@playwright/mcp 0.0.13 → 0.0.14

package/README.md

@@ -17,6 +17,8 @@ A Model Context Protocol (MCP) server that provides browser automation capabilit
 
 ### Example config
 
+#### NPX
+
 ```js
 {
   "mcpServers": {
@@ -30,7 +32,6 @@ A Model Context Protocol (MCP) server that provides browser automation capabilit
 }
 ```
 
-
 #### Installation in VS Code
 
 Install the Playwright MCP server in VS Code using one of these buttons:
@@ -128,6 +129,20 @@ And then in MCP client config, set the `url` to the SSE endpoint:
 }
 ```
 
+### Docker
+
+**NOTE:** The Docker implementation only supports headless chromium at the moment.
+```js
+{
+  "mcpServers": {
+    "playwright": {
+      "command": "docker",
+      "args": ["run", "-i", "--rm", "--init", "mcp/playwright"]
+    }
+  }
+}
+```
+
 ### Tool Modes
 
 The tools are available in two modes:
@@ -154,42 +169,72 @@ To use Vision Mode, add the `--vision` flag when starting the server:
 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.
 
+### Build with Docker
+
+You can build the Docker image yourself.
+```
+docker build -t mcp/playwright .
+```
+
 ### Programmatic usage with custom transports
 
 ```js
+import http from 'http';
+
 import { createServer } from '@playwright/mcp';
+import { SSEServerTransport } from '@modelcontextprotocol/sdk/server/sse.js';
+
+http.createServer(async (req, res) => {
+  // ...
 
-// ...
+  // Creates a headless Playwright MCP server with SSE transport
+  const mcpServer = await createServer({ headless: true });
+  const transport = new SSEServerTransport('/messages', res);
+  await mcpServer.connect(transport);
 
