Cloudflare Browser Rendering integration: operations for AI agents
Cloudflare Browser Rendering connects to Type.com as an integration. This page lists the 27 operations documented for Claude and Codex in Type.com: 21 read, 3 write, 3 destructive.
About Cloudflare Browser Rendering
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.
Categories: Analytics & Data
How to connect Cloudflare Browser Rendering to Type.com
- Access
- Organization connection: one shared account for the workspace.
To add the connection, follow the steps in Space connections.
Documented operations
27 operations. Your connection's permissions determine which operations are available. API references describe the vendor surface; they do not expand your connection's credentials or access.
27 operations listed.
- Read
Get accessibility tree page
Returns the page's accessibility tree. Use interestingOnly to only return semantically meaningful nodes; use root to scope the tree to a CSS-selector-anchored subtree. Control page loading with gotoOptions and waitFor options.
- Read
Get HTML content.
Fetches rendered HTML content from provided URL or HTML. Check available options like gotoOptions and waitFor to control page load behaviour.
- Read
Get crawl result.
Returns the result of a crawl job.
- Read
Get a browser session ID.
Acquires a browser and returns its session ID and websocket URL. Optionally accepts a JSON body with session guardrails to restrict outbound HTTP/S traffic.
- Read
List targets.
Returns a list of all debuggable targets including tabs, pages, service workers, and other browser contexts.
- Read
Activate a browser target.
Activates (brings to front) a specific browser target by its ID.
- Read
Close a browser target.
Closes a specific browser target (tab, page, etc.) by its ID. Returns 'Target is closing' on success or an error if the target is not found.
- Read
List targets.
Returns a list of all debuggable targets including tabs, pages, service workers, and other browser contexts.
- Read
Get a target by ID.
Returns the debuggable target with the given ID.
- Read
Get Chrome DevTools Protocol schema.
Returns the complete Chrome DevTools Protocol schema including all domains, commands, events, and types. This schema describes the entire CDP API surface.
- Read
Get browser version metadata.
Get browser version metadata.
- Read
List sessions.
List active browser sessions.
- Read
Get session details.
Get details for a specific browser session.
- Read
Get json.
Gets json from a webpage from a provided URL or HTML. Pass prompt or schema in the body. Control page loading with gotoOptions and waitFor options.
- Read
Get Links.
Get links from a web page.
- Read
Get markdown.
Gets markdown of a webpage from provided URL or HTML. Control page loading with gotoOptions and waitFor options.
- Read
Get PDF.
Fetches rendered PDF from provided URL or HTML. Check available options like gotoOptions and waitFor to control page load behaviour.
- Read
Get recording data.
Returns the recording data for a given session as a dictionary of events per targetId.
- Read
Get network recording data.
Returns network recording events for the requested target ID. Use ?format=har for a HAR JSON document.
- Read
Get screenshot.
Takes a screenshot of a webpage from provided URL or HTML. Control page loading with gotoOptions and waitFor options. Customize screenshots with viewport, fullPage, clip and others.
- Read
Get HTML content and screenshot.
Returns the page's HTML content and screenshot. Control page loading with gotoOptions and waitFor options. Customize screenshots with viewport, fullPage, clip and others.
- Write
Crawl websites.
Starts a crawl job for the provided URL and its children. Check available options like gotoOptions and waitFor to control page load behaviour.
- Write
Mint live view URLs for a browser session
Generates time-limited URLs to view a remote browser session. Set guardrails: { mode: 'readonly' } to create a view-only link.
- Write
Scrape elements.
Get meta attributes like height, width, text and others of selected elements.
- Destructive
Cancel a crawl job.
Cancels an ongoing crawl job by setting its status to cancelled and stopping all queued URLs.
- Destructive
Close browser session.
Closes an existing browser session.
- Destructive
Open a new browser tab.
Opens a new tab in the browser. Optionally specify a URL to navigate to.
No operations match.
See How connections work for access and permissions, or browse all integrations.