Greg Isenberg and developer Vinny break down WebMCP, the experimental browser feature that lets any AI agent search, compare, and buy on a website without scraping the page, then price two startup ideas built on it.
Posted
1 weeks ago
Duration
Format
Interview
educational
Views
89.9K
1.3K likes
57 · 43
Big Idea
The argument in one line.
WebMCP lets a website expose a short list of typed, agent-callable tools inside the browser itself, so any AI agent a visitor already uses can search, compare, and buy without scraping the page or handling API keys.
Who This Is For
Read if. Skip if.
READ IF YOU ARE…
A founder or agency operator looking for a productized service to sell right now, not just a technology to research for later.
A technical builder curious about the actual mechanics of browser-native agent tools, past the buzzword.
Someone running a complex product catalog, like configurable machines or gear, where customers already struggle to compare specs and compatibility.
SKIP IF…
You want a finished, ship-today API — WebMCP is an experimental Chrome flag behind remote debugging, not a stable production feature yet.
You want a no-code walkthrough — the demo assumes comfort reading registered tool definitions in code.
TL;DR
The full version, fast.
WebMCP is an experimental Chrome feature from Google and Microsoft that lets a website register a short list of typed tools an AI agent can call directly inside the browser, instead of the agent scraping the DOM or holding API keys. The browser session itself is the auth layer, so tools can be conditional on login state with zero token management. Vinny demos it live on an espresso-gear store where an agent compares machines, matches accessories, and checks out with a coupon, and the two frame it as the middle ground between headless APIs, computer use, browser MCP, and in-app agents. The best early fits are complex commerce, SaaS admin consoles, read-only flows in regulated industries, and internal tools. Two businesses fall out of it directly: a WebMCP conversion agency that makes boring local-business sites agent-ready for a setup fee plus retainer, and an agent mystery-shopper service that audits how well a site's agent journeys actually complete.
Free for members
Chat with this breakdown — free.
Sign in and you get 23 free chat messages on us — ask for the hook, quote a framework, find the exact transcript moment, generate a markdown action plan. Bring your own key when you want unlimited.
Greg previews the episode's money claim and hands off to Vinny to explain WebMCP.
02:28 – 07:22
02 · WebMCP Clearly Explained
Vinny defines WebMCP as MCP moved into the browser UI and demos it against his own espresso-gear shop, where comparing machines and accessories was previously a manual slog.
07:22 – 09:11
03 · Demo: Conditional Tools And Browser Session Login
The agent's available tools change with login state because the browser session itself is the authentication layer, removing the need for API keys or tokens.
09:11 – 12:12
04 · The Agent-Native Paradigm
Vinny maps four ways an agent can reach an app: headless API/MCP, computer use, browser MCP, and in-app agent, and places WebMCP in the middle of that spectrum.
12:12 – 16:05
05 · How Agents Interact with Apps
The two argue consumers are heading toward one personal agent used everywhere, which makes in-app agents a transitional stopgap rather than the end state.
16:05 – 18:42
06 · Demo: Accessories, Cart, And Coupons
A second live demo shows the agent finding compatible accessories, adding one to the cart, and applying a coupon in one continuous request using the store's order history.
18:42 – 21:03
07 · Where WebMCP fits
Vinny lists six early-adopter categories: compatibility-driven commerce, config-heavy SaaS admin, regulated industries, government/civic services, legacy internal tools, and accessibility.
21:03 – 24:27
08 · Startup Idea 1: WebMCP Conversion Agency
Greg pitches an agency that makes boring local-business websites agent-ready for a setup fee plus a monthly monitoring retainer.
24:27 – 26:11
09 · Startup Idea 2: Agent Mystery Shopper
Greg pitches a recurring audit service that runs an agent through a business's key user journeys and reports exactly where it fails.
26:11 – 28:58
10 · Closing Thoughts
Vinny points to his open-source demo repo and the two agree that betting on an experimental feature early is exactly where the opportunity is.
Atomic Insights
Lines worth screenshotting.
WebMCP puts MCP inside the browser itself: a site registers a short list of typed tools an agent can call, instead of the agent reading the whole page like a human would.
The browser session is the auth layer: log in and the full WebMCP tool list appears, log out and only three tools remain, with no API keys or tokens involved.
SEO asked if Google could understand a page, AEO asked if AI could cite the answer, and WebMCP asks whether an agent can actually finish the task.
Headless APIs and MCP servers keep an agent working blind, with no visible UI, and put the full burden of managing tokens and credentials on the agent side.
Computer use and browser MCP are both slow and fragile because the agent has to screenshot or parse the entire DOM just to figure out what to click.
