hmm, I see... but maybe you can do that without creating the MCP server, because at the end you just
hmm, I see... but maybe you can do that without creating the MCP server, because at the end you just need the tools, right?
Di guess not ideal (i’d love to separate and in my app users can bring their own mcp servers so it may be hosted on CF) .but i can give it a try.. any guidance on how to use the mcp lib without creating the server?
Kheads up - content endpoint was updated. and now returns title https://developers.cloudflare.com/api/resources/browser_rendering/subresources/content/methods/create/#(params)%200%20%3E%20(param)%20rejectRequestPattern%20%3E%20(schema)
Interact with Cloudflare's products and services via the Cloudflare API
Dcorrect me if i'm wrong but i only see
createMcpAgent
Ryes, right now without changes to the library it's not trivial, but all tools are available in playwright-mcp internal code
Dok, thx. i'm going w/ browserbase for now,
R@dandoen btw, just to better understand yhe error you had: are you exposing playwright MCP in the same worker that tries to consume it? Or do you have two different workers / apps, one as a playwright mcp server, and the other as a mcp client using ai-sdk?
Dtwo different workers!
Rwell, I would have to check that better, but nevertheless as I was saying , and because playwright-mcp basically has its toolset locally, there's no need to perform external calls. I did a small experiment of exposing a toolsetProvider, you can take a look at https://github.com/cloudflare/playwright-mcp/pull/20, check the example for usage (this depends on our merge of playwright-mcp 0.0.30 which was not released yet, we only released a new release of playwright today)
Dthat sounds great, i'll check it out.
Dbtw do you ever see cloudflare/playwright not force me to use the browser rendering api? i'd love to be able to use playwright-core inside workers to communicate with either my own CDP endpoint over ws or providers like browser base.
i noticed (at least the currently published 0.10 release) is doing a few things like overriding the host (setting a fake host), expecting session id query parameters to decide when to use connect (easy to bypass), checking for binding in the query param (easy to bypass) but also chunking the ws messages presumably due to limitation in the browser render api.
i noticed (at least the currently published 0.10 release) is doing a few things like overriding the host (setting a fake host), expecting session id query parameters to decide when to use connect (easy to bypass), checking for binding in the query param (easy to bypass) but also chunking the ws messages presumably due to limitation in the browser render api.
Di just spent the day patching playwright-core, in a similar way i saw ya'll had done it to make it work inside the worker runtime 
Rfor the time being it's not possible. We could in theory allow both scenarios, but from my experience, if the browser is not in the same network, we get lots of latency. For instance, a simple 
newPagetrue, but also depends on the customer use case whether 1s is acceptable or not. ie if it's an async job running in the background, then 1s doesn't really matter 
DI'm also interested in this!
@Rui Figueira Would you be interested in supporting this?
https://github.com/cloudflare/playwright/pull/59
cc @dandoen
@Rui Figueira Would you be interested in supporting this?
https://github.com/cloudflare/playwright/pull/59
cc @dandoen
GitHub
This adds support for using any ws CDP based server to connect to, without breaking existing usage of the browser rendering api. Example usage with Browserbase:
import { Browserbase } from &#39...
import { Browserbase } from &#39...
D@Kathy curious if ya'll would be interested to make the @Cloudflare/playwright package work also for customers not using the browser rendering API (yet). by supporting this, you'll help me keep an easy migration path (back) to cloudflare
AHi, I found that using the /content endpoint we can not set the returned HTML type. Others like Crawl4ai allow us to set raw, cleaned HTML and markdown. I think CF should implement it.
HIs browser rendering extremely slow for anyone else to bootup/work?
Hseeing extremely slow times.
Kyou're looking for info to be returned in markdown? we have https://developers.cloudflare.com/browser-rendering/rest-api/markdown-endpoint/
Cloudflare Docs
The /markdown endpoint retrieves a webpage's content and converts it into Markdown format. You can specify a URL and optional parameters to refine the extraction process.
