with the element
    • startX (number): Start X coordinate
    • startY (number): Start Y coordinate
    • endX (number): End X coordinate
    • endY (number): End Y coordinate
  • Read-only: false

• browser_screen_type
  • Title: Type text
  • Description: Type text
  • Parameters:
    • text (string): Text to type into the element
    • submit (boolean, optional): Whether to submit entered text (press Enter after)
  • Read-only: false

• browser_press_key
  • Title: Press a key
  • Description: Press a key on the keyboard
  • Parameters:
    • key (string): Name of the key to press or a character to generate, such as ArrowLeft or a
  • Read-only: false

• browser_wait_for
  • Title: Wait for
  • Description: Wait for text to appear or disappear or a specified time to pass
  • Parameters:
    • time (number, optional): The time to wait in seconds
    • text (string, optional): The text to wait for
    • textGone (string, optional): The text to wait for to disappear
  • Read-only: true

• browser_file_upload
  • Title: Upload files
  • Description: Upload one or multiple files
  • Parameters:
    • paths (array): The absolute paths to the files to upload. Can be a single file or multiple files.
  • Read-only: false

• browser_handle_dialog
  • Title: Handle a dialog
  • Description: Handle a dialog
  • Parameters:
    • accept (boolean): Whether to accept the dialog.
    • promptText (string, optional): The text of the prompt in case of a prompt dialog.
  • Read-only: false

Package Formats

NPM Package

• Name: @darbotlabs/darbot-browser-mcp
• Installation: npm install -g @darbotlabs/darbot-browser-mcp
• Usage: npx @darbotlabs/darbot-browser-mcp@latest

VS Code Extension

• Name: Darbot Browser MCP
• Publisher: darbotlabs
• Installation: Search for "Darbot Browser MCP" in VS Code Extensions marketplace
• Features: Start/stop MCP server, status monitoring, configuration management

NuGet Package (.NET)

• Name: DarbotLabs.Browser.MCP
• Installation: dotnet add package DarbotLabs.Browser.MCP
• Usage: Host the Browser MCP server in .NET applications

Browser Extension

• Name: Browser MCP Bridge
• Installation: Available in Chrome Web Store (coming soon)
• Features: Share browser tabs with MCP server via CDP bridge

Repository Structure

• /vscode-extension/ - VS Code extension source
• /dotnet/ - .NET NuGet package source
• /extension/ - Browser extension source
• /src/ - Main MCP server source code
• /tests/ - Test suite