mcp/playwright

Verified Publisher

By mcp

•Updated about 19 hours ago

Playwright MCP server

Image

Machine learning & AI

500K+

View on MCP:Hub

Overview Tags

mcp/playwright repository overview

⁠Playwright MCP Server

Playwright MCP server.

What is an MCP Server?⁠

⁠MCP Info

Attribute	Details
Docker Image	mcp/playwright⁠
Author	microsoft⁠
Repository	https://github.com/microsoft/playwright-mcp⁠

⁠Image Building Info

Attribute	Details
Dockerfile	https://github.com/microsoft/playwright-mcp/blob/e39e83bb130069a36b14a1e9274315e724f82ab3/Dockerfile⁠
Commit	`e39e83bb130069a36b14a1e9274315e724f82ab3`
Docker Image built by	Docker Inc.
Docker Scout Health Score
Verify Signature	`COSIGN_REPOSITORY=mcp/signatures cosign verify mcp/playwright --key https://raw.githubusercontent.com/docker/keyring/refs/heads/main/public/mcp/latest.pub`
Licence	Apache License 2.0

⁠Available Tools (22)

Tools provided by this Server	Short Description
`browser_click`	Click
`browser_close`	Close browser
`browser_console_messages`	Get console messages
`browser_drag`	Drag mouse
`browser_evaluate`	Evaluate JavaScript
`browser_file_upload`	Upload files
`browser_fill_form`	Fill form
`browser_handle_dialog`	Handle a dialog
`browser_hover`	Hover mouse
`browser_install`	Install the browser specified in the config
`browser_navigate`	Navigate to a URL
`browser_navigate_back`	Go back
`browser_network_requests`	List network requests
`browser_press_key`	Press a key
`browser_resize`	Resize browser window
`browser_run_code`	Run Playwright code
`browser_select_option`	Select option
`browser_snapshot`	Page snapshot
`browser_tabs`	Manage tabs
`browser_take_screenshot`	Take a screenshot
`browser_type`	Type text
`browser_wait_for`	Wait for

⁠Tools Details

⁠Tool: `browser_click`

Perform click on a web page

Parameters	Type	Description
`ref`	`string`	Exact target element reference from the page snapshot
`button`	`string` optional	Button to click, defaults to left
`doubleClick`	`boolean` optional	Whether to perform a double click instead of a single click
`element`	`string` optional	Human-readable element description used to obtain permission to interact with the element
`modifiers`	`array` optional	Modifier keys to press

This tool may perform destructive updates.

This tool interacts with external entities.

⁠Tool: `browser_close`

Close the page

⁠Tool: `browser_console_messages`

Returns all console messages

Parameters	Type	Description
`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.

This tool is read-only. It does not modify its environment.

This tool interacts with external entities.

⁠Tool: `browser_drag`

Perform drag and drop between two elements

Parameters	Type	Description
`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
`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

This tool may perform destructive updates.

This tool interacts with external entities.

⁠Tool: `browser_evaluate`

Evaluate JavaScript expression on page or element

Parameters	Type	Description
`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

This tool may perform destructive updates.

This tool interacts with external entities.

⁠Tool: `browser_file_upload`

Upload one or multiple files

Parameters	Type	Description
`paths`	`array` optional	The absolute paths to the files to upload. Can be single file or multiple files. If omitted, file chooser is cancelled.

This tool may perform destructive updates.

This tool interacts with external entities.

⁠Tool: `browser_fill_form`

Fill multiple form fields

Parameters	Type	Description
`fields`	`array`	Fields to fill in

This tool may perform destructive updates.

This tool interacts with external entities.

⁠Tool: `browser_handle_dialog`

Handle a dialog

Parameters	Type	Description
`accept`	`boolean`	Whether to accept the dialog.
`promptText`	`string` optional	The text of the prompt in case of a prompt dialog.

This tool may perform destructive updates.

This tool interacts with external entities.

⁠Tool: `browser_hover`

Hover over element on page

Parameters	Type	Description
`ref`	`string`	Exact target element reference from the page snapshot
`element`	`string` optional	Human-readable element description used to obtain permission to interact with the element

This tool may perform destructive updates.

This tool interacts with external entities.

⁠Tool: `browser_install`

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

⁠Tool: `browser_navigate`

Navigate to a URL

Parameters	Type	Description
`url`	`string`	The URL to navigate to

This tool may perform destructive updates.

This tool interacts with external entities.

⁠Tool: `browser_navigate_back`

Go back to the previous page in the history

⁠Tool: `browser_network_requests`

Returns all network requests since loading the page

Parameters	Type	Description
`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.

This tool is read-only. It does not modify its environment.

This tool interacts with external entities.

⁠Tool: `browser_press_key`

Press a key on the keyboard

Parameters	Type	Description
`key`	`string`	Name of the key to press or a character to generate, such as `ArrowLeft` or `a`

This tool may perform destructive updates.

