NagentArtefacts
Dev & Technology
Enterprise and White Glove
Company
OpenGraph.io connects to a Nagent workspace with an API key. Once it is connected, agents can call 4 OpenGraph.io actions, such as "Capture Screenshot", "Extract Site Metadata" and "Scrape Site". Nothing is enabled on connect: each action is allowed one at a time, and an action with side effects runs or waits for a person according to the agent's level.
Every operation an agent can call against OpenGraph.io, with input parameters and output schema.
OPENGRAPH_IO_CAPTURE_SCREENSHOTTool to capture high-quality screenshots of any webpage programmatically. Supports full-page captures, custom dimensions, device presets, element-specific screenshots, and quality settings. Screenshots are available for 24 hours after generation. Use when you need to capture visual snapshots of websites with specific rendering requirements or device simulations.
Input parameters
The target webpage URL to capture. Must be a valid HTTP or HTTPS URL.
Image format options for the screenshot.
Image quality from 10 to 80 (rounded to nearest 10). Higher values mean better quality but larger file size. Defaults to 80.
Allow returning a cached screenshot if available. Set to false to force a fresh capture. Defaults to true.
CSS selector to capture a specific element instead of the full page. Example: '.main-content' or '#header'.
Set browser preference to dark mode before capturing. Useful for capturing dark-themed versions of websites. Defaults to false.
Capture the entire scrollable page instead of just the viewport. Set to true for full-page screenshots. Defaults to false.
Use a proxy for accessing protected or restricted sites. Defaults to false.
Viewport size presets for different device types.
Delay in milliseconds before capturing the screenshot. Useful for waiting for dynamic content to load. Range: 0-10000ms.
Comma-separated CSS selectors of elements to hide from the screenshot. Useful for removing ads, popups, or unwanted elements. Example: '.header,.footer,.ads'.
Navigation timeout in milliseconds. Maximum time to wait for the page to load. Range: 1000-60000ms. Defaults to 30000ms (30 seconds).
Automatically block known cookie consent banners from appearing in the screenshot. Defaults to true.
Output
Data from the action execution
Error if any occurred during the execution of the action
Whether or not the action execution was successful or not
OPENGRAPH_IO_EXTRACT_SITETool to extract site metadata. Use when you need to retrieve Open Graph and other meta signals from a website.
Input parameters
URL of the site to extract metadata from
Scrape all data instead of just Open Graph and meta tags
Use a proxy during extraction
Preferred language for extracted data (e.g., 'en-US')
Render the page in a browser before extraction
Output
Data from the action execution
Error if any occurred during the execution of the action
Whether or not the action execution was successful or not
OPENGRAPH_IO_SCRAPE_SITETool to scrape a site for its raw HTML and social/OpenGraph metadata. Use when you need the full page content and metadata. Use after confirming the URL.
Input parameters
The URL of the site to scrape. This will be URL-encoded by the action. E.g., 'https://example.com'.
If true, forces scraping regardless of cache. Otherwise may return cached result.
If false, forces a fresh scrape instead of returning cached data. Defaults to using cache if not set.
If true, performs a full page render (runs JavaScript). Defaults to a lightweight scrape if not set.
Output
Data from the action execution
Error if any occurred during the execution of the action
Whether or not the action execution was successful or not
OPENGRAPH_IO_SCRAPE_URLTool to scrape raw HTML content from a website with anti-bot protection and optional JavaScript rendering. Use when you need the full HTML source code of a page, especially for sites with bot detection or dynamic content.
Input parameters
The target website URL to scrape. Must start with http:// or https://. This will be URL-encoded automatically.
Allow cached results. Set to false to force a fresh scrape. Defaults to true to improve performance.
Use standard datacenter proxy for the request. Helps bypass basic bot detection. Defaults to false.
Language header for localized content (e.g., 'en-US', 'fr-FR', 'es-ES'). Defaults to 'en-US'.
Enable JavaScript rendering. Required for Single Page Applications (SPAs) and dynamic content. Defaults to false for faster lightweight scraping.
Use residential proxy for the request. Better for scraping protected sites with stronger bot detection. Defaults to false.
Use mobile proxy for the request. Best for heavily protected sites with advanced bot detection. Defaults to false.
Output
Data from the action execution
Error if any occurred during the execution of the action
Whether or not the action execution was successful or not
Agents can call 4 OpenGraph.io actions on Nagent, including "Capture Screenshot", "Extract Site Metadata" and "Scrape Site". Capture Screenshot: Capture high-quality screenshots of any webpage programmatically. Each action is listed on this page with its input parameters and its output.
OpenGraph.io connects with an API key, under your workspace's own connection. Nothing is enabled on connect: each action is allowed one at a time and can be scoped to the agents that need it.
Capture Screenshot takes 1 required input: url. It also takes 12 optional inputs: format, quality, cache_ok, selector, dark_mode, full_page, use_proxy, dimensions, capture_delay, exclude_selectors, navigationTimeout and block_cookie_banner. It returns data, error and successful.