moltbrowser

The Problem

Every time an agent opens a browser, it starts from zero. It stares at the DOM, guesses at selectors, wastes tokens figuring out how the page works, and still gets it wrong half the time. This happens on every site, for every agent, every single run. Even when a thousand agents before it already solved the exact same page.

MoltBrowser fixes that. When an agent lands on x.com it gets post-tweet, like-post, follow-user as ready-to-call tools. When it lands on GitHub it gets search-repos, open-pr. Contributed by the community, tested on real pages. No guessing. No wasted tokens.

Two Interfaces, One Ecosystem

MoltBrowser comes in two flavors — pick whichever fits your workflow:

Both share the same WebMCP Hub — tools contributed via CLI are available in MCP and vice versa.

CLI (for coding agents)

The CLI wraps Playwright CLI with automatic hub tool discovery. Token-efficient, one command per action, with skill files for coding agents.

Getting Started

npm install -g moltbrowser-cli
npm install -g @playwright/cli@latest

# Login (one-time — uses your GitHub account)
moltbrowser login --github

# Or paste an API key from https://webmcp-hub.com
moltbrowser login

Quick Demo

moltbrowser open https://x.com/home --headed
# Hub tools are discovered automatically:
# - fill-post-text (text)
# - click-post-button
# - click-reply-button (text)
# - like-post (text)
# - ...

moltbrowser hub-execute fill-post-text --text="Hello from MoltBrowser!"
moltbrowser hub-execute click-post-button
moltbrowser snapshot
moltbrowser close

How It Works

$ moltbrowser goto https://x.com/home

### Hub Tools (7 available)
- fill-post-text (text): Fill the post text area
- click-post-button: Click the Post button
- click-reply-button (text): Reply to a specific post
- like-post (text): Like a specific post
- ...

$ moltbrowser hub-execute like-post --text="Hello from MoltBrowser!"
[action completed successfully]

1. Navigate with open or goto — hub tools are discovered automatically
2. Use hub-execute <tool> for pre-configured, community-tested actions
3. Fall back to standard Playwright commands (click, fill, snapshot, etc.) when needed
4. Contribute tools back so the next agent benefits

Commands

# Auth
moltbrowser login --github       # Login via GitHub (best for agents)
moltbrowser login                # Interactive login
moltbrowser whoami               # Show auth status

# Navigation (with hub discovery)
moltbrowser open [url]           # Open browser + discover hub tools
moltbrowser goto <url>           # Navigate + discover hub tools

# Hub tools
moltbrowser hub-list             # List discovered tools for current page
moltbrowser hub-execute <tool>   # Execute a hub tool
moltbrowser hub-info <tool>      # Show tool details

# Contribute
moltbrowser contribute-create    # Create a new hub config
moltbrowser contribute-add-tool  # Add a tool to a config
moltbrowser contribute-vote      # Vote on a tool

# All Playwright CLI commands pass through
moltbrowser click <ref>          moltbrowser type <text>
moltbrowser fill <ref> <text>    moltbrowser press <key>
moltbrowser snapshot             moltbrowser screenshot
moltbrowser close                moltbrowser tab-list
# ... and many more

Skills for Coding Agents

Install skill files so coding agents (Claude Code, Copilot) know how to use MoltBrowser:

moltbrowser install --skills

See the full CLI documentation.

MCP Server (for MCP-native agents)

The MCP server wraps Playwright browser automation with WebMCP Hub integration. It acts as a proxy — intercepting navigation to discover and inject per-site hub tools dynamically.

