NagentArtefacts
Dev & Technology
Enterprise and White Glove
Company
Screenshot.fyi connects to a Nagent workspace with an API key. Once it is connected, agents can call 1 Screenshot.fyi action: "Take Screenshot". 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 Screenshot.fyi, with input parameters and output schema.
SCREENSHOT_FYI_TAKE_SCREENSHOTTool to capture a webpage screenshot. Use after specifying the target URL and options. JavaScript-heavy pages may capture before full render; ensure the page is fully loaded prior to capture.
Input parameters
The URL of the web page to take a screenshot of.
Output image format.
Apply dark mode styling to the captured page.
Whether to capture the full scrollable page. Long pages can produce very tall images that may exceed downstream display or storage limits.
Viewport width in pixels.
Viewport height in pixels.
Automatically remove cookie consent banners from the screenshot.
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 1 Screenshot.fyi action on Nagent: "Take Screenshot". Take Screenshot: Capture a webpage screenshot. Each action is listed on this page with its input parameters and its output.
Screenshot.fyi 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.
Take Screenshot takes 1 required input: url. It also takes 6 optional inputs: format, dark_mode, full_page, viewport_width, viewport_height and disable_cookie_banners. It returns data, error and successful.