Lab: Building Agentic Apps with Docker
Get up and running with building agentic applications using Compose, Docker Model Runner, and the Docker MCP Gateway. This hands-on lab takes you from understanding AI models to building complete agentic applications.
Launch the lab
Start the labspace:
$ docker compose -p labspace -f oci://dockersamples/labspace-agentic-apps-with-docker up -dNoteThe lab may take a few minutes to launch, as this lab requires an AI model that will need to be downloaded.
Open your browser to http://localhost:3030.
When you're done, tear down the labspace:
$ docker compose -p labspace down
What you'll learn
This lab covers three core areas of agentic application development:
Models: What models are, how to interact with them, configuring Docker Model Runner in Compose, and writing code that connects to the Model Runner
Tools: Understanding tools and how they work, how MCP (Model Context Protocol) fits in, configuring the Docker MCP Gateway, and connecting to the MCP Gateway in code
Code: What agentic frameworks are, defining models and tools in a Compose file, and configuring your app to use those models and tools
Modules
| # | Module | Description |
|---|---|---|
| 1 | Introduction | Overview of agentic applications and the Docker AI stack |
| 2 | Understanding Model Interactions | Learn how to interact with AI models |
| 3 | The Docker Model Runner | Configure and use Docker Model Runner with Compose |
| 4 | Understanding Tools and MCP | Deep dive into tools, tool calling, and MCP |
| 5 | The Docker MCP Gateway | Set up and configure the MCP Gateway |
| 6 | Putting It All Together | Build a complete agentic application |
| 7 | Conclusion | Summary and next steps |