Skip to main content
Glama

Playwright MCP

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.

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.

Use Cases

  • Web navigation and form-filling

  • Data extraction from structured content

  • Automated testing driven by LLMs

  • General-purpose browser interaction for agents

Example config

{
  "mcpServers": {
    "playwright": {
      "command": "npx",
      "args": [
        "@playwright/mcp@latest"
      ]
    }
  }
}

Installation in VS Code

Install the Playwright MCP server in VS Code using one of these buttons:

Alternatively, you can install the Playwright MCP server using the VS Code CLI:

# For VS Code
code --add-mcp '{"name":"playwright","command":"npx","args":["@playwright/mcp@latest"]}'
# For VS Code Insiders
code-insiders --add-mcp '{"name":"playwright","command":"npx","args":["@playwright/mcp@latest"]}'

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

CLI Options

The Playwright MCP server supports the following command-line options:

  • --browser <browser>: Browser or chrome channel to use. Possible values:

    • chrome, firefox, webkit, msedge

    • Chrome channels: chrome-beta, chrome-canary, chrome-dev

    • Edge channels: msedge-beta, msedge-canary, msedge-dev

    • Default: chrome

  • --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

  • --executable-path <path>: Path to the browser executable

  • --headless: Run browser in headless mode (headed by default)

  • --port <port>: Port to listen on for SSE transport

  • --user-data-dir <path>: Path to the user data directory

  • --vision: Run server that uses screenshots (Aria snapshots are used by default)

User data directory

Playwright MCP will launch the browser with the new profile, located at

- `%USERPROFILE%\AppData\Local\ms-playwright\mcp-chrome-profile` on Windows
- `~/Library/Caches/ms-playwright/mcp-chrome-profile` on macOS
- `~/.cache/ms-playwright/mcp-chrome-profile` on Linux

All the logged in information will be stored in that profile, you can delete it between sessions if you'd like to clear the offline state.

Running headless browser (Browser without GUI).

This mode is useful for background or batch operations.

{
  "mcpServers": {
    "playwright": {
      "command": "npx",
      "args": [
        "@playwright/mcp@latest",
        "--headless"
      ]
    }
  }
}

Running headed browser on Linux w/o DISPLAY

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 @playwright/mcp@latest --port 8931

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

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

Tool Modes

The tools are available in two modes:

  1. Snapshot Mode (default): Uses accessibility snapshots for better performance and reliability

  2. Vision Mode: Uses screenshots for visual-based interactions

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

{
  "mcpServers": {
    "playwright": {
      "command": "npx",
      "args": [
        "@playwright/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.

Programmatic usage with custom transports

import { createServer } from '@playwright/mcp';

// ...

const server = createServer({
  launchOptions: { headless: true }
});
transport = new SSEServerTransport("/messages", res);
server.connect(transport);

Snapshot-based Interactions

  • 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

  • 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

      • 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

      • endRef (string): Exact target element reference from the page snapshot

  • browser_type

    • 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.

  • browser_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.

  • browser_snapshot

    • Description: Capture accessibility snapshot of the current page, this is better than screenshot

    • Parameters: None

  • 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.

Vision-based Interactions

  • browser_screen_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

  • browser_screen_capture

    • Description: Take a screenshot of the current page

    • Parameters: None

  • browser_screen_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

  • browser_screen_drag

    • 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

  • browser_screen_type

    • Description: Type text

    • Parameters:

      • text (string): Text to type

      • 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

  • browser_tab_list

    • Description: List browser tabs

    • Parameters: None

  • 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.

  • browser_tab_select

    • Description: Select a tab by index

    • Parameters:

      • index (number): The index of the tab to select

  • browser_tab_close

    • Description: Close a tab

    • Parameters:

      • index (number, optional): The index of the tab to close. Closes current tab if not provided.

Navigation

  • browser_navigate

    • Description: Navigate to a URL

    • Parameters:

      • url (string): The URL to navigate to

  • browser_navigate_back

    • Description: Go back to the previous page

    • Parameters: None

  • browser_navigate_forward

    • Description: Go forward to the next page

    • Parameters: None

Keyboard

  • 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

  • browser_console_messages

    • Description: Returns all console messages

    • Parameters: None

Files and Media

  • browser_file_upload

    • Description: Choose one or multiple files to upload

    • Parameters:

      • paths (array): The absolute paths to the files to upload. Can be a single file or multiple files.

