playwright-mcp/README.md

## Playwright MCP

A Model Context Protocol (MCP) server that provides browser automation capabilities using [Playwright](https://playwright.dev). 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

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


#### Installation in VS Code

Install the Playwright MCP server using the VS Code CLI:

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

```bash
# 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.


### Running headless browser (Browser without GUI).

This mode is useful for background or batch operations.

```js
{
  "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,
you can run Playwright in a client-server manner. You'll run the Playwright server
from environment with the DISPLAY

```sh
npx playwright run-server
```

And then in MCP config, add following to the `env`:

```js
{
  "mcpServers": {
    "playwright": {
      "command": "npx",
      "args": [
        "@playwright/mcp@latest"
      ],
      "env": {
        // Use the endpoint from the output of the server above.
        "PLAYWRIGHT_WS_ENDPOINT": "ws://localhost:<port>/"
      }
    }
  }
}
```

### 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:

```js
{
  "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

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

// ...

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

### Snapshot Mode

The Playwright MCP provides a set of tools for browser automation. Here are all available tools:

- **browser_navigate**
  - Description: Navigate to a URL
  - Parameters:
    - `url` (string): The URL to navigate to

- **browser_go_back**
  - Description: Go back to the previous page
  - Parameters: None

- **browser_go_forward**
  - Description: Go forward to the next page
  - Parameters: None

- **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): Whether to submit entered text (press Enter after)

- **browser_select_option**
  - Description: Select 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.

- **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`

- **browser_snapshot**
  - Description: Capture accessibility snapshot of the current page (better than screenshot)
  - Parameters: None

- **browser_save_as_pdf**
  - Description: Save page as PDF
  - Parameters: None

- **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


### Vision Mode

Vision Mode provides tools for visual-based interactions using screenshots. Here are all available tools:

- **browser_navigate**
  - Description: Navigate to a URL
  - Parameters:
    - `url` (string): The URL to navigate to

- **browser_go_back**
  - Description: Go back to the previous page
  - Parameters: None

- **browser_go_forward**
  - Description: Go forward to the next page
  - Parameters: None

- **browser_screenshot**
  - Description: Capture screenshot of the current page
  - Parameters: None

- **browser_move_mouse**
  - Description: Move mouse to specified coordinates
  - Parameters:
    - `x` (number): X coordinate
    - `y` (number): Y coordinate

- **browser_click**
  - Description: Click at specified coordinates
  - Parameters:
    - `x` (number): X coordinate to click at
    - `y` (number): Y coordinate to click at

- **browser_drag**
  - Description: Perform drag and drop operation
  - Parameters:
    - `startX` (number): Start X coordinate
    - `startY` (number): Start Y coordinate
    - `endX` (number): End X coordinate
    - `endY` (number): End Y coordinate

- **browser_type**
  - Description: Type text at specified coordinates
  - Parameters:
    - `text` (string): Text to type
    - `submit` (boolean): 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`

- **browser_save_as_pdf**
  - Description: Save page as PDF
  - Parameters: None

- **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