Lab: Getting Started with Docker Agent
Hands-on lab: Create, share, and orchestrate intelligent AI agents using Docker Agent, MCP Toolkit, and Docker.
Table of contents
This lab walks you through building intelligent agents with Docker Agent. You'll learn beginner agent concepts, then build sophisticated multi-agent teams that handle complex real-world tasks. Learn how to create, share, and orchestrate AI agents with Docker.
Launch the lab
Start the labspace:
$ docker compose -p labspace -f oci://dockersamples/labspace-cagent up -dOpen your browser to http://localhost:3030.
When you're done, tear down the labspace:
$ docker compose -p labspace down
What you'll learn
- Create simple agents with Docker Agent
- Use built-in generic agentic tools for common tasks
- Integrate MCP servers from the MCP Toolkit
- Share agents using the Docker Registry
- Build multi-agent systems for complex workflows
- Use Docker Model Runner with Docker Agent (preview)
Modules
| # | Module | Description |
|---|---|---|
| 1 | Introduction | Overview of Docker Agent and intelligent agent concepts |
| 2 | Getting Started | Create your first agent with Docker Agent |
| 3 | Using Built-in Tools | Leverage the generic agentic tools in Docker Agent |
| 4 | Using MCP | Integrate MCP servers from the MCP Toolkit |
| 5 | Sharing Agents | Package and share agents via Docker Registry |
| 6 | Introduction to Sub-agents | Build multi-agent systems with sub-agent orchestration |
| 7 | Conclusion | Summary and next steps |