In-app agents lock a user into the vendor's own bot and force the vendor to manage every token and setting, the exact complaint behind the 'I don't want your product's agent' sentiment the hosts reference.
WebMCP sits in the middle: the vendor exposes agent capability without owning an agent, and the visitor keeps using whatever agent already holds their context and memory.
Regulated industries are a strong early fit because WebMCP tools can be read-only and run inside an authenticated, human-watched session, somewhere a classic API key is structurally a non-starter.
Internal tools are the lowest-risk place for a founder to try WebMCP first, wiring it up for the team before ever exposing it to customers.
WebMCP launched in February as a joint experimental effort between Google and Microsoft, and using it today still requires enabling a Chrome flag plus remote debugging.
A WebMCP conversion agency can charge $2,000-$10,000 for a v1 setup on a 'boring' local-business site, plus $200-$700 a month for ongoing monitoring and evals.
An agent-mystery-shopper service runs an agent through real user journeys, like buying a hoodie or filing a claim, then sells the business a recurring report on exactly where the agent got stuck.
The two startup ideas pair naturally: a mystery-shopper report showing where agents fail becomes the sales pitch for the conversion-agency implementation work.
Vinny open-sourced a working WebMCP demo, an espresso-gear store with 16 registered tools, so anyone can clone the repo and read the actual tool definitions.
Takeaway
How To Make Your Website Agent-Ready
AGENT-READY WEB
WebMCP lets a site hand any agent a short list of typed tools instead of API keys or DOM-scraping, and two productized services built on it are sellable right now.
02WebMCP Clearly Explained
WebMCP puts MCP's structure inside the browser: the site registers a short list of typed tools (search, compare, buy) instead of the agent scraping the DOM.
The distinction worth holding onto is SEO (can Google read the page) vs AEO (can AI cite the answer) vs WebMCP (can the agent actually finish the task).
A complex product catalog, where comparing specs and compatibility is genuinely hard for a shopper, is the clearest sign a site needs this.
03Demo: Conditional Tools And Browser Session Login
Because WebMCP tools run inside the browser session, login IS the auth layer: log in and the full tool list appears, log out and it drops to three tools, no API keys or tokens involved.
That removes the biggest technical hurdle of MCP servers and APIs, managing credentials, which is why WebMCP is described as the least technical way to make a product agent-native.
The tradeoff is scope: the agent can only do what the site's registered tools allow, nothing more.
04The Agent-Native Paradigm
There are four ways an agent can reach an app today: headless API/MCP server, computer use, browser MCP, and in-app agent. WebMCP sits in the middle of that spectrum.
Headless and browser-MCP approaches are slow or fragile because the agent has to read the entire page structure to figure out what to click; WebMCP hands it a clean list of callable actions instead.
In-app agents work but lock the user into the vendor's own bot and force the vendor to own the tokens and setup; WebMCP lets the visitor bring whatever agent they already use.
05How Agents Interact with Apps
The bet is that within 24-36 months most consumers carry one agent everywhere and expect it to keep context across every tool they touch, rather than adopting a different bot per app.
In-app agents were a transitional stopgap while the web wasn't agent-ready yet, not the end state.
In-app agents still make sense when a company wants to gate an agent to a narrow, low-risk task set it can't be trusted to expand beyond.
06Demo: Accessories, Cart, And Coupons
The agent already has account context (order history, cart, coupons), so it can chain a multi-step task like finding compatible accessories, adding one, and applying a loyalty coupon in one request.
The pain WebMCP solves is real: matching parts across products that use different sizing conventions is exactly the task shoppers currently solve by pasting specs into ChatGPT by hand.
07Where WebMCP fits
Six early-adopter categories stand out: compatibility-driven commerce, config-heavy SaaS admin, regulated industries, government/civic services, legacy internal tools, and accessibility.
Regulated industries matter because WebMCP tools can be read-only and run inside the authenticated, human-watched session, something a classic API key structurally can't offer.
Internal tools are the lowest-risk place to start: a founder can wire up WebMCP for their own team before ever exposing it to customers.
08Startup Idea 1: WebMCP Conversion Agency
The service: audit a boring local business (law firm, HVAC, med spa, dentist) and ship v1 tools like request-a-quote or book-a-consult.
Suggested pricing: $2,000-$10,000 setup plus $200-$700 a month retainer for monitoring and evals, scaled to the client's size.
Package it as a broader agent conversion agency (MCP plus WebMCP plus internal tools) rather than a single-technology pitch, since the value is being the first-mover expert, not one spec.
09Startup Idea 2: Agent Mystery Shopper
The service: run an agent through a business's real user journeys, buying a product, booking a consult, filing a claim, and report exactly where it got stuck.
