[makingstuffs]

I don't see how an MCP can be useful for browsing the net and doing things like shopping as has been suggested. Large companies such as CloudFlare have spent millions on, and made a business from, bot detection and blocking.

Do we suppose they will just create a backdoor to allow _some_ bots in? If they do that how long will it be before other bots impersonate them? It seems like a bit of a fad from my small mind.

Suppose it does become a thing, what then? We end up with an internet which is heavily optimised for bots (arguably it already is to an extent) and unusable for humans?

Wild.

[kraftman]

There are already plenty of services that provide residential proxies and captcha bypass pretty cheaply.

https://brightdata.com/pricing/web-unlocker https://2captcha.com/pricing

[TeMPOraL]

> Suppose it does become a thing, what then? We end up with an internet which is heavily optimised for bots (arguably it already is to an extent) and unusable for humans?

As opposed to the Web we now have, which is heavily optimized for... wasting human life.

What you're asking for, what "large companies such as CloudFlare have spent millions on", is verifying that on the other end of the connection is a web browser, and behind that web browser there is a human being that's being made to needlessly suffer and waste their limited lifespans, as they tediously work their way through the UI maze like a good little lab rat, watching ads at every turn of the corridor, while being constantly surveilled.

Or do you believe there is some other reason why you should care about whether you're interacting with a "human" (really: an user agent called "web browser") vs. "not human" (really: any other user agent)?

The relationship between the commercial web and its users is antagonistic - businesses make money through friction, by making it more difficult for users to accomplish their goals. That's why we never got the era of APIs and web automation for users. That's why we're dealing with tons of bespoke shitty SPAs instead of consistent interfaces - because no store wants to make it easy for you to comparison-shop, or skip their upsells, or efficiently search through the stock; no news service wants you to skip ads or make focused searches, etc.

As users, we've lost the battle for APIs and continue to be forced to use the "manual web" (with active cooperation of the browser vendors, too). MCP feels promising because we're in a moment in time, however brief, where LLMs can navigate the "manual web" for us, shielding us from all the malicious bullshit (ads, marketing copy, funneling, call to actions, confusing design, dark patterns, less dark patterns, the fact that your store is a bloated SPA instead of an endpoint for a generic database querying frontend, and so on) while remaining mostly impervious to it. This will not last long - the vendors de-facto ruling the web have every reason to shut it down (or turn it around and use LLMs against us). But for now, it works.

Adversarial interoperability is the name of the game. LLMs, especially combined with tool use (and right tools), make it much easier and much more accessible than ever before. For however brief a moment.

[makingstuffs]

Sorry it wasn't entirely clear that I was by no means saying the web in its current form is anything close to what it could/should be. My main point was that, by making backdoors for MCPs there will be a new possible entry point for bad actors by exploiting said backdoor.

As for the optimisation to _waste human life_ I do agree but the reality is that the sites which waste the majority of human life/time are the ones which would not be automated by the MCP and would, ultimately, see more 'real' usage by virtue of the fact that your average human will have more time to mindlessly scroll their favourite echo-chamber.

Then we have the whole other debate of whether we really believe that the VC funders whom are largely responsible for the current state of the web will continue pumping money into something which would hurt their bottom line from another angle?

[TeMPOraL]

Fair enough. Thanks for clarifying. I agree with what you're saying in this comment.

On the topic of:

> whether we really believe that the VC funders whom are largely responsible for the current state of the web will continue pumping money into something which would hurt their bottom line from another angle?

No, I don't believe that at all - which is why I keep saying the current situation is an anomaly, a brief moment in time. LLMs deployed in form of general-purpose chatbots/agents are giving too much power to the people, which is already becoming disruptive to many businesses, so that power will be gradually taken away. Expect less general-purpose AI agents, and more "AI powered features" that shackle LLMs behind some limited UI, to ensure you can only get as much benefit from AI as it fits the vendors' business strategies.

[jedimastert]

Most thing that do this kind of fingerprinting bot detection aren't looking for a browser that's pretending to be a human, they're looking for other programs that are pretending to be a browser.

[m11a]

> Do we suppose they will just create a backdoor to allow _some_ bots in?

That, and maybe they will as CF seem quite big on MCP.[0] Or people just bypass the bot detection. It's already not terribly difficult to do; people in the sneaker bot and ticket scalping communities have long had bypasses for all the major companies.

I mean, we can all imagine bad use-cases of bots, but there's also the pros: the internet wastes loads of human time. I still remember needing to browse marketplaces real estate listings with terrible search and notification functionality to find a flat... shudders. Unbelievable amount of hours wasted.

If fewer people are able to build bots that can index a larger number of sites and give better searching capabilities, for instance, where sites are unable to provide this, I'm personally all for it. For many sites, it's that they lack the in-house development expertise and probably they wouldn't even mind.

[0]: https://developers.cloudflare.com/agents/model-context-proto... etc