| tool_add_cookieD | |
| tool_backA | Navigate back in the browser history. |
| tool_clickA | Click an element on the page. This tool finds and clicks an element on the page using either CSS selector
or XPath. It will wait for the element to be clickable before attempting
to click it.
Args:
selector (str): The selector to find the element
by (str, optional): The selector type. Either "css" or "xpath". Defaults to "css"
Returns:
Dict[str, Any]: A dictionary containing:
- success (bool): Whether the operation was successful
- message (str): Status message
Example:
{"tool": "click", "args": {"selector": "#submit-button"}}
{"tool": "click", "args": {"selector": "//button[@type='submit']", "by": "xpath"}}
|
| tool_close_browserA | Close the browser instance. This tool closes the current Chrome browser window and cleans up resources.
It's safe to call this even if no browser is open.
Returns:
Dict[str, Any]: A dictionary containing:
- success (bool): Whether the operation was successful
- message (str): Status message
Example:
{"tool": "close_browser"}
|
| tool_delete_all_cookiesA | |
| tool_delete_cookieC | Delete a specific cookie. |
| tool_execute_scriptC | |
| tool_forwardB | Navigate forward in the browser history. |
| tool_fullscreen_windowB | Switch the browser window to full screen. |
| tool_get_cookiesA | Return all cookies from the current page. |
| tool_get_credentialsC | Retrieve stored credentials from system keychain
Args:
site: Website domain
username: User's username
|
| tool_get_current_urlA | Return the current page's URL. |
| tool_get_elementsA | Get multiple elements matching a selector. This tool finds all elements matching the selector and returns their text
content and HTML.
Args:
selector (str): The selector to find the elements
by (str, optional): The selector type. Either "css" or "xpath". Defaults to "css"
Returns:
Dict[str, Any]: A dictionary containing:
- success (bool): Whether the operation was successful
- message (str): Status message
- data (List[Dict]): List of elements, each containing:
- text (str): The text content of the element
- html (str): The outer HTML of the element
Example:
{"tool": "get_elements", "args": {"selector": ".item"}}
{"tool": "get_elements", "args": {"selector": "//li[@class='item']", "by": "xpath"}}
|
| tool_get_logC | |
| tool_get_page_sourceA | Return the current page's HTML source. |
| tool_get_textA | Get text from an element. This tool finds an element and returns its text content.
Args:
selector (str): The selector to find the element
by (str, optional): The selector type. Either "css" or "xpath". Defaults to "css"
Returns:
Dict[str, Any]: A dictionary containing:
- success (bool): Whether the operation was successful
- message (str): Status message
- data (str): The text content of the element
Example:
{"tool": "get_text", "args": {"selector": "h1"}}
{"tool": "get_text", "args": {"selector": "//div[@class='content']", "by": "xpath"}}
|
| tool_get_titleA | Return the current page's title. |
| tool_get_window_handlesB | Return all window handles. |
| tool_get_window_sizeA | Return the current browser window size. |
| tool_implicitly_waitC | Set implicitly wait time. |
| tool_maximize_windowB | Maximize the browser window. |
| tool_minimize_windowB | Minimize the browser window. |
| tool_navigateA | Navigate to a URL. This tool navigates the browser to the specified URL. If no browser
is open, it will automatically open one.
Args:
url (str): The URL to navigate to (must include protocol, e.g., 'https://')
Returns:
Dict[str, Any]: A dictionary containing:
- success (bool): Whether the operation was successful
- message (str): Status message
Example:
{"tool": "navigate", "args": {"url": "https://www.example.com"}}
|
| tool_open_browserA | Open a new Chrome browser instance. This tool initializes a new Chrome browser window. If a browser instance
already exists, it will reuse that instance.
Returns:
Dict[str, Any]: A dictionary containing:
- success (bool): Whether the operation was successful
- message (str): Status message
Example:
{"tool": "open_browser"}
|
| tool_refreshB | Refresh the current page. |
| tool_sampleC | Set Sample execution timeout. |
| tool_save_credentialsC | Securely save credentials
Args:
site: Website domain
username: User's username
password: Password
|
| tool_set_page_load_timeoutC | |
| tool_set_script_timeoutC | Set script execution timeout. |
| tool_set_window_sizeC | Set the browser window size. |
| tool_switch_to_default_contentD | Switch back to default content. |
| tool_switch_to_frameC | Switch to a specific frame. |
| tool_switch_to_windowC | Switch to a specific window. |
| tool_take_screenshotC | Save a screenshot of the current page. |
| tool_typeA | Type text into an element. This tool finds an input element and types the specified text into it.
It will clear any existing text in the element before typing.
Args:
selector (str): The selector to find the element
text (str): The text to type into the element
by (str, optional): The selector type. Either "css" or "xpath". Defaults to "css"
Returns:
Dict[str, Any]: A dictionary containing:
- success (bool): Whether the operation was successful
- message (str): Status message
Example:
{"tool": "type", "args": {"selector": "#search-input", "text": "search query"}}
{"tool": "type", "args": {"selector": "//input[@name='q']", "text": "search", "by": "xpath"}}
|
| tool_web_loginA | Perform website login
This tool attempts to log in to the provided URL. It waits for automatic
input prevention (CAPTCHA) to be detected before allowing the user to manually resolve it.
Args:
url (str): Login page URL
credentials (Dict[str, str]): Login credentials
- username: User ID
- password: Password
selectors (Dict[str, str]): CSS selectors for login form elements
- username: ID input field selector
- password: Password input field selector
- submit: Login button selector
auth_type (str, optional): Authentication type. Defaults to "form"
- form: Regular form-based login
- oauth: OAuth authentication
- api: API-based authentication
wait_for (Optional[str], optional): CSS selector for element to wait for after login
Returns:
Dict[str, Any]: Login result
- success (bool): Login success status
- message (str): Status message
- session_data (Dict): Login success session information
- cookies: Cookie information
- localStorage: Local storage data
- sessionStorage: Session storage data
Special handling:
1. CAPTCHA detection
- If reCAPTCHA or standard CAPTCHA is detected, wait for user to manually resolve
- Automatically continue login process after resolution
2. Naver login
- Automatic detection of various special situations like automatic input prevention, 2-step authentication
- Detailed error message analysis and return
Example:
>>> result = tool_web_login(
... url="https://nid.naver.com/nidlogin.login",
... credentials={
... "username": "your_username",
... "password": "your_password"
... },
... selectors={
... "username": "#id",
... "password": "#pw",
... "submit": ".btn_login"
... }
... )
>>> if not result["success"] and "CAPTCHA" in result["message"]:
... # Wait for user input for CAPTCHA resolution
... print("Please solve the CAPTCHA in the browser")
|