-const server = createServer({
-  launchOptions: { headless: true }
+  // ...
 });
-transport = new SSEServerTransport("/messages", res);
-server.connect(transport);
+
 ```
 
+<!--- Generated by update-readme.js -->
+
 ### Snapshot-based Interactions
 
+<!-- NOTE: This has been generated via update-readme.js -->
+
+- **browser_snapshot**
+  - Description: Capture accessibility snapshot of the current page, this is better than screenshot
+  - Parameters: None
+
+<!-- NOTE: This has been generated via update-readme.js -->
+
 - **browser_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
 
-- **browser_hover**
-  - 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
+<!-- NOTE: This has been generated via update-readme.js -->
 
 - **browser_drag**
   - Description: Perform drag and drop between two elements
   - Parameters:
-    - `startElement` (string): Human-readable source element description used to obtain permission to interact with the element
+    - `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 permission to interact with the element
+    - `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
 
+<!-- NOTE: This has been generated via update-readme.js -->
+
+- **browser_hover**
+  - 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
+
+<!-- NOTE: This has been generated via update-readme.js -->
+
 - **browser_type**
   - Description: Type text into editable element
   - Parameters:
@@ -199,6 +244,8 @@ server.connect(transport);
     - `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.
 
+<!-- NOTE: This has been generated via update-readme.js -->
+
 - **browser_select_option**
   - Description: Select an option in a dropdown
   - Parameters:
@@ -206,17 +253,25 @@ server.connect(transport);
     - `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.
 
-- **browser_snapshot**
-  - Description: Capture accessibility snapshot of the current page, this is better than screenshot
-  - Parameters: None
+<!-- NOTE: This has been generated via update-readme.js -->
 
 - **browser_take_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.
+    - `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.
 
 ### Vision-based Interactions
 
+<!-- NOTE: This has been generated via update-readme.js -->
+
+- **browser_screen_capture**
+  - Description: Take a screenshot of the current page
+  - Parameters: None
+
+<!-- NOTE: This has been generated via update-readme.js -->
+
 - **browser_screen_move_mouse**
   - Description: Move mouse to a given position
   - Parameters:
@@ -224,9 +279,7 @@ server.connect(transport);
     - `x` (number): X coordinate
     - `y` (number): Y coordinate
 
-- **browser_screen_capture**
-  - Description: Take a screenshot of the current page
-  - Parameters: None
+<!-- NOTE: This has been generated via update-readme.js -->
 
 - **browser_screen_click**
   - Description: Click left mouse button
@@ -235,6 +288,8 @@ server.connect(transport);
     - `x` (number): X coordinate
     - `y` (number): Y coordinate
 
+<!-- NOTE: This has been generated via update-readme.js -->
+
 - **browser_screen_drag**
   - Description: Drag left mouse button
   - Parameters:
@@ -244,33 +299,38 @@ server.connect(transport);
     - `endX` (number): End X coordinate
     - `endY` (number): End Y coordinate
 
+<!-- NOTE: This has been generated via update-readme.js -->
+
 - **browser_screen_type**
   - Description: Type text
   - Parameters:
-    - `text` (string): Text to type
+    - `text` (string): Text to type into the element
     - `submit` (boolean, optional): Whether to submit entered text (press Enter after)
 
-- **browser_press_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`
-
 ### Tab Management
 
+<!-- NOTE: This has been generated via update-readme.js -->
+
 - **browser_tab_list**
   - Description: List browser tabs
   - Parameters: None
 
+<!-- NOTE: This has been generated via update-readme.js -->
+
 - **browser_tab_new**
   - 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.
 
+<!-- NOTE: This has been generated via update-readme.js -->
+
 - **browser_tab_select**
   - Description: Select a tab by index
   - Parameters:
     - `index` (number): The index of the tab to select
 
+<!-- NOTE: This has been generated via update-readme.js -->
+
 - **browser_tab_close**
   - Description: Close a tab
   - Parameters:
@@ -278,48 +338,92 @@ server.connect(transport);
 
 ### Navigation
 
+<!-- NOTE: This has been generated via update-readme.js -->
+
 - **browser_navigate**
   - Description: Navigate to a URL
   - Parameters:
     - `url` (string): The URL to navigate to
 
+<!-- NOTE: This has been generated via update-readme.js -->
+
 - **browser_navigate_back**
   - Description: Go back to the previous page
   - Parameters: None
 
+<!-- NOTE: This has been generated via update-readme.js -->
+
 - **browser_navigate_forward**
   - Description: Go forward to the next page
   - Parameters: None
 
 ### Keyboard
 
+<!-- NOTE: This has been generated via update-readme.js -->
+
 - **browser_press_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`
 
+### Console
+
+<!-- NOTE: This has been generated via update-readme.js -->
+
+- **browser_console_messages**
+  - Description: Returns all console messages
+  - Parameters: None
+
 ### Files and Media
 
+<!-- NOTE: This has been generated via update-readme.js -->
+
 - **browser_file_upload**
-  - Description: Choose one or multiple files to upload
+  - 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.
 
+<!-- NOTE: This has been generated via update-readme.js -->
+
 - **browser_pdf_save**
   - Description: Save page as PDF
   - Parameters: None
 
 ### Utilities
 
-- **browser_wait**
-  - Description: Wait for a specified time in seconds
-  - Parameters:
-    - `time` (number): The time to wait in seconds (capped at 10 seconds)
+<!-- NOTE: This has been generated via update-readme.js -->
 
 - **browser_close**
   - Description: Close the page
   - Parameters: None
 
+<!-- NOTE: This has been generated via update-readme.js -->
+
+- **browser_wait**
+  - Description: Wait for a specified time in seconds
+  - Parameters:
+    - `time` (number): The time to wait in seconds
+
+<!-- NOTE: This has been generated via update-readme.js -->
+
+- **browser_resize**
+  - Description: Resize the browser window
+  - Parameters:
+    - `width` (number): Width of the browser window
+    - `height` (number): Height of the browser window
+
+<!-- NOTE: This has been generated via update-readme.js -->
+
 - **browser_install**
   - Description: Install the browser specified in the config. Call this if you get an error about the browser not being installed.
   - Parameters: None
+
+<!-- NOTE: This has been generated via update-readme.js -->
+
+- **browser_handle_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.
+
+<!--- End of generated section -->

package/index.d.ts

@@ -15,33 +15,46 @@
  * limitations under the License.
  */
 
-import type { LaunchOptions } from 'playwright';
 import type { Server } from '@modelcontextprotocol/sdk/server/index.js';
 
 type ToolCapability = 'core' | 'tabs' | 'pdf' | 'history' | 'wait' | 'files' | 'install';
 
 type Options = {
-  /**
-   * Path to the user data directory.
-   */
-  userDataDir?: string;
-
-  /**
-   * Launch options for the browser.
-   */
-  launchOptions?: LaunchOptions;
-
-  /**
-   * Use screenshots instead of snapshots. Less accurate, reliable and overall
-   * slower, but contains visual representation of the page.
-   * @default false
-   */
-  vision?: boolean;
-
-  /**
-   * Capabilities to enable.
-   */
-  capabilities?: ToolCapability[];
+    /**
+     * The browser to use (e.g., 'chrome', 'chromium', 'firefox', 'webkit', 'msedge').
+     */
+    browser?: string;
+    /**
+     * Path to a user data directory for browser profile persistence.
+     */
+    userDataDir?: string;
+    /**
+     * Whether to run the browser in headless mode (default: true).
+     */
+    headless?: boolean;
+    /**
+     * Path to a custom browser executable.
+     */
+    executablePath?: string;
+    /**
+     * Chrome DevTools Protocol endpoint to connect to an existing browser instance.
+     */
+    cdpEndpoint?: string;
+    /**
+     * Enable vision capabilities (e.g., visual automation or OCR).
+     */
+    vision?: boolean;
+    /**
+     * List of enabled tool capabilities. Possible values:
+     *   - 'core': Core browser automation features.
+     *   - 'tabs': Tab management features.
+     *   - 'pdf': PDF generation and manipulation.
+     *   - 'history': Browser history access.
+     *   - 'wait': Wait and timing utilities.
+     *   - 'files': File upload/download support.
+     *   - 'install': Browser installation utilities.
+     */
+    capabilities?: ToolCapability[];
 };
-
-export function createServer(options?: Options): Server;
+export declare function createServer(options?: Options): Promise<Server>;
+export {};