MCP — Model Context Protocol

MCP is an open protocol that standardizes how applications provide context to LLMs. Think of MCP like a USB-C port for AI applications. Just as USB-C provides a standardized way to connect your devices to various peripherals and accessories, MCP provides a standardized way to connect AI models to different data sources and tools.
​
Why MCP?

MCP helps you build agents and complex workflows on top of LLMs. LLMs frequently need to integrate with data and tools, and MCP provides:

MCP stands for Model Context Protocol, and it's an open standard that allows AI agents to connect to our tools, our systems, and our data. 

What the AI agent connects to is called an MCP server and that server is essentially just a wrapper around an API, which makes it easier for the AI agent to interact with. So goals, in any AI agent that adheres to MCP can connect to all sorts of data and systems just by using the MCP for those things. This means instead of writing a customer integration for every single API that you want to use, you can plug into an MCP and boom, you've got access to its functionality in a way that's easier for the AIs to interact with.

So there's MCP servers for all sorts of things. Databases, cloud services, internal tools you name it. And guess what? There's even one for Selenium.