This is an advanced version of the Playwright MCP that provides additional tools for browser automation.
A Model Context Protocol (MCP) server that provides browser automation capabilities using Playwright. This server enables LLMs to interact with web pages through structured accessibility snapshots, bypassing the need for screenshots or visually-tuned models.
Advanced Playwright Tools for MCP
2026-11-17
스타
—
도구
—
가동 시간
—
Key Features
Fast and lightweight. Uses Playwright's accessibility tree, not pixel-based input.
LLM-friendly. No vision models needed, operates purely on structured data.
Deterministic tool application. Avoids ambiguity common with screenshot-based approaches.
🚀 Advanced Features
This advanced version includes additional capabilities not available in the original Playwright MCP:
📸 Enhanced Screenshot Tools
Full page screenshots - Capture entire scrollable page content with fullPage: true
Element screenshots by locator - Screenshot specific elements using Playwright locators (#id, .class, text=Hello)
Multiple element screenshots - Capture multiple elements simultaneously with locator arrays
Vision mode enhancements - All screenshot capabilities available in vision mode
🔍 HTML Content Extraction
browser_get_html_content - Extract HTML content from the entire page or specific elements
browser_get_outer_html - Get complete element HTML including the element tag itself
Batch processing - Extract HTML from multiple elements in parallel
Error handling - Graceful handling of missing elements
📋 Element Snapshot Tools
browser_element_snapshot - Capture accessibility snapshots of specific elements by locator(s)
Structured element data - Get tag names, text content, attributes, and visibility status
Multiple element snapshots - Process multiple elements simultaneously with locator arrays
YAML formatted output - Consistent format matching the main page snapshot tool
💡 Key Improvements
Parallel execution - Multiple operations execute simultaneously for better performance
You can also install the Playwright MCP server using the VS Code CLI:
# For VS Code
code --add-mcp '{"name":"playwright","command":"npx","args":["playwright-mcp-advanced@latest"]}'
After installation, the Playwright MCP server will be available for use with your GitHub Copilot agent in VS Code.
For original Playwright MCP:
Or install manually: Go to Cursor Settings -> MCP -> Add new MCP Server. Name to your liking, use command type with the command npx playwright-mcp-advanced.
Playwright MCP server supports following arguments. They can be provided in the JSON configuration above, as a part of the "args" list:
> npx playwright-mcp-advanced@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: chrome, firefox, webkit, msedge.
--caps <caps> comma-separated list of additional capabilities
to enable, possible values: vision, pdf.
--cdp-endpoint <endpoint> CDP endpoint to connect to.
--config <path> path to the configuration file.
--device <device> device to emulate, for example: "iPhone 15"
--electron enable Electron application support, requires
--cdp-endpoint
--extension run in extension mode, starts CDP relay server
for Chrome extension
--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" or "omit", Defaults to "allow".
--no-sandbox disable the sandbox for all process types that
are normally sandboxed.
--output-dir <path> path to the directory for output files.
--plugins-folder <path> path to the plugins directory. Default is
"./plugins".
--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"
Redirect Handling in CDP Relay
When using the Chrome Extension mode (--extension), the CDP Relay now intelligently handles redirects to ensure that the targetInfo (URL and title) always matches the actual page being displayed. This solves issues where the reported URL might not match the actual page after redirects.
Key features:
Automatic URL Updates: The targetInfo is automatically updated after HTTP redirects, meta refreshes, and JavaScript redirects
Title Synchronization: Page titles are kept in sync with the actual page content
Event-Based Detection: Monitors CDP events to detect navigation and redirect events
Reliable Snapshots: Ensures that snapshots always show the correct URL and title
You can run Playwright 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.
The Playwright MCP server can be configured using a JSON configuration file. You can specify the configuration file
using the --config command line option:
{
// 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. 'chrome')
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;
}
NOTE: The Docker implementation only supports headless chromium at the moment.
import http from "http";
import { createConnection } from "playwright-mcp-advanced";
import { SSEServerTransport } from "@modelcontextprotocol/sdk/server/sse.js";
http.createServer(async (req, res) => {
// ...
// Creates a headless Playwright MCP server with SSE transport
const connection = await createConnection({
browser: { launchOptions: { headless: true } },
});
const transport = new SSEServerTransport("/messages", res);
await connection.sever.connect(transport);
// ...
});
Command Line Utilities
This package includes additional command-line utilities for working with MCP servers:
🔍 mcp-list-tools
A utility for discovering and inspecting available tools, resources, and prompts from any MCP server over HTTP.
# List all capabilities from default server
mcp-list-tools
# Connect to custom server
mcp-list-tools http://localhost:8080/mcp
# Get JSON output for scripting
mcp-list-tools --format=json
# Show only tools with detailed schemas
mcp-list-tools --tools-only --detailed
# Show only resources or prompts
mcp-list-tools --resources-only
mcp-list-tools --prompts-only
Key Features:
🔍 Discovery: List all available tools, resources, and prompts
📋 Detailed Info: Show input schemas and parameter details with --detailed
🎯 Selective Output: Filter to show only tools, resources, or prompts
💻 JSON Support: Machine-readable output for automation and scripting
🔤 Icon Legend: Visual indicators for read-only (🔒) and destructive (⚠️) tools
⚡ Fast: Quick inspection without full MCP client setup
The Chrome Extension mode allows you to connect the MCP server to existing Chrome tabs through a Chrome extension. This feature has been thoroughly tested and verified working with complete CDP (Chrome DevTools Protocol) integration.
