Loading summary
Transcript1 lines
- [00:00]
A
Welcome to the podcast. Just yesterday I released an episode where I said that I have created a tool, an MCP, with my company, AI Box, that gives Claude the ability to generate Images, it gives ChatGPT the ability to generate video once Sora dies. And I'm going to have to use Google VO3 and it gives something like Gemini the ability to generate audio with 11 labs. So you essentially can take any of the main AI tools you use day to day. And I think Claude, Claude Cowork Claude code is kind of one of the most popular and you can put all of the other AI models inside of it. Now I had a lot of people asking me, number one, how MCPs work, what MCPs are, what the difference between an MCP and an API is. So I want to make an episode where I'm going to say some of the cool functionality that I've created with AI Box and some of the cool things I've learned on the journey there. But I'm also going to break down for anyone curious what the top MCPs are that you should be using with Claude or whatever AI tools and assistants you are building with and how these MCPs and APIs actually work, what the differences between them and how you can get the most out of them. So any just two seconds of background, I'm sure most of you know, but just to define the terms and explain what an API is, it's basically the way for one piece of software to talk to another piece of software. And the difference between an AI, an API and an MCP is that an MCP is basically a standard way for an AI assistant. You can think of something like Claude to basically discover and use tools, any apps, any files that are inside of a database or inside of a service. So an API, a lot of times, not always, it's kind of like, I guess a good analogy for this is kind of a universal adapter, right? So every country in the world has a different outlet plug that's kind of like an API. It's kind of like a very specific way to use their software. And an MCP is more like a universal adapter that will fit into any of those plugs. Because the way an MCP works is it's basically kind of like a Documents page. It's basically an explanation to something like Claude of all of the ways that your API or, or all of the ways your software operates and how you can interact with it versus like an API was like very structured, very rigid. And as an example from something I've built, you know, I recently built a tool that helped me with posting some of my podcast episodes. But I have three different podcast distribution companies that I use. I use RSS.com, i use Acast, I use Art 19. All of them have APIs that help me with my podcast publishing. So a way for me to upload an episode to my platform and have it go and publish it onto one of those distribution networks. But the problem is every single one of those APIs, like, the way they work, the way that you integrate them into software is different. So what all of those companies do and what everyone has done with APIs, they've always kind of published a documents page that explains how you structure your API calls, how you have to give them code, how they'll give you code back, and if you have anything wrong in that code that you send them, you get back, it crashes and breaks and the API doesn't work. So it's been pretty, you know, it's frustrating and a lot of times when I was first building with tools with Claude and building, you know, that particularly that use case, that podcast distribution tool that I created, I would literally say, hey, Claude, here's my API, which I'll tell you why that's a bad thing in the future. But I'd say here's my API key and here is a link to their documents page. Read this entire page of context pages and pages to figure out how the heck their API works to integrate it. And it still wouldn't work all the time. We'd have to do tons of tests. Sometimes I have to get on with their customer support and they'd have to look at what I was doing and looking at my code errors and Claude was telling me stuff and anyways, nightmare. So then we have a beautiful, you know, solution which is an mcp, which is basically they give you a link that you can give Claude that thoroughly helps it understand how your API works. And newsflash, MCP is also leveraging an API a lot of the time, but it's basically the universal adapter to explain to the AI agent how to successfully use these APIs, and it's a standardized way to do it. So, so now instead of struggling with an API and trying to figure out how to work with a software, you just give the MCP link to your AI agent and it will figure it all out for you. You don't have to finic anything anymore. And it's really easy to set up an mcp, by the way, in Claude and I, I didn't really realize this. I Think a lot of us have probably done this before with Claude or with Chat GPT where you go to the connectors panel, right? And it shows you like, hey look, here's like 20 different softwares that integrate with Claude or with ChatGPT or Gemini. And I, I'll be honest, like when I first saw all of the list of connectors on Claude, I was kind of disappointed. I'm