This tool interacts with external entities.

⁠Tool: `browser_resize`

Resize the browser window

Parameters	Type	Description
`height`	`number`	Height of the browser window
`width`	`number`	Width of the browser window

This tool may perform destructive updates.

This tool interacts with external entities.

⁠Tool: `browser_run_code`

Run Playwright code snippet

Parameters	Type	Description
`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(); }`

This tool may perform destructive updates.

This tool interacts with external entities.

⁠Tool: `browser_select_option`

Select an option in a dropdown

Parameters	Type	Description
`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.
`element`	`string` optional	Human-readable element description used to obtain permission to interact with the element

This tool may perform destructive updates.

This tool interacts with external entities.

⁠Tool: `browser_snapshot`

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

Parameters	Type	Description
`filename`	`string` optional	Save snapshot to markdown file instead of returning it in the response.

This tool is read-only. It does not modify its environment.

This tool interacts with external entities.

⁠Tool: `browser_tabs`

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

Parameters	Type	Description
`action`	`string`	Operation to perform
`index`	`number` optional	Tab index, used for close/select. If omitted for close, current tab is closed.

This tool may perform destructive updates.

This tool interacts with external entities.

⁠Tool: `browser_take_screenshot`

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

Parameters	Type	Description
`type`	`string`	Image format for the screenshot. Default is png.
`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.
`filename`	`string` optional	File name to save the screenshot to. Defaults to `page-{timestamp}.{png
`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.
`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.

This tool is read-only. It does not modify its environment.

This tool interacts with external entities.

⁠Tool: `browser_type`

Type text into editable element

Parameters	Type	Description
`ref`	`string`	Exact target element reference from the page snapshot
`text`	`string`	Text to type into the element
`element`	`string` optional	Human-readable element description used to obtain permission to interact with the element
`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.
`submit`	`boolean` optional	Whether to submit entered text (press Enter after)

This tool may perform destructive updates.

This tool interacts with external entities.

⁠Tool: `browser_wait_for`

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

Parameters	Type	Description
`text`	`string` optional	The text to wait for
`textGone`	`string` optional	The text to wait for to disappear
`time`	`number` optional	The time to wait in seconds

This tool is read-only. It does not modify its environment.

This tool interacts with external entities.

⁠Use this MCP Server

{
  "mcpServers": {
    "playwright": {
      "command": "docker",
      "args": [
        "run",
        "-i",
        "--rm",
        "mcp/playwright"
      ]
    }
  }
}

Why is it safer to run MCP Servers with Docker?⁠

Install from MCP:Hub

Playwright

View and Install from MCP:Hub

Tag summary

Recent tags

Content type

Image

Digest

sha256:c1a5c5acb…

Size

378.4 MB

Last updated

about 19 hours ago

Run in Docker Desktop

Requires Docker Desktop 4.37.1 or later.

This week's pulls

Pulls:

19,016

Last week

Learn more⁠

mcp/playwright

mcp/playwright repository overview

⁠Playwright MCP Server

⁠MCP Info

⁠Image Building Info

⁠Available Tools (22)

⁠Tools Details

⁠Tool: browser_click

⁠Tool: browser_close

⁠Tool: browser_console_messages

⁠Tool: browser_drag

⁠Tool: browser_evaluate

⁠Tool: browser_file_upload

⁠Tool: browser_fill_form

⁠Tool: browser_handle_dialog

⁠Tool: browser_hover

⁠Tool: browser_install

⁠Tool: browser_navigate

⁠Tool: browser_navigate_back

⁠Tool: browser_network_requests

⁠Tool: browser_press_key

⁠Tool: browser_resize

⁠Tool: browser_run_code

⁠Tool: browser_select_option

⁠Tool: browser_snapshot

⁠Tool: browser_tabs

⁠Tool: browser_take_screenshot

⁠Tool: browser_type

⁠Tool: browser_wait_for

⁠Use this MCP Server

Install from MCP:Hub

Playwright

Tag summary

This week's pulls

⁠Tool: `browser_click`

⁠Tool: `browser_close`

⁠Tool: `browser_console_messages`

⁠Tool: `browser_drag`

⁠Tool: `browser_evaluate`

⁠Tool: `browser_file_upload`

⁠Tool: `browser_fill_form`

⁠Tool: `browser_handle_dialog`

⁠Tool: `browser_hover`

⁠Tool: `browser_install`

⁠Tool: `browser_navigate`

⁠Tool: `browser_navigate_back`

⁠Tool: `browser_network_requests`

⁠Tool: `browser_press_key`

⁠Tool: `browser_resize`

⁠Tool: `browser_run_code`

⁠Tool: `browser_select_option`

⁠Tool: `browser_snapshot`

⁠Tool: `browser_tabs`

⁠Tool: `browser_take_screenshot`

⁠Tool: `browser_type`

⁠Tool: `browser_wait_for`