Cloudflare Browser Rendering

Render web pages, capture screenshots, and extract content with Cloudflare's headless browser. Sign in with Cloudflare to connect.

OAuthInfrastructure13 tools
Tools

What Cloudflare Browser Rendering exposes.

Every tool below is one this server advertised the last time Omniio refreshed it, under the cloudflare-browser__ namespace. Your agent never loads them all — it searches, and gets the few that match.

13 tools
  • cloudflare-browser__cancel_crawl1 argument · 1 required

    Cancel a running crawl job

    Requiredjob_id

  • cloudflare-browser__get_crawl_result1 argument · 1 required

    Get the status and records of a crawl job started with start_crawl

    Requiredjob_id

  • cloudflare-browser__get_url_html_content1 argument · 1 required

    Get page HTML content

    Requiredurl

  • cloudflare-browser__get_url_json3 arguments · 1 required

    Extract structured JSON from a page using AI. Provide a prompt and/or a response_format JSON schema to guide extraction.

    Requiredurl

  • cloudflare-browser__get_url_links2 arguments · 1 required

    Get the list of links on a page

    Requiredurl

  • cloudflare-browser__get_url_markdown1 argument · 1 required

    Get page converted into Markdown

    Requiredurl

  • cloudflare-browser__get_url_pdf1 argument · 1 required

    Render a page to PDF

    Requiredurl

  • cloudflare-browser__get_url_screenshot2 arguments · 1 required

    Get page screenshot

    Requiredurl

  • cloudflare-browser__get_url_snapshot1 argument · 1 required

    Get page HTML content and a screenshot in a single call

    Requiredurl

  • cloudflare-browser__kill_browser_session1 argument · 1 required

    Close (kill) a Browser Run session by its session ID

    Requiredsession_id

  • cloudflare-browser__list_browser_sessionsno arguments

    List active Browser Run sessions for the account

  • cloudflare-browser__scrape_url_elements2 arguments · 2 required

    Scrape elements from a page by CSS selector

    Requiredurlelements

  • cloudflare-browser__start_crawl4 arguments · 1 required

    Start an asynchronous crawl of a website. Returns a job_id — poll get_crawl_result to retrieve records.

    Requiredurl

Connecting

Three steps, and the last one is not yours.

01

Point a client at Omniio

One URL, authorized once by your client. If you already use Omniio, this step is done.

02

Switch Cloudflare Browser Rendering on

Authorize it from your library; the grant is yours and stays yours.

03

Ask for what you need

The agent searches, reads the one schema it picked, and runs it. You do not name the tool.

claude code
claude mcp add --transport http omniio https://mcp.omniio.dev
Infrastructure

Others in the same category.

They share the endpoint, so having more than one on costs you nothing in context — the search decides which is relevant.

Browse the whole library