like, oh yeah, there's 20 things here. I might use like three of them like Gmail and Slack and Google Drive. But like I don't really use all these other random things and there's tons of, you know, software that I like and I use, but it wasn't listed on there, right? Example, my, my email newsletter software, Beehive, like it's just not, you know, they didn't have that. And so Beehive actually went and created the very own mcp. And it's a link you can get, but it's not inside of the Claude connections, kind of, kind of like a store or whatever. So what you can do, it's actually super easy. You grab that link from Beehive, you click add your own connection, you paste that link in and it's going to have a pop up come up on your screen that asks you to log into your account on Beehive. Or you do this also with AI Box. So you put the AI box MCP link in as a pop up that says log your AI Box account. You log in just like it like a login with Google kind of thing. And all of a sudden that is how it authenticates. And now it knows that it has your login credentials and it's using those and it has this MCP link so understands how to interact with your software and you're off to the races at this point. You don't need to do anything. You don't need to mess around with APIs or figure out how anything works. You could just tell Claude, hey, go to Beehive and you know, help me figure out my analytics for my newsletter that I've been publishing. Or go to AI Box and build a tool that can help me automate generating thumbnails much faster. Just a PSA if you use Claude, Claude Cowork or Claude Code and you'd like to be able to work with all of the tools that you have. There's probably MCPs for all of the different software you use. You just have to go and manually connect it. You just have to go Google, you know, like Vercel, mcp, URL and you go get that and manually add it. So anyways, hope this was useful, honestly. It has 10x what I've been capable of doing with Claude. And so in the case of AI Box, what you can do with it, you go and add the AI box MCP URL, you go and authenticate and log in and then you're able to anytime you build like a tool on AI box, if you've built like an image generator or like a newsletter generator or you know, some sort of like audio or video generation, you know, creating ad assets like a tool, you know, you can build all these kind of no code tools on AI box with all the different AI models. If you've created something like that, you can go to Claude and say, hey Claude, I need to go and generate like 10 new images for my Facebook ad campaign for my product. X, Y, Z. Go and use my, you know, my, my box over on AI Box. And you say the name of the box to generate 10 new things and make sure that they have like this new direction or this new style or theme that we're thinking of or this new product. And it will go and access that box on AI Box because it has the MCP connection, it will generate your assets and then it will let you know and it give you links back to your assets where you can go of the images or videos or whatever you've created. Or if it's text, I think we might even pour it straight into your chat message so you can see it right there. So that's how it works with AI Box. I'm really super excited about it. And by the way, if you haven't tried out something like this, MCPs are really useful specifically if you have to do, you know, generations that have many, many different iterations. And so an example of this, I was recently creating a Bible study app and I wanted it so you could tap on any verse in the Bible and get it to, you know, like, give me, give me the background, give me the explanation, give me the context of this verse, like explain this verse to me. I feel like very often I'm reading something, have no idea what it's saying, right? And so what I did is I had Claude go and generate an explanation for every single verse in the Bible. Now the problem with that is there is like 30 to 45,000 verses in the Bible in the Old and New Testament. It is insane. And generating that takes a very long time. And I wanted these to be really high quality generations that talked about like the historical context and like all this stuff Right. So I had this massive project. I wanted Claude to do it. And the problem was I would say, like, hey, go do these generations. And it would be like, okay, it's going to take me like two days to do them. And I'm like, okay, you know, I just have to keep, like, clean. Continue, continue, continue every, like, couple hours when it does a new batch. The problem was sometimes my computer gets shut off. Sometimes the Internet would cut out. Sometimes Claude would just, you know, like, their connection would sever, their servers would sever, sometimes I'd hit a rate limit, whatever. There's a hundred different reasons why halfway through a generation of a batch, it would just crash. And what happens when it would crash is I would basically lose the entire generation. So it could be for an hour crash at minute 50, and I would lose, like half or all of everything it was