Price it like a recurring audit, roughly $100 to a few hundred dollars a month, and turn the repeated fixes into reusable software over time.
Pair it with the conversion agency: the mystery-shopper report showing where agents fail becomes the sales pitch for the implementation work.
Glossary
Terms worth knowing.
WebMCP
An experimental browser feature, launched by Google and Microsoft in February, that lets a website register a short list of typed tools an AI agent can call directly, instead of the agent scraping the page.
MCP (Model Context Protocol)
A standard way for an AI agent to call external tools through a dedicated server, which typically requires the agent to hold API keys or tokens to authenticate.
Browser MCP
An approach where an agent reads a website's full DOM (the underlying page code) to figure out where to click and what to do, similar to computer use but working from code instead of screenshots.
Computer use
An agent capability where a bot controls a real computer, taking screenshots and clicking on-screen like a human would, which is slow because every action needs a fresh screenshot.
In-app agent
An AI assistant built directly into a product by its own vendor, such as a chat sidebar, that can only act within that one app and requires the vendor to manage its setup and credentials.
AEO (Answer Engine Optimization)
Optimizing content so an AI system will cite it directly as the answer to a query, treated here as the successor to traditional SEO.
Conditional tools
WebMCP tools that only appear to an agent based on browser state, such as being logged in, so a logged-out visitor's agent sees fewer available actions than a logged-in one.
Resources
Things they pointed at.
26:29toolCrema & Co. — WebMCP espresso-gear demo store (clientfly.dev)
“AI agents are about to become a new kind of visitor on the Internet, and I think billions of dollars of wealth will change hands in the process.”
cold-open thesis with a bold, specific prediction→ TikTok hook↗ Tweet quote
01:44
“It's MCP, but in the UI, in the browser.”
the whole concept in one clean sentence→ IG reel cold open↗ Tweet quote
05:37
“If you think about SEO, it was like, can Google understand the page? And then we had AEO, which is can AI cite the answer? And now we're entering this WebMCP era, which is basically, can the agent finish the job?”
a three-step framework people will quote as a soundbite→ newsletter pull-quote↗ Tweet quote
13:12
“WebMCP is like this really nice middle ground where you don't have to pay for tokens.”
tight cost argument for why WebMCP beats an API integration→ IG reel cold open↗ Tweet quote
21:31
“The big idea is how can you make boring business websites agent ready?”
frames startup idea 1 in one line→ TikTok hook↗ Tweet quote
27:29
“I love playing when things are experimental because the arbitrage exists when it's experimental.”
the first-mover thesis stated plainly→ newsletter pull-quote↗ Tweet quote
Topic Map
Where the conversation goes.
00:00 – 07:22denseWhat WebMCP is and how it differs from MCP
07:22 – 09:11denseLive demo: conditional tools and browser-session auth
09:11 – 16:05denseMapping the agent-native landscape, headless to in-app
16:05 – 18:42steadyLive demo: accessories, cart, and coupons
21:03 – 26:11denseTwo startup ideas: conversion agency and mystery shopper
26:11 – 28:58steadyWhy bet on an experimental Chrome feature now
The Script
Word for word.
Read-along
Don't just watch it. Burn it in.
See every word as it's spoken — crank it to 2× and still catch all of it. The same dual-channel trick behind Amazon's Kindle + Audible.
17px
metaphoranalogy
Think about this. AI agents are about to become a new kind of visitor on the Internet, and I think billions of dollars of wealth will change hands in the process. Because millions of AI agents are gonna be browsing and buying on the Internet, but the Internet isn't designed for them to do that.
And that creates a really interesting question, which is what does an agent ready website or app look like, and how do you actually build one? Well, there's this new little thing by Google called WebMCP, and I'm honestly surprised more people aren't talking about it.
The simple idea is that websites can expose cleaner actions for AI agents. So instead of an AI agent trying to figure out a page like a human being, the site can basically tell an agent, here's how to search, here's how to book, here's how to buy.
So today, have my friend Vinny come on and just clearly explain what WebMCP is, how it differs from MCPs, why it matters, where the opportunities lie, and I give you two startup ideas that I think could cash flow that you can start today.
Enjoy the episode. I hope it gets the creative juices flowing. And if you haven't liked, commented, subscribed, what are you doing?
This stuff should be paid. We make it free. I just wanna see you win.
Let's go, and I'll see you at the end of the episode.
Thank the MRR gods. Vinny is back on the pod to explain something very, very, very powerful.
WebMCP, Vince, you you actually brought it to my attention. Vinny, by the end of this episode, what are people gonna learn?
