Skip to main content
Glama
AkhatorKing1

Playwright MCP Server

by AkhatorKing1
OverviewSchemaSourceRelated ServersDiscussionsAdmin
TypeScript
README.md
# Playwright MCP Server

This Actor wraps the [playwright-mcp](https://github.com/microsoft/playwright-mcp) project to provide a serverless Playwright browser in the cloud.
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.

All credits to the original authors of https://github.com/microsoft/playwright-mcp

🚩 Claim this MCP server. [Contact info](https://apify.com/contact)

## Key features

- 🚀 Uses Playwright's accessibility tree instead of pixel-based input for faster, lighter operation
- 📊 Works with structured data only - no vision models required
- 🎯 Applies tools deterministically, avoiding the ambiguity of screenshot approaches
- 🌐 Supports [Apify Proxy](https://apify.com/proxy) (datacenter, residential, custom) and other Apify features

## Use cases

- 🌐 Web navigation and form filling
- 📋 Structured data extraction
- 🧪 LLM-driven automated testing
- 🤖 Browser automation for AI agents

## Tools ([source](https://github.com/microsoft/playwright-mcp))

<!--- 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

<!-- 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 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

<!-- 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:
        - `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.

<!-- NOTE: This has been generated via update-readme.js -->

- **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.

<!-- 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:
        - `element` (string): Human-readable element description used to obtain permission to interact with the element
        - `x` (number): X coordinate
        - `y` (number): Y coordinate

<!-- NOTE: This has been generated via update-readme.js -->

- **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

<!-- NOTE: This has been generated via update-readme.js -->

- **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

<!-- NOTE: This has been generated via update-readme.js -->

- **browser_screen_type**
    - Description: Type text
    - Parameters:
        - `text` (string): Text to type into the element
        - `submit` (boolean, optional): Whether to submit entered text (press Enter after)

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

### 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: 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

<!-- 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 -->
Deploy Server
One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

TDQS

B3.4/5.0

Scored across 7 tools

Disambiguation3/5

The tools have overlapping purposes that could cause confusion, particularly around snapshot variants (get-full-snapshot, get-interactive-snapshot, get-text-snapshot) which all extract page content in different ways. However, descriptions help differentiate them by specifying focus areas like interactive elements or text content, preventing complete misselection.

Naming Consistency4/5

Tool names follow a consistent verb-object pattern with hyphens (e.g., execute-code, get-screenshot), making them predictable and readable. The only minor deviation is 'init-browser' which uses 'init' instead of a more standard verb like 'launch' or 'open', but it still fits the overall naming convention.

Tool Count5/5

With 7 tools, this server is well-scoped for browser automation with Playwright, covering key operations like initialization, code execution, and various content extraction methods. Each tool earns its place by addressing distinct aspects of web interaction without being overly sparse or bloated.

Completeness4/5

The toolset provides solid coverage for core Playwright workflows, including browser setup, DOM/content access, and automation execution. A minor gap exists in navigation control (e.g., no explicit 'navigate' or 'go-back' tools), but agents can work around this using execute-code or init-browser with URLs.

Maintenance

ActivityInactive
ResponsivenessNo issues

Resources