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.

Enabling tool-use in your agent's configuration

Enabling tool-use in your agent's configuration

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

Enabling tool-use in your agent's configuration

“

The next thing that we're going to do is give our agent access to some tools. That way, it can start reaching out into the outside world to help with the task that we want to give it. I'm going to clean up things here just a little bit. To start, I'm going to switch back to the GPT 4.1 mini model from Azure AI Foundry. That does get rid of our structured JSON schema that is driving the output for the model, but that's okay because we are going to redefine how we want the output to be. I'm also going to clean up the chat window as well. I'll click the icon for a new chat. Then we're back to how the agent was originally designed. The first thing that we're going to need to do right now is scroll down in the agent builder to the tool section. Within this tool section, this is where we can come and add either an existing MCP server or a custom one that we may have made. We're going to use an existing MCP server. To do so, within tools, you'll click the Add Tool icon followed by MCP…

Contents