Hi. They're gonna learn how to use WebMCP,
which is kind of exactly like it sounds. It's MCP, but in the UI, in the browser. And this is like a brand new experimental feature from, um, Google and Microsoft.
So I really think this is a first mover advantage here. So if you can learn this stuff, you're really bringing, um, you're getting the skills that you need to bring stuff to market that is emerging, that's going to probably be the next big trend. So I think this is a really cool thing.
So Vince is gonna actually explain to you in a clear way what WebMCP
is, how to use it. And at the end of the episode, I'm gonna share with you two startup ideas, cash flowing startup ideas that I think could use WebMCP that you can build today.
That'll be at the end. Vince,
you start them off. Alright. Cool.
So let me start from, like, a problem I had myself. When I heard about WebMCP, the first thing that came to mind is this shop that I've got here.
It's an espresso machines and gear shop. So I was buying an an espresso machine, and it has, like, a lot of specifications.
It's got a a lot of gear and accessories. And figuring out which one's right for me, um, and also which accessories fit was kind of a pain.
So it was a lot of back and forth, googling, also putting stuff into, um, an agent or ChatGPT or whatever. And, like, does this fit?
Will this work? So I thought, oh, cool. This is a great, um, use case for something like this where we can build a shop with WebMCP tools in it that your agent can talk to.
So you can bring any agent that you're using, which is whether it's, like, Claude Code or ChatGPT, Cowork, whatever these, um, whatever agents are out there, maybe GrokBot, and you can talk to the website and ask its stuff.
So, uh, let me just show an example real quick. And, um, so I wanna upgrade from my current MaraX machine, and I wanna get one that's able to make two flat whites a day easily and fits on my counter space, which is about 32 centimeters wide.
By the way, in simplest like, in the simplest form, correct me if I'm wrong, Vince, but WebMCP
is basically just websites with agent buttons. So you're we're making websites agent readable and agent
actionable. Is that right? Exactly.
And it's not like this wasn't available before, but it was available in a lot, like, clunkier way. So you've got computer use or you've also got agents that can, uh, kind of browse and use a browser and and go through websites, click buttons. But before they had to do it in a very not so efficient way.
So they're they're getting the entire DOM, which means they're getting all the code from the website. And they're, like, scanning through it and finding where to click, taking screenshots and stuff. But look at that what just happened right here on the screen.
It manipulated the the website, was able to find two machines, put them side by side, and then it highlighted, really cool feature, highlighted what features or what specs about the machines fit my request that I just had.
So it's like the porta filter fit, which is, um, going to fit, like, an accessory you have. And then will it make the two flat whites like you asked?
And does it have the right width? Will it fit on your counter spot? So, like, that's really cool.
And before, to do all that, well, first of all, it wouldn't be able to manipulate a page in this way as easily. And, also, it'd have to go through all this scanning, all this code reading.
Whereas this, now with WebMCP, there's a set of tools like the ones that are just popping up on the screen here. And, um, those are the ones that you make available to the agent.
So it gives it a really, uh, efficient, concise list of things that it can do on the website, and it knows how to do that, and it can just do it easily. And and you can do some really cool creative stuff with this.
Yeah. And I think, like, one of the reasons I think this actually matters is if you think about SEO, right, it was like, can Google understand the page?
And then we had AEO, which is can AI cite the answer?
And now we're entering this WebMCP era, which is basically, can the agent finish the job? And we're what we're learning is that websites aren't really optimized, and I think that's why Google and and Microsoft decided to build this thing.
Right? Because they don't want a broken Internet to exist. Mhmm.
And I think as, like, a founder, like, why does this matter? It's because there's there's, you know, billions billions of dollars changing hands on these tools.
Right? Or on the Internet. And if we can optimize some of these websites, you know, there's just there's a lot of opportunity.
Yeah. And I think I mean, maybe the people like you and I and the people listening, they're more agent native or they're more this kind of early adopters of new technology.
But we have to remember that the web has been around for a while. People are used to UIs and browsing websites and stuff like that.
And people don't really want to the majority of web users don't want to use just like a CLI tool or or an agent in the terminal like this. They wanna be able to interact with something visual.
So, um, this web MCP really makes it the best path to do that.
So we'll really allow for kind of, um, normal the average consumer to adopt agent tools. So it's kind of like meeting them in the middle, right, with the new agent technology and the stuff that they're used to. Cool.
What else do we need to know about it? Um, so, like, one of the big things is, um, like I said, is that it's not, um, scraping and parsing the entire DOM. So it doesn't have to it's more efficient in the way it works.