Getting Started

Get started at webmcp-hub.com - create an account, grab your API key, and add this to your MCP client settings:

{
  "mcpServers": {
    "moltbrowser-mcp": {
      "command": "npx",
      "args": ["moltbrowser-mcp-server"],
      "env": {
        "HUB_API_KEY": "whub_your_api_key"
      }
    }
  }
}

How It Works

Agent (Claude, Cursor, etc.)
  |
  |  MCP protocol (stdio)
  v
moltbrowser-mcp (hub proxy)
  |-- On navigate: queries WebMCP Hub REST API
  |-- Dynamically adds hub tools to tool list
  |-- Hub tool calls -> translates to Playwright code -> browser_run_code
  |
  |  MCP protocol (stdio, child process)
  v
Playwright browser automation
  |
  v
Browser (Chrome, Firefox, WebKit)

1. Agent navigates to a page via browser_navigate
2. Proxy queries webmcp-hub.com for configs matching the domain/URL
3. If configs exist, hub tools appear in the navigation response (e.g. hub_search-repos, hub_get-results)
4. Agent calls a hub tool. The proxy translates execution metadata into Playwright code and runs it
5. If no config exists, all standard Playwright tools work as usual

Hub Tools

These tools are always available when hub integration is enabled:

• browser_click
  • Title: Click
  • Description: Perform click on a web page
  • Parameters:
    • element (string, optional): 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
    • button (string, optional): Button to click, defaults to left
    • modifiers (array, optional): Modifier keys to press
  • Read-only: false

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

• browser_console_messages
  • Title: Get console messages
  • Description: Returns all console messages
  • Parameters:
    • level (string): Level of the console messages to return. Each level includes the messages of more severe levels. Defaults to "info".
    • filename (string, optional): Filename to save the console messages to. If not provided, messages are returned as text.
  • Read-only: true

• 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_evaluate
  • Title: Evaluate JavaScript
  • Description: Evaluate JavaScript expression on page or element
  • Parameters:
    • function (string): () => { /* code / } or (element) => { / code */ } when element is provided
    • element (string, optional): Human-readable element description used to obtain permission to interact with the element
    • ref (string, optional): Exact target element reference from the page snapshot
    • filename (string, optional): Filename to save the result to. If not provided, result is returned as JSON string.
  • Read-only: false

• browser_file_upload
  • Title: Upload files
  • Description: Upload one or multiple files
  • Parameters:
    • paths (array, optional): The absolute paths to the files to upload. Can be single file or multiple files. If omitted, file chooser is cancelled.
  • Read-only: false

• browser_fill_form
  • Title: Fill form
  • Description: Fill multiple form fields
  • Parameters:
    • fields (array): Fields to fill in
  • 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_hover
  • Title: Hover mouse
  • Description: Hover over element on page
  • Parameters:
    • element (string, optional): 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: 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: false

• browser_network_requests
  • Title: List network requests
  • Description: Returns all network requests since loading the page
  • Parameters:
    • includeStatic (boolean): Whether to include successful static resources like images, fonts, scripts, etc. Defaults to false.
    • filename (string, optional): Filename to save the network requests to. If not provided, requests are returned as text.
  • Read-only: true

• 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_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: false

• browser_run_code
  • Title: Run Playwright code
  • Description: Run Playwright code snippet
  • Parameters:
    • code (string): A JavaScript function containing Playwright code to execute. It will be invoked with a single argument, page, which you can use for any page interaction. For example: async (page) => { await page.getByRole('button', { name: 'Submit' }).click(); return await page.title(); }
    • filename (string, optional): Filename to save the result to. If not provided, result is returned as JSON string.
  • Read-only: false

• browser_select_option
  • Title: Select option
  • Description: Select an option in a dropdown
  • Parameters:
    • element (string, optional): 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_snapshot
  • Title: Page snapshot
  • Description: Capture accessibility snapshot of the current page, this is better than screenshot
  • Parameters:
    • filename (string, optional): Save snapshot to markdown file instead of returning it in the response.
  • 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:
    • type (string): Image format for the screenshot. Default is png.
    • filename (string, optional): File name to save the screenshot to. Defaults to page-{timestamp}.{png|jpeg} if not specified. Prefer relative file names to stay within the output directory.
    • 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.
    • fullPage (boolean, optional): When true, takes a screenshot of the full scrollable page, instead of the currently visible viewport. Cannot be used with element screenshots.
  • Read-only: true

• browser_type
  • Title: Type text
  • Description: Type text into editable element
  • Parameters:
    • element (string, optional): 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_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: false

• browser_tabs
  • Title: Manage tabs
  • Description: List, create, close, or select a browser tab.
  • Parameters:
    • action (string): Operation to perform
    • index (number, optional): Tab index, used for close/select. If omitted for close, current tab is closed.
  • Read-only: false

