From the course: Creating Agents with Python and the AI Toolkit for Visual Studio Code

Unlock this course with a free trial

Join today to access over 25,200 courses taught by industry experts.

Creating a custom MCP server

Creating a custom MCP server

From the course: Creating Agents with Python and the AI Toolkit for Visual Studio Code

Start my 1-month free trial Buy for my team

Creating a custom MCP server

“

In addition to using existing MCP servers, we can also create our very own MCP server with its own tools and we can run that server locally and continue to use it while we're testing out our agent. This is a pretty powerful feature of the AI toolkit because you're not just beholden to the servers that you can find online, you can also create your own and connect to whatever data sources you need to connect to as well. I have some fictitious data that we're going to use for the MCP server that we're building for this course. Now, in order to actually add in that server itself, we're going to add that in a different area of the AI toolkit because we won't start here in the agent builder for that. But once that tool has been added or the server has been added, then we'll come back and add it to the agent in the agent builder. To get started, I'm going to click these three dots so I can go back to find the AI Toolkit extension itself. Then as I scroll down, what I need to do from here is…

Contents