generating. It was very frustrating. So what I'm able to do is go create a box on AI Box where it's. It's just like the MD file that you're giving Claude to do the project. And in fact, you can take that MD file and bring it over AI Box and just give it a prompt in the Vibe builder to create that tool. But I created a box in a box that can generate these verse descriptions. And then over on Claude, I say, hey, look, I need to go generate like 30,000 of these verse descriptions, use this particular box to do it. And a couple things. It's capable of doing a couple things. Number one, because it's running the processing on AI Box, you can, instead of having to wait two days for it to generate everything, it technically could open, you know, a hundred or a thousand or, you know, 20,000 instances of AI box and get to generate all of them in parallel at once. So, number one, that saves you a ton of time. Rather than having to wait for Claude to do it one by one, you could just have AI Box, you know, do a million of them in parallel. Not literally a million, but a ton of them in parallel. And number two, if it. If any of them crashes, or particularly if Claude crashes in the middle of any of these generations, AI Box still has all of your assets saved over there. So, you know, let's say like cloud crash, and it's like, oh, shoot, I crash. You're like, okay, great. Well, AI Box has them all generated. There's a Documents folder, there's a file section. Over on AI Box, you can actually go and access everything that has been created on any boxes or tools on Air Box. So nothing is lost in the case of a lot of my generations. And it's not the end of the world when it's, you know, trying to generate, like, some piece of text. But I was. I was doing something very similar with 11 labs, where I was generating, like, a whole bunch of Sleep History podcast episodes is a new thing I was trying. Someone in my studio wanted to. Wanted a new project. So we generated a bunch of sleep History podcast episodes. They're like, you know, they're like two to four hours long. And I had a ton of, you know, free credits from 11 labs that they were giving me, and they were worth, you know, thousands of dollars. And so I spent about $1200, unbeknownst to me, because I told, like, my. My AI generation tool to, like, go generate these podcasts, put them in a specific folder. I was using Claude, and it crashed. At some point in that generation, I had, like, an API, but it all crashed. And I said, you know, what's the status of it? And it's like, oh, shoot, yeah, we crashed generating all of these things. Your 11 Labs API crashed, and so we actually don't have anything saved. And I'm like, okay, well, how many, like, had we generated? I think it had got stuck on a loop or a glitch. Something happened, and it's like, okay, well, we actually spent about $1,200 of credits on 11 labs. But, yeah, it all crashed, and we don't have any of that. So that was a very painful experience to just lose $1,200 for no reason. I mean, for the crashes. And it was unrecoverable. If you had done that with AI Box, right? So created a box on AI Box that had an MD file, had an explanation of the type of, you know, the sleep history podcast that I was going to create. And you. All you have to do is just give it the title of the episode, and then it would write the whole episode and generate it and give you your audio file. If you'd done that with AI Box, then there wouldn't be the crashing. And if Claude crashed for any reason, AI Box would have safely generated and be able to get you your asset. So instead of me saying, oh, shoot, um, I just lost $1200 of 11 labs generations, they would all. Even if cloud crashes, they would all still be safe on AI Box. So this is what we're trying to build with the mcp. We're basically trying to make it your pipelines of AI content much more reliable. And at the same time, we're trying to make it so that if any, any crashes happen on Claude or on any of the software that you're vibe coding, if you have the engine of it being run on AI Box, you never lose your assets, you never lose access to your assets. And of course, the other thing that people love about it is if you're creating tools that generate images, audio, video, Claude just can't do that, doesn't have the capabilities. And so if you create a box on AI box that can generate any of those assets, you can tell Claude to call it and to do it. And essentially you're able to generate, you know, images with Claude, which was never a capability that Claude had before. And it saves you a ton of time for, you know, whether that's generated images for, you know, graphics for your apps or for, you know, blog post titles. Like all, if you go look@aichatdaily.com, my AI news site, all of the titles, all of the banner images and all of the articles are AI generated. And using something like AI Box to generate them helps it to be super consistent. And then we don't have that crashing issue. Okay. And of course Also we give ChatGPT or Claude the ability to generate images, which it didn't even have before. Okay, I