Tools Reference

Overview

browserTools(session) returns all 32 tools. You can filter by module or import individual tool factories.

import { browserTools } from '@cogitator-ai/browser';

const allTools = browserTools(session);

const subset = browserTools(session, {
  modules: ['navigation', 'extraction'],
});

Navigation

7 tools for page navigation and waiting.

browser_navigate

Navigate to a URL. Returns the final URL, page title, and HTTP status.

browser_go_back

Go back to the previous page in browser history. No parameters.

browser_go_forward

Go forward to the next page in browser history. No parameters.

browser_reload

Reload the current page.

browser_wait_for_navigation

Wait for the page to navigate to a URL matching a pattern.

browser_get_current_url

Get the current page URL and title. No parameters.

browser_wait_for_selector

Wait for a CSS selector to appear on the page.

Interaction

9 tools for clicking, typing, and form manipulation.

browser_click

Click an element by CSS selector.

browser_type

Type text into an input element. Uses fill() for instant input or type() for keystroke simulation. When stealth is enabled, automatically adds human-like delays between keystrokes.

browser_select_option

Select an option from a <select> element.

browser_hover

Hover over an element.

browser_scroll

Scroll the page or a specific element.

browser_press_key

Press a keyboard key with optional modifiers.

browser_drag_and_drop

Drag an element and drop it onto another.

browser_fill_form

Smart form filler. Finds inputs by name, placeholder, aria-label, or associated label text.

String values are typed into inputs, booleans toggle checkboxes, and string arrays select multiple options. When stealth is enabled, typing uses human-like delays.

// the agent calls this tool with:
{
  "fields": {
    "Email": "user@example.com",
    "Password": "secret",
    "Remember me": true,
    "Country": ["US"]
  }
}

browser_upload_file

Upload files to a file input element.

Extraction

7 tools for reading page content.

browser_get_text

Extract text content from the page or a specific element.

browser_get_html

Get HTML content of the page or a specific element.

browser_get_attribute

Get the value of an attribute on a DOM element.

browser_get_links

Extract all links from the page or a scoped element. Returns text, href, and title for each link.

browser_query_selector_all

Query all elements matching a CSS selector. Returns tag, text, attributes, and visibility for each.

browser_extract_table

Extract structured data from an HTML table as headers and rows.

browser_extract_structured

Extract clean readable text from the page. Removes scripts, styles, and non-visible elements. Returns the text alongside the extraction instruction for agent processing.

Vision

4 tools for visual interaction. See the dedicated Vision page for details.

browser_screenshot

Take a screenshot of the page or element. Returns base64-encoded image data.

browser_screenshot_element

Screenshot a specific element with bounding box coordinates.

browser_find_by_description

Find elements matching a natural language description using the accessibility tree.

browser_click_by_description

Find an element by description and click it. Tries button, link, text, label, and placeholder strategies.

Network

5 tools for request interception and traffic monitoring. See the dedicated Network page for details.

browser_intercept_request

Intercept HTTP requests matching a URL pattern.

browser_wait_for_response

Wait for an HTTP response matching a URL pattern.

browser_block_resources

Block specific resource types from loading.

browser_capture_har

Start or stop capturing HTTP traffic in HAR format.

browser_get_api_calls

Get captured XHR/fetch API calls with optional filtering.