But the other thing that's really cool is that these tools, you can make them conditional. So, like, you see here in this list, we have tools that are always available versus logged in. This is all happening through the browser session.
Right? So I've logged in. You can see I'm up here.
I've logged in. These are the tools available. And if I log out, well, then we'll see there's only three tools available now.
Right? So this is really cool because, one of the big hurdles to doing other kind of agent native, um, approaches like an MCP server or, um, an API is that you have to deal with, um, tokens, credentials, people sending sending their their identity through, you know, API keys and tokens and things like that.
Whereas this, you just log in. Right? So I can log in with my username and password, and it has access to the entire browser session there.
So the fact that I'm logged in, the agent has to doesn't have to do anything special. Uh, we don't have to connect an MCP server and authenticate and all that stuff like you have to do with, you know, a typical MCP server or with an API or things like that. So it's like the least technical, uh, approach to making an app or a website or a web store agent native, um, but with the most flexibility and the most features.
So this conditional tool calling, all this stuff just happens because of the browser state. And that's a really nice thing. Yeah.
That's really cool. That's just like built in. Because they they I mean, it makes sense.
Right? Yep. It's using the whole browser session.
So that's really nice. Alright. So, um, I saw this tweet the other day and I've seen this going around a lot where people are saying, I don't wanna use your product's agent.
I want my agents to be efficiently enabled to use your product. And that's exactly what we're getting with WebMCP and especially for things like web stores and stuff like that, um, for ecommerce, um, or maybe even, you know, other examples that we'll look at later that you that you have, uh, prepared for us.
So, um, this is this is a sentiment that's going around on Twitter a lot lately. And, um, what does Dylan from Cloudflare mean by this? So we have these, like, different ways an agent can meet an app.
Right? And let me go zoom in real quick because we have a lot of them. And they're going from headless.
You see at the bottom here, it says headless. Um, so basically, running an app via your agent without ever seeing the app.
That's what headless means. Right? There's no app in the browser.
There's no website. So you bring your own agent. You can hit a raw API.
But there's, like we said, there's lots of things, uh, you have to deal with authentication, and the agent has to hold an API key and things like that. But then you can bring your own agent and you can use MCP, which is a typical, um, MCP server.
But that's another layer on top of your app's back end. And then your agent can't manipulate the UI, right, like we just saw.
So those are completely headless ways. They're little add a little bit more complexity to your to your app or to your product. Now we have computer use, which is where the the bots or the agents literally have a computer that you they can use, whether it's your local computer or a computer in the cloud, and they're running through screenshotting stuff and clicking stuff on the computer, on the UI like, uh, you would.
And, um, this isn't really the most efficient because of, like we said before, you've gotta go through, you've got a screenshot, or the agent has to screenshot all this stuff. So this is slow and fragile at the moment. We have browser MCP, which is similar to computer use where, like, we were talking about where you get the whole code from the website, and it has to kind of figure out through the HTML code and where it can click and what it can do.
Again, that's a little bit more fragile. WebMCP kinda comes now to be somewhere in the middle of that or the things we just mentioned and an in app agent, which is what the tweet was complaining about.
Right? Which is that, like, you build an app with a little agent sidebar, and your, um, the agent in that app is the only thing that can communicate and deal with it.
Right? So what they're saying is they want something where they can bring their agent and and they can use your product efficiently.
And that's where I think, especially for traditional apps with a u, uh, front end, uh, storefront, whatever that they can then use, bring their agent and use your app efficiently.
So that's what's really cool about it. Does that make sense? So
if I'm getting this right, so WebMCP, you've got your agent. There's a set of tools or things that you can do basically on the website or the app.
And then and it's sort of limited to that. Exactly. The in app agent, you have your you know, the the the vendor's agent and the app's agent.
Right? And that just interfaces with the app's logic and data back and forth.
Mhmm. And the app is like isn't that, like, the the best end state of of where we think things are going?
Right?
The in app agent, you mean? Yeah. Well, I mean, you can look at it from two different perspectives.
Right? That, uh, it's nice to have, a little, um, in app agent there. But, um, you're responsible then for configuring everything.
You're responsible for the tokens. Right? You're responsible for setting it all up.
Whereas with WebMCP, WebMCP is like this really nice middle ground where you don't have to work you don't have to pay for tokens. You're giving the app agent capabilities, but the user is bringing the app the agent that they used, and any agent will work with it.
So if we're moving quickly to this world where everyone has an agent that they use at work, that they that they use for personal purse preference, you know, um, you don't have to then separate them from that.
That's the agent they know, and they can just use it with your tool via WebMCP. So it's kind of like the nicest because it makes it easy for you, and it makes it most comfortable for them. Yeah.