want to talk about some of the top, most used MCP tools that are out there. There's a really interesting, some interesting leaderboards, MCP leaderboards, which are great places to see what ones are actually very useful. Sometimes a company will come out with an mcp, but it doesn't have all of the capabilities of their plat. Um, and you know, I hate to, I hate to beg on like Beehive, because I love that platform for email sending. But their MCP only gives you data about the platform. It doesn't actually help you post to the platform yet. And they said like they're working on it. So there's some, you know, that sometimes the functionality isn't completely there. Of everything you could do if you were just on the website. But I did want to say some of my favorite mcps I use and talk about some of the other more popular ones. The number one is that I'm using is the GitHub MCP and that can also, I think it's like built into Claude, so you probably see that one. You probably don't have to go get a custom connection for it, but I have everything. If you're going to be doing, developing anything, I recommend getting something like Vercel or Netlify McP and getting Supabase and then getting GitHub and connecting that stack, you can essentially log into all your accounts and anything you want to build. Claude can go and set up your database, it can set up your hosting and it can set up, you know, where you store your code, which is GitHub and what you're working through. So just those three are basically the most popular ones that I personally am using. I love some of the Google connection ones that are able to do something like Gmail, Google Calendar and Google Drive and interact with all of those for me. And those are all also super popular. And then a couple that I was seeing people recommend online that are really useful are one of them being Brave Search. It's I think one of the most popular web search mcps. Basically the AI can get past any sort of training cutoff and can find current library releases or CVEs. Figma has one, which is interesting when it comes to working between design and code. Canva has some version of this and then I think Notion, a lot of people use Notion. If you have that, it's a great way to connect AI to some of your workspaces for syncing your knowledge bases, your documents and a bunch of your tasks. Now there's tons that, tons of places that you can plug this into. You can plug these all into Cursor, Cloud, Desktop, Gemini, I think Grok and a bunch of others. So lots of different places to give these MCPS to and lots of different software. But honestly, chances are if you have software that you use specifically in your industry and it's not, you know, some super niche software and even, honestly a lot of super niche software even too, it will have an MCP built out for it. So go check just Google MCP for your software, see if it's there and go and attach it and basically you'll, you know, save yourself. If you're using something like Cloud Cowork, like yes, you can get around this. And I do this all the time where like it'll say, hey, I don't have like the. Even sometimes I have the MCP for example to like supabase my database and it's like, hey, I don't have like the permission to edit this one particular thing. Can you get me login or this like, you know, specific credential key and I don't really want to mess around with it. I'm like, look, it's just logged in on my browser, control my computer screen on my browser, go click and figure it out yourself and it can go do that. So that is one way to get around some of these MCPs and the logins. But if you don't want to have to do that, and if you're using a lot of different things or you have repetitive workflows, getting the MCPS and having it connect with them, number one, uses less tokens for you, because computer use, where it's like looking at your computer and moving it around and screenshotting it all the time, that's super. It used a ton of tokens. So if you want to use less tokens, I would get the mcp. If you want to make it more consistent, I'd get the mcp. It has less issues and glitches. And if you're doing, you know, pipelines and other things that are repeated tasks, I would definitely get MCPS for anything you're using. All right. I hope that was a useful episode. If you want to get Access to the AI box MCP, it's $8 a month over on AI box AI, you sign up for an account and then in your settings, you can grab the MCP link, you can go to Claude, give that to Claude, and it will get that. Get that set up. So you can access any of the tools you build on AI box, and you get 80 plus different AI models now built into Claude or Chat, GPT or Gemini using that. So if you want to go check that out, it's AI Box, AI, slash, mcp. That's a page I created that will explain a little bit about how it works and how you connect it. There's a little diagram on there. Hope that is incredibly useful, unlocks all the capabilities of what you'd like to do with Claude. Hope you guys all have a fantastic rest of your day and I'll catch you all in the next episode.