Serpdog connects to a Nagent workspace with an API key. Once it is connected, agents can call 1 Serpdog action: "Screenshot API". 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 Serpdog, with input parameters and output schema.
SERPDOG_SCREENSHOT_APITool to capture a screenshot of a webpage. Use when you need a visual snapshot of a page; supports full-page, device emulation, delays, and dark mode.
Input parameters
Fully-qualified URL of the page to capture.
Seconds to wait before capturing the screenshot (optional).
Device emulation: 'desktop', 'tablet', or 'mobile'.
Response format: 'json' returns base64-encoded PNG in JSON; 'image' returns raw PNG bytes.
Capture in dark mode if supported (default: false).
Capture the entire scrollable page (default: false).
Viewport width in pixels (optional).
Viewport height in pixels (optional).
Hide cookie banners if possible (default: 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 1 Serpdog action on Nagent: "Screenshot API". Screenshot API: Capture a screenshot of a webpage. Each action is listed on this page with its input parameters and its output.
Serpdog 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.
Screenshot API takes 1 required input: url. It also takes 8 optional inputs: delay, device, output, dark_mode, full_page, window_width, window_height and no_cookie_banners. It returns data, error and successful.