I guess the in app agent was sort of like a transitionary
piece of software that needed to exist for a certain amount of time, but we're, like, kinda growing out of it.
Like, the idea of, like, you know, use, you know, Intercom Fin, right, which is basically, like, I think, a customer support agent. Mhmm. Mhmm.
Like, that experience is really, really good. Mhmm. But now in a world where it's pretty clear that over the next twenty four, thirty six months, everyone consumers are going to have their own agents.
It just makes sense that these agents are gonna need places to interface with Yeah. The Internet at large, and the Internet is just not designed for those agents yet.
So, you know, that's why WebMCP,
know, exists. Yeah. I think there is a place for in app agents.
Right? Like, if in Notion, for example, they offer both. But, like, if there's something that is, like, Cloudflare dashboard, they have an in app agent.
And this is so it's, like, very it's gated to only use their, um, their tools and not to change preferences too much so that you don't do anything kinda hazardous. I can see where in app agents might make sense, but we're moving into this world where it's like we're doing so much with agents and we want them to keep their context.
So you want one tool that kinda has the context and knowledge and memory of everything that you do and to be able to bring that one agent with all that context to different tools is really powerful. And I think that's where you're gonna see people. They're gonna kinda get stuck on one agent, one kind of agent products, whether that be Grokbot or Claude Cowork or, uh, ChatGPT work or whatever.
And then they're just gonna kind of access the Internet and and interface with the with different things on the Internet through those agents. So that's where I think WebMCP is really powerful. It's also just like a great companion for when you're shopping with for, uh, complicated things.
You can use an agent if you need to kinda help you out, figure out which specs were things right. And, um, you don't have to build in this big bloated, you know, in app agent into your into your app to get some better, uh, customer,
um, experience for you. Can you show an example? Another example?
Yeah. Sure. So I could say, like yeah.
So you suggested the Lilith Bianca. What are some really nice accessories I should add that will fit the Lilith Bianca? So this is something that, like, bugged me a ton was I found the machine.
Now I need a grinder. Now I need the right porta filter. I want a new basket.
They're all different sizes. They all use one might use a measurement. One might use a name or or some kind of, like, brand name.
And parsing through all that information as a customer can get really tedious. So just to have an agent that can do that and then let you know is perfect because it has all the context here from the store. It knows what I've ordered.
It has different tools here. Like, I scroll over here, it can see get my gear is one tool, so it knows what I've ordered from here.
It can get the cart. It can add coupons. Right?
So it can apply a coupon on checkout and all this stuff. So here, it's just saying the first thing you should buy is this Lalit water softener two pack. So I'll just say, cool.
Add that to my cart. That sounds great. Right?
So the nice thing is is that I could tell it highlight that on the UI or I can just say, you know, whatever. I I like the sound of that. Go and and add it to the cart and it'll do all that stuff in real time and I have visual confirmation of that.
I can see the things. Right? And
I think that's pretty cool. That's really cool. I mean, come on.
That's really cool. Yeah.
So and even tell me here, you have softener is in. Uh, you have a barista 10 coupon, 10%, adding it for the rest.
So
I don't know if it's just because I'm a coffee aficionado. You know? I love coffee.
You know? You can see my coffee setup back there. Yep.
That this is just hitting for me so hard. But, like, to me, it's like it makes so much sense. Like, we're as customers, we're gonna be using agents.
We're gonna want them to go and do stuff for us. We wanna make sure that the things that they do, it actually is able to complete the tasks.
And to see this work just so seamlessly just is awesome.
Yep. Yeah. It's really cool.
I think so this is a great example, but you can think about anything where it kinda gets complicated. You know, technical stuff, if you're buying hard like hardware and, I don't know, you need to, uh, you're doing, like, hardware hacking and you need the right the right battery for for the, uh, development board or car stuff and you need the right parts.
Like, all this stuff that can be really complicated like that, this is a great use case.
I mean, I'm just curious, you know, where MCP in your mind, where MCP fits, which I think is, like, another way of saying, you know, how do you like, in which sectors, niches should you be implementing WebMCP?
Because there's gonna be like, some some industries are gonna be last to implement it.
Right? And I think from a founder perspective, I care about the the ones that have the highest priority.
So which are those and why do they matter? Yeah.
Yeah. I think, like like I said, these compatibility driven commerce.
Right? So it's like all those things, camera systems, any kind of web web store that's complicated, that will be a great thing. Um, you could do it in SaaS admin.
So, like, any kind of admin board or console or analytics or marketing tools, you can add these things in to make it easier for, you know, your marketing team to to deal with these things and and set up features and stuff like that. And even, like, regulated industries, like, the nice thing is is that you can't use API keys.
