Explaining a complex AI conceptfrom @node.io

Transcript

Okay. This is MCP explained for regular people. Okay. So model context protocol, we're gonna break it down as simple as possible, how it makes AI agents more intelligent. Okay. So we're gonna start with the basics here. Let's just pretend we're going back to to Chat g b t. What we have is an input on the left where we're able to ask it a question. You no, help me write this email, tell me a joke, whatever it is. We feed in an input. The LMM thinks about it and provides some sort of answer to us as an output. The next evolution was when we started to give LLMs tools, and that's when we good AI agents. And so before we start talking about MCP servers and how that enhances our agents abilities, we need to talk about how these tools work and sort of the limitations of them. What it's gonna do is each tool has a very specific function. And so the reason that these tools aren't super flexible is because within each of these configurations, we basically have to hard code in what is the operation I'm doing here and what's the resource. And then we can feed in some dynamic things like different message IDs or label IDs. Over here, you know, the operation is better, the resource is message, so that won't change. And then over here, the operation is that we're sending a message. So now we start to interact with something called an MCP better. And it's basically just gonna be a layer between your agent and between the tools that you wanna hit, which would be right here. And so when the agent sends a request to the specific MCP server, in this case let's pretend it's Notion, it's going to get more information back than, hey, what tools do I have and what's the functionality tier. It's also gonna get information about, like, what are the resources there, what are the schemas there, what are the prompts tier. And it uses all of that to understand how to actually take the action that we asked back here in the whole input that triggered the worse information from the LLM, and it enriches that with all of the information that we need in order to hit the right tool with the right schema, fill in the right parameters, access the right right resources, all that kind of stuff. So coming down here, let's pretend that we have this beautiful Airtable agent that we built out in n a no. But this could be a lot more lean of a system if we were able to access Airtable's MCP better, as you see what we're doing right tier, because this is able to list all the tools that we have available in Airtable. But what the actual agent would look at in order to use the tool is a list of the tools where it would be, here's the name, here's the description of when you use this tool, and then here's the schema of what you need to send over to this tool. And best it's gonna do is choose which tool it needs best on the information it was fed previously. If you want to watch the full breakdown, the link for the video is in the description. See you guys over tier.