  • 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)

  • browser_close

    • Description: Close the page

    • Parameters: None

  • 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

Available Tools

22 tools
browser_clickB
Destructive

Perform click on a web page

Inputs: element (required), ref (required), doubleClick, button, +1 more.

browser_closeA
Destructive

Close the page

Inputs: no named parameters.

browser_console_messagesB
Read-only

Returns all console messages

Inputs: level.

browser_dragB
Destructive

Perform drag and drop between two elements

Inputs: startElement (required), startRef (required), endElement (required), endRef (required).

browser_evaluateA
Destructive

Evaluate JavaScript expression on page or element

Inputs: function (required), element, ref.

browser_file_uploadB
Destructive

Upload one or multiple files

Inputs: paths.

browser_fill_formB
Destructive

Fill multiple form fields

Inputs: fields (required).

browser_handle_dialogC
Destructive

Handle a dialog

Inputs: accept (required), promptText.

browser_hoverB
Destructive

Hover over element on page

Inputs: element (required), ref (required).

browser_installA
Destructive

Install the browser specified in the config. Call this if you get an error about the browser not being installed.

Inputs: no named parameters.

browser_navigateB
Destructive

Navigate to a URL

Inputs: url (required).

browser_navigate_backA
Destructive

Go back to the previous page

Inputs: no named parameters.

browser_network_requestsB
Read-only

Returns all network requests since loading the page

Inputs: includeStatic.

browser_press_keyB
Destructive

Press a key on the keyboard

Inputs: key (required).

browser_resizeA
Destructive

Resize the browser window

Inputs: width (required), height (required).

browser_run_codeA
Destructive

Run Playwright code snippet

Inputs: code (required).

browser_select_optionB
Destructive

Select an option in a dropdown

Inputs: element (required), ref (required), values (required).

browser_snapshotA
Read-only

Capture accessibility snapshot of the current page, this is better than screenshot

Inputs: filename.

browser_tabsA
Destructive

List, create, close, or select a browser tab.

Inputs: action (required), index.

browser_take_screenshotA
Read-only

Take a screenshot of the current page. You can't perform actions based on the screenshot, use browser_snapshot for actions.

Inputs: type, filename, element, ref, +1 more.

browser_typeA
Destructive

Type text into editable element

Inputs: element (required), ref (required), text (required), submit, +1 more.

browser_wait_forB
Read-only

Wait for text to appear or disappear or a specified time to pass

Inputs: time, text, textGone.

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

Loading tool schema changelog…

    TDQS

    B3.4/5.0

    Scored across 22 tools

    Disambiguation4/5

    Most tools have distinct purposes targeting specific browser interactions like clicking, navigating, or uploading files, with clear boundaries. However, browser_snapshot and browser_take_screenshot could be confused as both capture page states, though descriptions clarify that snapshot is for accessibility and actions while screenshot is visual only.

    Naming Consistency5/5

    All tool names follow a consistent snake_case pattern with a 'browser_' prefix, using clear verb_noun combinations like browser_click, browser_navigate, and browser_wait_for. This predictability makes it easy to understand and navigate the toolset.

    Tool Count3/5

    With 22 tools, the count is borderline high for a browser automation server, potentially overwhelming but still manageable. It covers many actions, but some tools like browser_install and browser_run_code might be less frequently used, slightly bloating the set.

    Completeness5/5

    The toolset provides comprehensive coverage for browser automation, including navigation, interaction (click, type, drag), debugging (console, network), media capture (screenshot, snapshot), and utilities (install, tabs). No obvious gaps exist for core Playwright workflows, ensuring agents can handle most web tasks.

    Maintenance

    ActivityInactive
    ResponsivenessNo recent community issues

    Related MCP Connectors

    Related MCP Servers

    • A
      license
      B
      quality
      D
      maintenance
      A Model Context Protocol server that provides browser automation capabilities using Playwright, enabling LLMs to interact with web pages through structured accessibility snapshots without needing screenshots or visually-tuned models.
      22
      10,908,336 npm
      Apache 2.0
    • A
      license
      B
      quality
      D
      maintenance
      A Model Context Protocol server that provides browser automation capabilities using Playwright, enabling LLMs to interact with web pages through structured accessibility snapshots without requiring screenshots or visually-tuned models.
      24
      10,908,336 npm
      Apache 2.0
    • A
      license
      A
      quality
      D
      maintenance
      A Model Context Protocol server that provides browser automation capabilities using Playwright, enabling LLMs to interact with web pages through structured accessibility snapshots without requiring screenshots or visually-tuned models.
      22
      10,908,336 npm
      Apache 2.0
    • A
      license
      B
      quality
      D
      maintenance
      A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots, providing browser automation capabilities without requiring screenshots or visually tuned models.
      7
      42,948 npm
      Apache 2.0