So you don't wanna go to you don't really wanna use MCP servers or APIs. You maybe wanna set up a few and that's a great thing about WebMCP. It's like a few tools that are using the browser state that can can be read only so they don't actually touch anything.
So let's imagine, like, insurance or banking self-service. Like, you could set up some WebMCP tools that are read only or only, uh, touch very nonsensitive settings, and then that will help the user figure out where they need to go to enter something or where they need to to go to to get the right information or it can even, uh, summarize and and pull the right information for them via their agent.
So stuff like that. I even think, um, internal tools.
So building internal tools at a company. So if you're, um, like, a a entrepreneur, you don't necessarily need to use web MCP right away for your customers.
And there might be a really great solution for you in house, like your internal tools, stuff for your for yourself, for your employees. That's where I think there's a lot of potential.
I love it. Alright. Let's let's go to some business ideas that people can implement.
I'm curious your take on it too. So let me share my screen. Yeah.
Alright, Vinnie. So web m WebMCP is here.
I wanted to come up with two business ideas that I think are cash flowing that I think are anyone nontechnical can set up or or somewhat nontechnical. You just don't need to be, like, a hardcore engineer.
The first idea is a WebMCP conversion agency. And I bet you there's probably some domains that are available like webmcp.agency or something like that that someone can go and grab right now.
So the the big idea is how can you make boring business websites agent ready? So you have these boring businesses like law firms and home service and HVAC, you know, med spas, dentists, and you just go and create these, you know, v one tools for them.
So that can be like requesting a quote or booking consults, and you're just selling them on this idea that that there's gonna be a new class of citizens on the Internet.
These are gonna be these AI visitors. And these AI visitors, these agents are going to book jobs. Right?
So you sell them on maybe a 2 to $10,000 setup, and then you charge you know, it could be $500 a month or a few $100 a month, $700 depending on who it is. Is it a big law firm, a small law firm?
On monitoring and evals, and then you you build this retainer that, you know, is building cash flow every single month, and you just update it and that sort of thing.
What do you think of this idea? Yeah. I I actually think it's a really good idea.
I see stuff on the web floating around where they're showing that things like you said of dentists or law firms are starting to use agents at their offices.
And so I think they'll get it. And it's good, uh, that you bring this up because I think it's worth mentioning that WebMCP is an experimental feature in Chrome right now. So it launched in February, joint effort from Microsoft and Google, but it's still in early days.
But that's why I think there's real potential here because we talked about this package. I showed the diagram of, you know, from headless to, um, bound to UI, the different types of agent native, uh, approaches you can use to, um, connect to apps.
Right? So you could do this as a package where, um, it's not only WebMCP but other tools, maybe a MCP server for them. And you tell them that, like, look, this is new emerging stuff or you're learning this because it is this new emerging stuff so that when it does get adopted, you're the first mover.
You have the first mover advantage. And so you can sell it as a package. Like, we'll we'll put in MCP.
We'll put in WebMCP. Mhmm. We'll we'll create, you know, whatever.
All of this stuff that that aligns with their vision, you can make whatever they want available, and you can show them the different approaches. You have the one that uses a a UI, one that is headless, and you you're the expert there and that's the way that you, uh, make money.
Yeah. Maybe it's just agent conversion agency. And then WebMCP is just one of the the technologies that you use.
Yep. Or like we were saying before, internal tools, it doesn't only have to be about, uh, customer facing stuff.
You can show them how they can make processes in their office better for them and their employees using stuff like WebMCP.
Totally. Cool. Startup idea number two.
I'm calling it the agent mystery shopper. So it's testing whether agents can complete the most important user journeys.
So if you think about a user journey, maybe it's a Shopify store, you you know, you wanna buy a hoodie. If it's you know, consulting company, it's booking a consult.
If it's an insurance company, you're filing a claim. Requesting quotes, you're ordering items, all these different things that you want the agent to do.
So the agent is gonna run a bunch of tests, and you, the customer, get a report back. Where did the agent get stuck?
Were there bad descriptions? Were there missing tools? Conversion risk.
And then you're basically selling, you know, agent reports.
Maybe it's monthly, weekly, and you turn the repeated fixes into software. So I like this business because it's pretty simple. It's almost like, you know, just a report, like a credit report almost on, you know, how your how your your website and your apps are around implementing things like WebMCP.
And then you can charge a few $100 a month or a $100 a month for something like this. What do you think about this idea? Yeah.
I think also a cool thing it makes a lot of sense. And the cool thing is is that you can even pair approaches like this to your agent conversion agency.
