@darbotlabs/darbot-browser-mcp

v1.3.0

Published

2 months ago

Darbot Browser - framework for 52 AI-driven browser tools with session state support and VS Code GitHub Copilot agent mode integration

Downloads

151

Darbot Browser MCP

Your Autonomous Browser Companion

Darbot Browser is a framework for autonomous web automation. This tool enables AI models to interact with UI through structured accessibility snapshots, delivering autonomous browsing without requiring vision models. Optimized for Microsoft Edge with comprehensive session state support.

Key Features

Fast and lightweight - Uses accessibility tree, not pixel-based input
DarbotLM framework - No vision models needed, operates purely on structured data
Deterministic - Avoids ambiguity common with screenshot-based approaches
Session States - Save and restore complete browser sessions with Edge profile context
52 Autonomous Tools - Comprehensive autonomous browser capabilities
Autonomous Crawling - BFS strategy with memory, guardrails, and reporting
DarbotLabsMemory System - State tracking and deduplication with darbot-memory-mcp integration
HTML Reports - Comprehensive crawl reports with screenshots and statistics
Multi-Platform - Available as NPM package, VS Code extension, NuGet package, and browser extension

Requirements

Node.js 23 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:

Install the extension from VS Code marketplace
The extension will automatically prompt you to enable MCP and configure the server
Use Command Palette: "Darbot Browser MCP: Start Server"
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 | | ----------------------------- | -------------------- | | ERROR Pixel-based, brittle selectors | AI-friendly accessibility snapshots | | ERROR Requires vision models | Pure structured data approach | | ERROR Complex setup and maintenance | Simple NPM install, ready in seconds | | ERROR Browser-specific code | Universal MCP protocol | | ERROR No session management | Advanced autonomous session states |

Complete Autonomous Toolkit (52 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_start_autonomous_crawl - Start intelligent BFS crawling with memory and reporting
browser_configure_memory - Configure memory system with darbot-memory-mcp integration
Built-in guardrail system for safe autonomous operation
Comprehensive HTML reporting with screenshots and statistics

browser_save_profile - Save complete browser session states with Edge profile context
browser_switch_profile - Restore saved session states
browser_list_profiles - List all saved session states with Edge/workspace context
browser_delete_profile - Delete session states from storage

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 52 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)

Install the VS Code Extension
Extension auto-configures MCP settings
Start the server via Command Palette
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:

Install from marketplace: Search "Darbot Browser MCP" in VS Code extensions
Auto-configuration: Extension prompts to enable MCP and configures the server
Start & Use: Use Command Palette → "Darbot Browser MCP: Start Server"
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)
  --edge-profile <name>         Edge profile name to use (e.g., "Profile 1",
                                "Default"). This is recorded in saved session
                                states.
  --edge-profile-email <email>  Email associated with the Edge profile. This is
                                recorded in saved session states for context.
  --auto-sign-in                Auto sign in with work/school account (Edge
                                profile preference)
  --profile-switching           Enable automatic profile switching based on site
                                (Edge profile preference)
  --intranet-switch             Automatically switch to work profile for
                                intranet sites (Edge profile preference)
  --ie-mode-switch              Automatically switch profile for IE mode sites
                                (Edge profile preference)
  --default-profile <name>      Default Edge profile for external links (Edge
                                profile preference)

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 MCP endpoint:

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

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:

Snapshot Mode (default): Uses accessibility snapshots for better performance and reliability
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: Autonomous page snapshot
- Description: Autonomously capture a detailed accessibility snapshot of the current page for analysis. This provides structured page content better than a screenshot.
- Parameters: None
- Read-only: true

browser_click
- Title: Autonomous click
- Description: Autonomously perform click interactions on web page elements
- 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: Autonomous drag & drop
- Description: Autonomously perform drag and drop operations between web page 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: Autonomous hover
- Description: Autonomously hover over specific elements on the 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
- Read-only: true

browser_type
- Title: Autonomous text input
- Description: Autonomously type text into editable elements on the 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
  - 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: Autonomous dropdown selection
- Description: Autonomously select options in dropdown menus on the 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
  - 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: Autonomous keyboard input
- Description: Autonomously press keys on the keyboard to interact with the web page
- 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: Autonomous wait conditions
- Description: Autonomously wait for specific conditions: text appearance, text disappearance, or time duration
- 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: Autonomous file upload
- Description: Autonomously upload one or multiple files when a file chooser dialog appears
- 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: Autonomous dialog handling
- Description: Autonomously handle browser dialog boxes (alerts, confirmations, prompts)
- 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: Autonomously navigate the browser to any URL. Use this command to launch and direct the browser to websites.
- Parameters:
  - url (string): The URL to navigate to
- Read-only: false