• 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_mouse_click_xy
  • Title: Click
  • Description: Click left mouse button at 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: false

• browser_mouse_drag_xy
  • Title: Drag mouse
  • Description: Drag left mouse button to a given position
  • 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_mouse_move_xy
  • 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: false

• 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. Prefer relative file names to stay within the output directory.
  • Read-only: true

• browser_generate_locator
  • Title: Create locator for element
  • Description: Generate locator for the given element to use in tests
  • Parameters:
    • element (string, optional): 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_verify_element_visible
  • Title: Verify element visible
  • Description: Verify element is visible on the page
  • Parameters:
    • role (string): ROLE of the element. Can be found in the snapshot like this: - {ROLE} "Accessible Name":
    • accessibleName (string): ACCESSIBLE_NAME of the element. Can be found in the snapshot like this: - role "{ACCESSIBLE_NAME}"
  • Read-only: false

• browser_verify_list_visible
  • Title: Verify list visible
  • Description: Verify list is visible on the page
  • Parameters:
    • element (string): Human-readable list description
    • ref (string): Exact target element reference that points to the list
    • items (array): Items to verify
  • Read-only: false

• browser_verify_text_visible
  • Title: Verify text visible
  • Description: Verify text is visible on the page. Prefer browser_verify_element_visible if possible.
  • Parameters:
    • text (string): TEXT to verify. Can be found in the snapshot like this: - role "Accessible Name": {TEXT} or like this: - text: {TEXT}
  • Read-only: false

• browser_verify_value
  • Title: Verify value
  • Description: Verify element value
  • Parameters:
    • type (string): Type of the element
    • element (string): Human-readable element description
    • ref (string): Exact target element reference that points to the element
    • value (string): Value to verify. For checkbox, use "true" or "false".
  • Read-only: false

• browser_start_tracing
  • Title: Start tracing
  • Description: Start trace recording
  • Parameters: None
  • Read-only: true

• browser_stop_tracing
  • Title: Stop tracing
  • Description: Stop trace recording
  • Parameters: None
  • Read-only: true

{
  /**
   * The browser to use.
   */
  browser?: {
    /**
     * The type of browser to use.
     */
    browserName?: 'chromium' | 'firefox' | 'webkit';

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

    /**
     * Path to a user data directory for browser profile persistence.
     * Temporary directory is created by default.
     */
    userDataDir?: string;

    /**
     * Launch options passed to
     * @see https://playwright.dev/docs/api/class-browsertype#browser-type-launch-persistent-context
     *
     * This is useful for settings options like `channel`, `headless`, `executablePath`, etc.
     */
    launchOptions?: playwright.LaunchOptions;

    /**
     * Context options for the browser context.
     *
     * This is useful for settings options like `viewport`.
     */
    contextOptions?: playwright.BrowserContextOptions;

    /**
     * Chrome DevTools Protocol endpoint to connect to an existing browser instance in case of Chromium family browsers.
     */
    cdpEndpoint?: string;

    /**
     * CDP headers to send with the connect request.
     */
    cdpHeaders?: Record<string, string>;

    /**
     * Timeout in milliseconds for connecting to CDP endpoint. Defaults to 30000 (30 seconds). Pass 0 to disable timeout.
     */
    cdpTimeout?: number;

    /**
     * Remote endpoint to connect to an existing Playwright server.
     */
    remoteEndpoint?: string;

    /**
     * Paths to TypeScript files to add as initialization scripts for Playwright page.
     */
    initPage?: string[];

    /**
     * Paths to JavaScript files to add as initialization scripts.
     * The scripts will be evaluated in every page before any of the page's scripts.
     */
    initScript?: string[];
  },

  /**
   * Connect to a running browser instance (Edge/Chrome only). If specified, `browser`
   * config is ignored.
   * Requires the "Playwright MCP Bridge" browser extension to be installed.
   */
  extension?: boolean;

  server?: {
    /**
     * The port to listen on for SSE or MCP transport.
     */
    port?: number;