AThank you, but I need the other 2 ones: raw HTML for getting invisible metadata and cleaned HTML for visible content. i think both Firecrawl and Crawl4ai features would inspire Browser Rendering PMs and devs a lot.
Pis Browser Rendering down? Been getting 503 error for the last 10 minutes
Kso our /html endpoint returns raw already today. So what we don't yet have for you is
can you explain what you'd like to do with
cleanedcan you explain what you'd like to do with
cleanedraw
Hwe ended up moving away
Hused both playwright/puppeeter, don't think it makes any difference.
SCan we have wrapped functions for rest api in worker bindings?
K
is on the listSDoes failed rest api calls (waitForTimeout exceeds) adds to billable browser hours?
SCan we have browser hours used in the response of rest api?
Kgreat idea. adding to the list
Kit does not
SIs the rest api rate limit sliding window or fixed time period? I’m trying to adjust my backend concurrency settings.
SIs it possible to make the /markdown api return both the original html and the extracted markdown? I'm building something that requires verifying results afterwards, which need a "snapshot" of original html dom (like wayback machine).
Kgreat q - will add to docs too
Rate limits are enforced with a fixed per second fill rate. For example, the workers paid limit of 60 requests per minute translates to 1 request per second. This means you cannot send all 60 requests at once; the API expects them to be spread evenly over the minute.
Rate limits are enforced with a fixed per second fill rate. For example, the workers paid limit of 60 requests per minute translates to 1 request per second. This means you cannot send all 60 requests at once; the API expects them to be spread evenly over the minute.
Kwe have a separate /content endpoint for html https://developers.cloudflare.com/browser-rendering/rest-api/content-endpoint/. any reason that doesn't work for you?
Cloudflare Docs
The /content endpoint instructs the browser to navigate to a website and capture the fully rendered HTML of a page, including the head section, after JavaScript execution. This is ideal for capturing content from JavaScript-heavy or interactive websites.
SI don’t want to make 2 request for a single scrape. I’m thinking that for /json or /markdown endpoint, the original content is already available, could have an option to just return both json/markdown and original content.
GHello, is it allowed to scrap for example Instagram for their OG meta properties or does it break the Cloudflare rules?
Ahow does one monitor the usage of the api? I only see how many requests its making to the api but not how much browser hours that consumed?
AI just saw "Currently, the Cloudflare dashboard displays usage metrics exclusively for the Workers Bindings method. Usage data for the REST API is not yet available in the dashboard. We are actively working on adding REST API usage metrics to the dashboard.". How do I monitor my usage somewhere else?
GCan anyone give me an answer to this question please :/
MHi there! Since I'm not getting an answer in the #workers-help thingy, am I in the right place here to report this bug? Or am I doing something wrong?
workers-and-pages-helpFonts look bad in Browser Rendering screenshots
workers-and-pages-helpFonts look bad in Browser Rendering screenshots
GDoes anyone use this api for retrieving the opengraph meta data of a website? Are there any configurations which I have to consider for best practice? Appreciate any help
KDepends on a site but usually you don't need browser rendering to fetch opengraph. Just do simple http call to fetch html.
GInstagram and Tiktok loads the opengraph dynamically
Khmm might be an unsupported font. let me get a list of fonts we currently support. do you know what font it is?
Kwhen using the rest api you can see the browser time used for every request in the
ah i need to update that in the docs. thanks for reminding
X-Browser-Ms-Used headerah i need to update that in the docs. thanks for reminding
MOne example is the google font Poppins
Kgot it, yea looks like it's not a supported font right now. would you be able to use one of the ones here instead? https://kathayl-patch-9.preview.developers.cloudflare.com/browser-rendering/reference/supported-fonts/
Cloudflare Docs
Browser Rendering uses a managed Chromium environment that includes a standard set of fonts. When you generate a screenshot or PDF, text is rendered using the fonts available in this environment.