browser_navigate_back
- Title: Go back
- Description: Autonomously navigate back to the previous page in browser history
- Parameters: None
- Read-only: true

browser_navigate_forward
- Title: Go forward
- Description: Autonomously navigate forward to the next page in browser history
- Parameters: None
- Read-only: true

browser_take_screenshot
- Title: Autonomous screenshot capture
- Description: Autonomously take visual screenshots of the current page or specific elements. Use browser_snapshot for structured page data instead of visual screenshots.
- 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: Autonomous PDF generation
- Description: Autonomously save the current web page as a PDF document for archival or sharing
- 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: Autonomous network monitoring
- Description: Autonomously capture and analyze all network requests made since page load for debugging
- Parameters: None
- Read-only: true

browser_console_messages
- Title: Autonomous console monitoring
- Description: Autonomously retrieve all browser console messages for debugging and analysis
- Parameters: None
- Read-only: true

browser_install
- Title: Autonomous browser installation
- Description: Autonomously install the required browser engine specified in configuration. Use this to resolve browser installation errors.
- Parameters: None
- Read-only: false

browser_close
- Title: Autonomous browser closure
- Description: Autonomously close the browser session and terminate all operations
- Parameters: None
- Read-only: true

browser_resize
- Title: Autonomous window resizing
- Description: Autonomously resize the browser window to specific dimensions for optimal viewing
- Parameters:
  - width (number): Width of the browser window
  - height (number): Height of the browser window
- Read-only: true

browser_tab_list
- Title: Autonomous tab listing
- Description: Autonomously list all open browser tabs and their current status
- Parameters: None
- Read-only: true

browser_tab_new
- Title: Autonomous new tab creation
- Description: Autonomously open a new browser tab, optionally navigating to a specified URL
- 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: Autonomous tab selection
- Description: Autonomously select and switch to a specific browser tab by index
- Parameters:
  - index (number): The index of the tab to select
- Read-only: true

browser_tab_close
- Title: Autonomous tab closure
- Description: Autonomously close a browser tab by index, or close the current tab if no index specified
- 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 session state
- Description: Save the current browser session state (cookies, localStorage, URL) for later restoration. Includes Edge profile and VS Code workspace context.
- Parameters:
  - name (string): Name for the session state
  - description (string, optional): Optional description for the session state
- Read-only: false

browser_switch_profile
- Title: Restore session state
- Description: Restore a previously saved session state, including cookies, localStorage, and navigate to the saved URL
- Parameters:
  - name (string): Name of the session state to restore
- Read-only: false

browser_list_profiles
- Title: List session states
- Description: List all saved Darbot session states with their Edge profile context and workspace information
- Parameters: None
- Read-only: true

browser_delete_profile
- Title: Delete session state
- Description: Permanently delete a saved session state from storage
- Parameters:
  - name (string): Name of the session state to delete
- Read-only: false

browser_generate_playwright_test
- Title: Autonomous test generation
- Description: Autonomously generate Playwright test code for browser automation scenarios and user workflows
- 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: Autonomous keyboard input
- Description: Autonomously press keys on the keyboard to interact with the web page
- 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: Autonomous wait conditions
- Description: Autonomously wait for specific conditions: text appearance, text disappearance, or time duration
- 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: Autonomous file upload
- Description: Autonomously upload one or multiple files when a file chooser dialog appears
- 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: Autonomous dialog handling
- Description: Autonomously handle browser dialog boxes (alerts, confirmations, prompts)
- 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

Autonomous Features

For detailed information about the autonomous crawling capabilities, including memory system, BFS planner, guardrails, and reporting, see AUTONOMOUS_FEATURES.md.

Key Autonomous Capabilities:

Intelligent BFS crawling with memory and state tracking
Darbot-memory-mcp integration for persistent memory
HTML report generation with screenshots and statistics
Configurable domain filtering and safety policies

Published

Vulnerabilities

Links

Maintainers

Keywords

Readme

Darbot Browser MCP

Key Features

Requirements

Installation Options

NPM Package

VS Code Extension

NuGet Package (.NET)

Browser Extension

Why Choose Darbot Browser MCP?

Complete Autonomous Toolkit (52 Tools)

Getting Started

VS Code (Automatic Setup)

Manual Configuration (Other Clients)

Quick Install Buttons

Click the button to install:

Or install manually:

Configuration

User profile

Configuration file

Standalone MCP server

Tools

Package Formats

NPM Package

VS Code Extension

NuGet Package (.NET)

Browser Extension

Repository Structure

Autonomous Features