Verified capabilities:
✅ Real-time browser control through Chrome extension
✅ Navigation and page interaction (browser_navigate, browser_click)
Click "Load unpacked" and select the extension/ folder from this repository
The "Playwright MCP Bridge" extension should now be installed
3. Connect a Chrome tab
Open the Chrome tab you want to control
Click the Playwright MCP Bridge extension icon
The extension will show the bridge URL (default: ws://localhost:9223/extension)
Click "Share This Tab" to connect the tab to the MCP server
4. Use MCP tools with the connected tab
Once connected, you can use all MCP tools like browser_navigate, browser_click, browser_screenshot, etc., and they will operate on the connected Chrome tab.
Extension Features
Real-time connection status - See which tab is currently shared
Easy tab switching - Switch between shared tabs directly from the extension
browser_screen_capture - Enhanced screenshot capture with locator support
browser_screen_click - Click at X,Y coordinates
browser_screen_drag - Drag between coordinates
browser_screen_move_mouse - Move mouse to coordinates
browser_screen_type - Type text in vision mode
Note: All HTML extraction tools (browser_get_html_content, browser_get_outer_html) work in both modes. Most interaction tools like browser_press_key, browser_wait_for, browser_file_upload, and browser_handle_dialog are shared between modes.
browser_snapshot
Title: Page snapshot
Description: Capture accessibility snapshot of the current page, this is better than screenshot
Parameters: None
Read-only: true
browser_element_snapshot 🆕
Title: Element snapshot
Description: Capture accessibility snapshot of specific elements by locator(s). Better than screenshot for specific elements.
Enhancement: Capture structured accessibility data for specific elements using locators
Parameters:
locator (string, optional): Playwright locator string to capture accessibility snapshot of a specific element (e.g., "#id", ".class", "text=Hello"). Cannot be combined with locators parameter.
locators (array, optional): Array of Playwright locator strings to capture accessibility snapshots of multiple elements. Cannot be combined with locator parameter.
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 double click instead of 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_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_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_screen_capture ⭐
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.
Enhancement: Enhanced with fullPage and locator support for flexible screenshot capture
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.
fullPage (boolean, optional): Whether to take a screenshot of the full scrollable page. Cannot be combined with element/ref/locator parameters.
locator (string, optional): Playwright locator string to screenshot a specific element (e.g., "#id", ".class", "text=Hello"). Cannot be combined with element/ref/fullPage parameters.
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_get_html_content 🆕
Title: Get HTML content
Description: Get HTML content of the current page or specific elements. Returns full page HTML by default, or HTML of specific elements when locator(s) provided.
Enhancement: Extract HTML content from page or specific elements with flexible locator support
Parameters:
locator (string, optional): Playwright locator string to get HTML content of a specific element (e.g., "#id", ".class", "text=Hello"). Cannot be combined with locators parameter.
locators (array, optional): Array of Playwright locator strings to get HTML content of multiple elements. Cannot be combined with locator parameter.
Read-only: true
browser_get_outer_html 🆕
Title: Get outer HTML content
Description: Get outer HTML content of specific elements (includes the element tag itself). Requires locator(s) to be specified.
Enhancement: Get complete element HTML including the element tag itself
Parameters:
locator (string, optional): Playwright locator string to get outer HTML content of a specific element (e.g., "#id", ".class", "text=Hello"). Cannot be combined with locators parameter.
locators (array, optional): Array of Playwright locator strings to get outer HTML content of multiple elements. Cannot be combined with locator parameter.
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_screen_capture ⭐
Title: Take a screenshot
Description: Take a screenshot of the current page
Enhancement: Enhanced with fullPage and locator/locators support for flexible vision mode capture
Parameters:
fullPage (boolean, optional): Whether to take a screenshot of the full scrollable page. Cannot be combined with locator/locators parameters.
locator (string, optional): Playwright locator string to screenshot a specific element (e.g., "#id", ".class", "text=Hello"). Cannot be combined with fullPage/locators parameters.
locators (array, optional): Array of Playwright locator strings to screenshot multiple elements. Cannot be combined with fullPage/locator parameters.
Read-only: true
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: true
browser_mouse_click_xy
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_mouse_drag_xy
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_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_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_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_get_html_content 🆕
Title: Get HTML content
Description: Get HTML content of the current page or specific elements. Returns full page HTML by default, or HTML of specific elements when locator(s) provided.
Enhancement: Extract HTML content from page or specific elements with flexible locator support
Parameters:
locator (string, optional): Playwright locator string to get HTML content of a specific element (e.g., "#id", ".class", "text=Hello"). Cannot be combined with locators parameter.
locators (array, optional): Array of Playwright locator strings to get HTML content of multiple elements. Cannot be combined with locator parameter.
Read-only: true
browser_get_outer_html 🆕
Title: Get outer HTML content
Description: Get outer HTML content of specific elements (includes the element tag itself). Requires locator(s) to be specified.
Enhancement: Get complete element HTML including the element tag itself
Parameters:
locator (string, optional): Playwright locator string to get outer HTML content of a specific element (e.g., "#id", ".class", "text=Hello"). Cannot be combined with locators parameter.
locators (array, optional): Array of Playwright locator strings to get outer HTML content of multiple elements. Cannot be combined with locator parameter.
Read-only: true
License
This project is licensed under the same terms as the original Playwright MCP.