Right? So it's like you can go and run these agent tests and evals and you can be and you can show them that, hey, this might work better if you used WebMCP on top of it.
You're only using x. Why not check out this as well? So you can kind of combine the approaches with, uh, I think here.
So that's a really cool idea.
I like it.
Yeah. So I just also wanted to mention that, um, I showed a couple examples here, but there are 16 different tools that you can use with your agent via WebMCP on this example, espresso machines and gear store.
And you can do that right now. You can go to crema and co clientfly.dev.
We'll put the URL in the show notes and stuff, and you can test it out there. One thing you should know is that, like we said, it's experimental stuff, early days. So go into Chrome flags, enable WebMCP support, and go into Chrome inspect and allow remote debugging.
So these are the things that you'll wanna, uh, enable so that you can start using these experimental features. And if you want to build your own app like this, you can also click on the, um, GitHub repo button down there next to the WebMCP tools pill, and you can clone this repo.
And you can play around with it, make your own version, whatever. It's free for you to start playing around with cool business ideas. So those are two important, uh, things I think are worth mentioning.
And, yeah, I'd be it would be cool to see what other people do with this repo, what other people do with these ideas. Um, so people should definitely share those online with us. I think that would be awesome to see.
Yeah. We'd love to see it. And I think, you know, I there's
I can just see the comment, uh, of someone saying, well, it's an experimental it's, you know, it's so experimental.
Like, it's so it's way too early. Like, why even bother playing with this stuff?
And I you know, you know me. I love playing when things are experimental because when you know, the arbitrage exists when when it's experimental.
Like, I would love trying things, getting my hands dirty, and and and seeing what I can build now. Because when it's gonna be, you know, super popular, that's when that window starts closing.
Yep. Definitely. Think about when ChatGPT came out or when GPT, I think it was GPT two and three came around and people were playing with it and going, it was just two years before ChatGPT launched and people were going, this is crap.
This is we're way off. We're years away from AI being like a serious thing or serious tool. And then boom, the explosion happened just a year or two later.
So, like, shouldn't pass this stuff off as, you know, just, like, experimental stuff that's not going to get implemented. I mean, we're talking about Google here. They have pretty good foresight.
This is something that they've been talking about for a few years now. They made the proposal two years ago. They launched it the beginning of this year.
So I wouldn't I wouldn't fade this personally. And I'm excited about it. So that that's enough for me.
Alright. Thanks for coming on, Vince. Sharing.
Bring the sauce, and I'll see you next time. Yep.
The Hook
The bait, then the rug-pull.
Greg opens with a bold claim: AI agents are about to become the internet's newest customers, and billions of dollars will move because of it. Vinny then walks through WebMCP, the actual browser feature making agent-native websites possible today, live on a real store.
Add Modern Creator as a preferred source and Google shows you more of our breakdowns in Search, Top Stories, and AI Overviews. It only changes what you see, and you can undo it in your Google settings anytime.
Add to Preferred SourcesOpens your Google source preferences with us pre-loaded. Tick the box and you're done.
A solo walkthrough of five open-source GitHub repos getting traction right now, an AI writing editor, an agent-run CRM, a video-editing agent, a skill security scanner, and a phone-controlling harness, each with the exact install command and the first small workflow to try.
Cloudflare quietly built the payment rail for AI agents to pay tiny fees for web resources, and that rail is about to spawn a whole generation of businesses selling clean data, agent-readiness, and packaged expertise.
Cody Schneider maps the exact infrastructure — pipeline, warehouse, agent — behind a Facebook ads system that researches, creates, publishes, and kills its own losing ads.
Nick Vasilescu spins up an AI co-founder running on Grok 4.5 and, in one live session, takes it from idea to landing page, thumbnail, and cold-email sequence.
Greg Isenberg names the role he thinks AI agents are about to make the most valuable job in tech, and hands over the folder structure, tool stack, and 30-day plan to become one.
00:22
00:47
01:14
01:33
01:47
02:24
02:59
03:20
03:41
04:02
04:23
04:44
05:05
05:26
05:47
06:08
06:29
06:50
07:11
07:54
08:16
08:38
09:00
09:44
10:07
10:30
10:52
11:15
11:38
12:00
12:22
12:43
13:26
13:47
14:08
14:29
14:50
15:12
15:33
15:54
16:38
17:01
17:23
17:45
18:08
18:30
19:17
19:40
20:04
20:27
20:51
21:37
21:59
22:22
22:45
23:07
23:30
23:53
24:15
24:58
25:19
25:39
26:00
26:37
26:55
27:30
27:42
28:03
28:26
28:51
24:43
34:10
Video of the Day37:47
Video of the Day56:00
26:03
35:18