NagentArtefacts
Dev & Technology
Enterprise and White Glove
Company
Cloudflare Browser Rendering connects to a Nagent workspace with an API key. Once it is connected, agents can call 4 Cloudflare Browser Rendering actions, such as "List Accounts", "Capture Screenshot" and "Scrape HTML Elements". 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 Cloudflare Browser Rendering, with input parameters and output schema.
CLOUDFLARE_BROWSER_RENDERING_CAPTURE_SCREENSHOTTool to capture a webpage screenshot. Use when you need a visual snapshot of a URL or HTML with optional viewport and clipping. Always validate screenshot content — the tool returns a successful result even when the captured page is a 404 or error page, with no error signal raised.
Input parameters
URL of the page to capture; required if `html` is unset
Raw HTML content to render; required if `url` is unset
Cache TTL in seconds (0 disables cache)
Viewport dimensions
Cloudflare account identifier
Screenshot options like fullPage or clip
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
CLOUDFLARE_BROWSER_RENDERING_LIST_ACCOUNTSList all Cloudflare accounts accessible to the authenticated API token. Returns account IDs, names, types, and settings. Use this to retrieve a valid account_id required by other browser-rendering actions like capture_screenshot, scrape_html_elements, and take_webpage_snapshot.
Input parameters
Filter accounts by name using partial/substring match. Case-insensitive.
Page number for pagination (1-indexed). Use with per_page to navigate through results.
Number of accounts to return per page. Valid range: 5-50. Default: 20.
Sort direction for results ordering. Use 'asc' for ascending (A-Z, oldest first) or 'desc' for descending (Z-A, newest first).
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
CLOUDFLARE_BROWSER_RENDERING_SCRAPE_HTML_ELEMENTSTool to scrape HTML elements for text, HTML, attributes, and box metrics. Use when you need detailed data of matched selectors after rendering a page.
Input parameters
URL of the webpage to navigate and scrape. Either 'url' or 'html' must be provided.
Inline HTML content to render and scrape. Either 'url' or 'html' must be provided.
Cache TTL in seconds (0-86400). Default is 5 seconds. Set to 0 to disable caching.
List of CSS selectors to scrape. At least one selector is required.
Cloudflare Account ID (32-character hexadecimal string). Use List Accounts to retrieve valid IDs.
Maximum time to wait after page load in milliseconds (0-300000). Use for JavaScript-heavy pages.
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
CLOUDFLARE_BROWSER_RENDERING_TAKE_WEBPAGE_SNAPSHOTCapture both rendered HTML content and a screenshot of a webpage in a single request. Returns the full DOM content as a string and a Base64-encoded screenshot image. Useful when you need both visual representation and page content for analysis.
Input parameters
URL of the webpage to capture. Either 'url' or 'html' must be provided.
Raw HTML content to render and capture. Use this instead of 'url' when you have HTML directly.
List of cookies to set before navigation
Cache TTL in seconds (0 disables caching, max 86400)
Viewport dimensions and device emulation
Cloudflare account identifier. Optional - the account is typically derived from the API connection configuration.
Custom user agent string
Styles to inject into the page
Continue even if certain events fail
Navigation settings before snapshot
Scripts to inject into the page
HTTP authentication credentials
Max time in ms for post-load actions
Wait time in ms before proceeding
Wait for an element before snapshot
Emulate CSS media type (e.g., 'print')
Options controlling screenshot capture
Allowed resource types
Regex patterns to allow requests
Blocked resource types
Additional HTTP headers for navigation
Regex patterns to block requests
Enable or disable JavaScript execution
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 Cloudflare Browser Rendering actions on Nagent, including "List Accounts", "Capture Screenshot" and "Scrape HTML Elements". List Accounts: List all Cloudflare accounts accessible to the authenticated API token. Each action is listed on this page with its input parameters and its output.
Cloudflare Browser Rendering 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.
It also takes 4 optional inputs: name, page, per_page and direction. It returns data, error and successful.