Technical Specifications
- Service Type: MCP Server
- Supported Formats:
- Input: JSON parameters for Playwright tools
- Output: Text responses with optional annotations
Usage Examples
Navigate to a website and take a screenshot
User prompt:
Check the earthquake situation this week and enter the earthquake website for the earthquake information in Taiwan in the last day
Result
Result from playwright.... too large to show
Raw Tool call (How LLM might use this tool)
{
"name": "browser_navigate",
"arguments": {
"url": "https://www.cwa.gov.tw/V8/E/E/index.html"
}
}
Raw tool result from the MCP server
{
"type": "text",
"text": "Result from playwright.... too large to show",
"annotations": null
}
Tools
browser_snapshot
Usage: Capture accessibility snapshot of the current page
Input Arguments: No arguments required.
browser_click
Usage: Perform click on a web page
Input Arguments:
| Name | Type | Required | Description |
|---|---|---|---|
element |
string | ✓ | Human-readable element description |
ref |
string | ✓ | Exact target element reference from snapshot |
browser_type
Usage: Type text into editable element
Input Arguments:
| Name | Type | Required | Description |
|---|---|---|---|
element |
string | ✓ | Human-readable element description |
ref |
string | ✓ | Exact target element reference from snapshot |
text |
string | ✓ | Text to type into the element |
submit |
boolean | Whether to submit entered text (press Enter after) | |
slowly |
boolean | 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_hover
Usage: Hover over element on page
Input Arguments:
| Name | Type | Required | Description |
|---|---|---|---|
element |
string | ✓ | Human-readable element description |
ref |
string | ✓ | Exact target element reference from snapshot |
browser_select_option
Usage: Select an option in a dropdown
Input Arguments:
| Name | Type | Required | Description |
|---|---|---|---|
element |
string | ✓ | Human-readable element description |
ref |
string | ✓ | Exact target element reference from snapshot |
values |
string[] | ✓ | Array of values to select in the dropdown. This can be a single value or multiple values. |
browser_navigate
Usage: Navigate to a URL
Input Arguments:
| Name | Type | Required | Description |
|---|---|---|---|
url |
string | ✓ | The URL to navigate to |
browser_navigate_back
Usage: Go back to the previous page
Input Arguments: No arguments required.
browser_navigate_forward
Usage: Go forward to the next page
Input Arguments: No arguments required.
browser_take_screenshot
Usage: Take a screenshot of the current page. You can't perform actions based on the screenshot, use browser_snapshot for actions.
Input Arguments:
| Name | Type | Required | Description |
|---|---|---|---|
raw |
boolean | Return raw PNG format | |
filename |
string | File name to save screenshot | |
element |
string | Element to screenshot | |
ref |
string | Element reference for screenshot |
browser_pdf_save
Usage: Save page as PDF
Input Arguments:
| Name | Type | Required | Description |
|---|---|---|---|
filename |
string | File name to save PDF |
browser_wait_for
Usage: Wait for text to appear or disappear or a specified time to pass
Input Arguments:
| Name | Type | Required | Description |
|---|---|---|---|
time |
number | The time to wait in seconds | |
text |
string | The text to wait for | |
textGone |
string | The text to wait for to disappear |
browser_press_key
Usage: Press a key on the keyboard
Input Arguments:
| Name | Type | Required | Description |
|---|---|---|---|
key |
string | ✓ | Name of the key to press or a character to generate, such as ArrowLeft or a |
browser_network_requests
Usage: Returns all network requests since loading the page
Input Arguments: No arguments required.
browser_console_messages
Usage: Returns all console messages
Input Arguments: No arguments required.
browser_close
Usage: Close the browser
Input Arguments: No arguments required.