Skip to Content
View all events

MCP Agent Accelerator

Published by Pearson

Intermediate content levelIntermediate

Get up and running quickly to build AI Agents with the Model Context Protocol

  • Learn how to configure MCP clients, build your own MCP servers, and get hands-on experience with creating AI Agents using the official MCP SDKs for Python, Java, and Node.js.
  • Learn the best practices using MCP to AI-enable your HTTP REST APIs to become AI Agents and learn how to use MCP with your PostgreSQL database.
  • Create AI Agents with off-the-shelf hardware to convert dumb appliances into smart appliances for your home without the need for Apple Home, Google Home, or Amazon Alexa hub devices.

The Model Context Protocol is the open standard supported by both Anthropic (Claude) and OpenAI (ChatGPT) that standardizes how AI agent clients connect to AI agent servers. With official SDK support across Python, Java, JavaScript, C#, and more, it has rapidly emerged as the de-facto protocol for AI interoperability.

Day 1 of this course gives you the complete foundation for MCP. You will start with MCP architecture and core concepts, then immediately put them to work. You will learn how to implement the protocol in the most popular programming languages, such as Python, Java, and JavaScript. You will understand the clear differences between the major transports, STDIO and streaming HTTP. You will get hands-on experience with multiple MCP client applications such as ChatGPT, Claude Desktop, Postman, and the MCP Inspector. Finally, you will learn how to leverage open source MCP servers to connect to your PostgreSQL database.

Day 2 of this course shows you the foundation for creating real-world applications with MCP. You will learn the advanced concepts of the protocol, including MCP Sampling and MCP Resources. You will learn how to take your organization's existing REST APIs and create MCP servers with the CTO (Curate, Truncate, Orchestrate) pattern for AI agent orchestration. Then you will cross into the physical world: using inexpensive, off-the-shelf hardware, you will create an MCP Server that lets any AI agent monitor and control real home appliances. You will also learn how to utilize custom URIs for advanced agent orchestration.

What you’ll learn and how you can apply it

  • Build MCP Servers from scratch using the official SDKs for Python, Java, and Node.js
  • Connect AI agents to real data sources your organization already uses, including PostgreSQL databases, local filesystems, and existing REST APIs running in production
  • Learn the CTO Pattern for MCP servers (Curate, Truncate, Orchestrate)
  • Scale your deployment of MCP Servers using Resources and custom URIs

This live event is for you because...

  • You are a software developer or engineer who needs to connect AI capabilities to your organization's existing APIs, databases, and internal services
  • You have used ChatGPT or Claude for chat-based tasks, but you are ready to move beyond prompting and start building AI agents that take actions, access real data, and integrate with the systems your team already depends on
  • You are a technical lead or engineering manager evaluating MCP for your organization and you need hands-on experience with the protocol

Prerequisites

  • Basic programming experience in any major programming language like Python, Java, or JavaScript
  • Familiarity with HTTP APIs and JSON
  • Experience using ChatGPT, Claude, or other LLMs (as a user)
  • Understanding of basic software development concepts (functions, variables, APIs)

Course Set-up

  • Python 3.10+ installed
  • Basic command line proficiency
  • Understanding of REST APIs and JSON

Recommended Preparation

Recommended Follow-up

Schedule

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

Day 1: MCP Fundamentals: From Protocol Concepts to Database-Connected Agents

Segment 1: Introducing the Model Context Protocol (MCP) for AI Agents (30 minutes)

  • MCP Architecture and Core Concepts
  • Why is MCP Important now?
  • Q&A

Segment 2: Getting Hands-on with MCP Clients: ChatGPT, Claude Desktop, Postman, and the MCP Inspector (40 minutes)

  • DEMO: Checking your system’s health (sysmon) with MCP
  • Q&A

Break (5 minutes)

Segment 3: Building Your First MCP Server in Python (40 minutes)

  • Setting up your project and building a weather MCP server
  • DEMO: Using the MCP Inspector with your Python weather MCP server
  • Q&A

Segment 4: Building Your First MCP Server in Java (40 minutes)

  • Setting up your project and building a weather MCP server
  • DEMO: Using Postman with your Java weather MCP server
  • Q&A

Break (5 minutes)

Segment 5: Building Your First MCP Server in Node.js (40 minutes)

  • Setting up your project and building a system monitor MCP server
  • DEMO: Using Claude Desktop with system monitor MCP server
  • Q&A

Segment 6: Using the PostgreSQL Database with MCP (40 minutes)

  • How to setup and configure the official PostgreSQL MCP Server
  • DEMO: Talking to your database in Natural Language without SQL
  • Q&A

Break (5 minutes)

Day 1 Wrap-up and Preview of Day 2 (10 minutes)

  • Take-Home Project: Challenge - Learn the solution on Day 2

Day 2: Production MCP Servers: External APIs, Smart Home Hardware, and Multi-Agent Orchestration

Segment 1: Recap from Day-1 (30 minutes)

  • Welcome back: Take-Home Project Results (10 mins)
  • MCP Architecture and Core Concepts
  • Q&A

Segment 2: Learning the CTO Pattern for Creating MCP Servers from Existing APIs (60 minutes)

  • CTO - Curate, Truncate, Orchestrate
  • DEMO: Creating a Basic MCP Server from an external API
  • Q&A

Break (5 minutes)

Segment 3: MCP AI Agent Orchestration with Resources and Custom URIs (60 minutes)

  • The Best Practices for Working with Multiple MCP Servers
  • Using MCP Resources and Custom URIs for agent-to-agent communication and data sharing
  • DEMO: Multi-Agent Orchestration with Resources and Custom URIs
  • Q&A

Segment 4: Using MCP to Create AI Agents for Your Smart Home (60 minutes)

  • Creating MCP Servers for remote control of your home while you are present or away
  • Create AI Agents with off-the-shelf hardware to convert dumb appliances into smart appliances for your home without the need for Apple Home, Google Home, or Amazon Alexa hub devices
  • DEMO: Ask your home how much power is being used by appliances!
  • Q&A

Course Wrap-up and Next Steps (10 minutes)

Your Instructor

  • Bruce Hopkins

    Bruce Hopkins is a technical writer and AI expert. He is an Intel Software Innovator for AI, as well as an Oracle Java Champion. Bruce is also the author of the books, "ChatGPT for Java" and the co-author of "Beginning ChatGPT for Python".

    Xlinksearch

Skills covered

  • Application Programming Interface (API)
  • ASP.NET Core
  • Web APIs
  • RESTful API