    /**
     * The host to bind the server to. Default is localhost. Use 0.0.0.0 to bind to all interfaces.
     */
    host?: string;

    /**
     * The hosts this server is allowed to serve from. Defaults to the host server is bound to.
     * This is not for CORS, but rather for the DNS rebinding protection.
     */
    allowedHosts?: string[];
  },

  /**
   * List of enabled tool capabilities. Possible values:
   *   - 'core': Core browser automation features.
   *   - 'pdf': PDF generation and manipulation.
   *   - 'vision': Coordinate-based interactions.
   *   - 'devtools': Developer tools features.
   */
  capabilities?: ToolCapability[];

  /**
   * Whether to save the Playwright session into the output directory.
   */
  saveSession?: boolean;

  /**
   * Whether to save the Playwright trace of the session into the output directory.
   */
  saveTrace?: boolean;

  /**
   * If specified, saves the Playwright video of the session into the output directory.
   */
  saveVideo?: {
    width: number;
    height: number;
  };

  /**
   * Reuse the same browser context between all connected HTTP clients.
   */
  sharedBrowserContext?: boolean;

  /**
   * Secrets are used to prevent LLM from getting sensitive data while
   * automating scenarios such as authentication.
   * Prefer the browser.contextOptions.storageState over secrets file as a more secure alternative.
   */
  secrets?: Record<string, string>;

  /**
   * The directory to save output files.
   */
  outputDir?: string;

  /**
   * Whether to save snapshots, console messages, network logs and other session logs to a file or to the standard output. Defaults to "stdout".
   */
  outputMode?: 'file' | 'stdout';

  console?: {
    /**
     * The level of console messages to return. Each level includes the messages of more severe levels. Defaults to "info".
     */
    level?: 'error' | 'warning' | 'info' | 'debug';
  },

  network?: {
    /**
     * List of origins to allow the browser to request. Default is to allow all. Origins matching both `allowedOrigins` and `blockedOrigins` will be blocked.
     *
     * Supported formats:
     * - Full origin: `https://example.com:8080` - matches only that origin
     * - Wildcard port: `http://localhost:*` - matches any port on localhost with http protocol
     */
    allowedOrigins?: string[];

    /**
     * List of origins to block the browser to request. Origins matching both `allowedOrigins` and `blockedOrigins` will be blocked.
     *
     * Supported formats:
     * - Full origin: `https://example.com:8080` - matches only that origin
     * - Wildcard port: `http://localhost:*` - matches any port on localhost with http protocol
     */
    blockedOrigins?: string[];
  };

  /**
   * Specify the attribute to use for test ids, defaults to "data-testid".
   */
  testIdAttribute?: string;

  timeouts?: {
    /*
     * Configures default action timeout: https://playwright.dev/docs/api/class-page#page-set-default-timeout. Defaults to 5000ms.
     */
    action?: number;

    /*
     * Configures default navigation timeout: https://playwright.dev/docs/api/class-page#page-set-default-navigation-timeout. Defaults to 60000ms.
     */
    navigation?: number;
  };

  /**
   * 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.
   */
  imageResponses?: 'allow' | 'omit';

  snapshot?: {
    /**
     * When taking snapshots for responses, specifies the mode to use.
     */
    mode?: 'incremental' | 'full' | 'none';
  };

  /**
   * Whether to allow file uploads from anywhere on the file system.
   * By default (false), file uploads are restricted to paths within the MCP roots only.
   */
  allowUnrestrictedFileAccess?: boolean;

  /**
   * Specify the language to use for code generation.
   */
  codegen?: 'typescript' | 'none';
}

Contributing Tools to the Hub

Both CLI and MCP users can contribute tools. When you automate a site manually, contribute the selectors and actions so the next agent gets them for free.

# CLI
moltbrowser contribute-create --domain=example.com --url-pattern="example.com/search" --title="Example Search"
moltbrowser contribute-add-tool --config-id=<id> --name=search-items --description="Search" ...
moltbrowser contribute-vote --config-id=<id> --name=search-items --vote=up

Tools are community-maintained. Bad tools get downvoted, good tools rise. The ecosystem self-corrects.

License

Apache-2.0