Scrape any SPA or JS-rendered webpage and return its content.

Args: url: The page URL to scrape. wait_for: Playwright wait state — 'networkidle' | 'load' | 'domcontentloaded'. selector: Optional CSS selector to wait for before returning content. mode: Output format — 'markdown' | 'html' | 'text'. wait_ms: Extra settle delay in milliseconds after the page loads.

Returns: {content, page_title, url, word_count, mode}

Extract structured API endpoint data from an API documentation site.

Automatically detects the site type (swagger, redoc, stoplight, fmp, generic). Override detection by passing site_type explicitly.

Args: url: URL of the API documentation page. site_type: Force a specific extractor — 'swagger' | 'redoc' | 'stoplight' | 'fmp' | 'generic'.

Returns: { endpoints: [{method, path, operation_id, summary, description, tags, parameters}], count: int, site_type: str, url: str, }

Take a full-page screenshot of a URL for visual debugging.

Returns the file path and the PNG encoded as base64 so the agent can display it inline.

Args: url: URL to screenshot. full_page: Capture the full scrollable page (default True).

Returns: {saved_path: str, base64: str}

Scrape API documentation and seed a finanal-style SQLite database directly.

The target database must have an 'endpoints' table with columns: path, method, operation_id, summary, description, tags, parameters, source

Args: url: URL of the API documentation page. db_path: Absolute path to the SQLite database file. source_name: Label for the 'source' column (e.g. 'fmp', 'tapetide'). site_type: Optional site type override for the extractor.

Returns: {seeded: int, skipped: int, source: str, db_path: str}