Skip to Content
View all events

Hands-on AI Agents with Model Context Protocol (MCP)

Published by O'Reilly Media, Inc.

Intermediate content levelIntermediate

Getting started with AI agents that leverage MCP and SDKs

What you’ll learn and how you can apply it

  • Learn about the benefits and practical applications of AI agents that leverage the Model Context Protocol (MCP)
  • Learn how to configure MCP clients and build your own MCP servers
  • Get hands-on experience with creating AI agents using the HTTP REST APIs in addition to the official MCP SDKs for Python, Java 21, and Node.js
  • Learn how to use MCP with your PostgreSQL database

Course description

The Model Context Protocol is an open standard that enables developers to build secure, two-way connections between their data sources and AI-powered tools. The architecture is supported by both OpenAI and Anthropic for a globally interoperable standard for AI agent clients and servers. In this live course with Bruce Hopkins, you’ll learn how to get started creating AI agents that leverage the MCP so that your agents can be accessed from MCP AI-agent client tools.

This live event is for you because...

  • You’re a software developer who needs to create AI-based applications and services that connect to corporate, confidential, or personal data sources.
  • You’re familiar with ChatGPT, but you want to learn what the best practices are for creating AI agents that conform to the MCP standard.
  • You’re a technical manager who wants to understand the capabilities and benefits of AI agents and the MCP standard.

Prerequisites

  • An API key for OpenAI or Anthropic Claude
  • An IDE configured with your preferred programming language to execute HTTP REST calls
  • An understanding of programming in any major programming language, such as how to interact with HTTP REST APIs
  • Basic understanding of how to make HTTP calls
  • Familiarity with using ChatGPT

Recommended preparation:

Schedule

The time frames are only estimates and may vary according to how the class is progressing.

Introducing the Model Context Protocol (MCP) for AI agents (30 minutes)

  • Presentation: MCP architecture and core concepts; why MCP is important now
  • Q&A

Getting started with the Anthropic Claude API and MCP app development (70 minutes)

  • Presentation: Leveraging MCP for local file access
  • Demonstration: Accessing your local files with MCP
  • Q&A
  • Break

Getting started with the OpenAI agents and the responses APIs for MCP app development (70 minutes)

  • Presentation: Creating a multimodal AI agent for AI expense reports
  • Demonstration: Expense report done in 60 seconds
  • Q&A
  • Break

Using the PostgresSQL database with MCP (60 minutes)

  • Presentation: Setting up and configuring the official PostgresSQL MCP server
  • Demonstration: Talking to your database in natural language without SQL
  • Q&A

Wrap-up and next steps (10 minutes)

Your Instructor

  • Bruce Hopkins

    Bruce Hopkins is a technical writer, an AI expert, an Intel Software Innovator for AI, and an Oracle Java Champion. He’s also the author of ChatGPT for Java and the coauthor of Beginning ChatGPT for Python.

    Xlinksearch

Skills covered

  • Application Programming Interface (API)
  • RESTful API
  • Web APIs