Cloudflare Browser Rendering enables developers to programmatically control and interact with headless browser instances running on Cloudflare’s global network, facilitating tasks such as automating browser interactions, capturing screenshots, generating PDFs, and extracting data from web pages.
Cloudflare Browser Rendering enables developers to programmatically control and interact with headless browser instances running on Cloudflare’s global network, facilitating tasks such as automating browser interactions, capturing screenshots, generating PDFs, and extracting data from web pages. On Nagent, Cloudflare Browser Rendering is exposed as a fully-configurable ai web scraping integration that any agent can call — 4 actions, and API key authentication. No code is required to wire Cloudflare Browser Rendering into your workflow — connect it once via the External Integrations panel and reuse it across every agent you build.
Agent builders use Cloudflare Browser Rendering to automate the kinds of tasks ai web scraping teams previously handled manually. Concrete examples — each one is a single agent step in Nagent — include:
Every action and trigger is paired with a structured input/output schema (visible in the sections below), so when you wire Cloudflare Browser Rendering into Helix — our agentic agent builder — the editor knows exactly what each step expects and produces. Configure once, deploy anywhere across your Nagent agents.
Every operation an agent can call against Cloudflare Browser Rendering, with input parameters and output schema. Drop these into any step of an agent built in Helix.
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
No publicly available marketplace agent is found using this tool yet. There are 71 agents privately built on Nagent that already use Cloudflare Browser Rendering.
Build on Nagent
Connect Cloudflare Browser Rendering to any Nagent agent in minutes — no API key management, no boilerplate. Just configure and deploy.
The five questions agent builders ask before adopting a new integration.
Open the External Integrations panel inside Nagent (app.nagent.ai/externalIntegration), find Cloudflare Browser Rendering, and click "Connect Now." You'll authenticate with an API key — Nagent handles credential storage and refresh automatically. Once connected, Cloudflare Browser Rendering is available to any agent in your workspace.
No. Nagent provides no-code integration for every tool. Once Cloudflare Browser Rendering is connected, you configure its 4 actions directly in the agent builder UI — no API calls, no boilerplate, no schema management.
Helix — Nagent's agentic agent builder — lets you drop Cloudflare Browser Rendering steps into any workflow visually. Pick an action (e.g., one of those listed above), fill in the inputs (Helix knows the required vs. optional schema for each parameter), and connect it to upstream/downstream steps. Triggers run as the entry point of an agent, so when a Cloudflare Browser Rendering event fires, the agent kicks off automatically.
Every Cloudflare Browser Rendering action and trigger ships with a fully-typed schema — input parameters with name, type, required flag, and description, plus the output payload shape. The schemas are documented in the sections above. Helix uses these schemas to validate your configuration at build time and to type-check the data flowing between steps.
Yes. While Cloudflare Browser Rendering ships with 4 pre-built ai web scraping actions, you can layer custom logic around them inside Helix — pre/post-processing steps, conditional branches, retries, or stitching Cloudflare Browser Rendering together with other connected tools. For deeper customization, talk to our team about Nagent's Agentic AI Lab — forward-deployed engineers who build Cloudflare Browser Rendering-based workflows tailored to your business.