Program JavaZone

Workshop Tirsdag 1. september

Build AI Agents That Actually Do Things — Hands-on with MCP

Workshop C

Engelsk 2 t AI / Machine Learning Architecture & Design Back-End DevOps Cloud

Leif Terje Fonnes

Leif Terje heads digital development at Fjord Line, where he runs Kubernetes clusters on ferries with spotty satellite connections — which has given him strong opinions about building systems that need to actually work. Before Fjord Line he spent over a decade as an independent consultant across banking, pharma, and shipping. Active in the Bergen developer community through javaBin and Cloud Native Bergen.

Lars Søraas

Lars heads the cloud and custom applications team at Capgemini Bergen. Over 25 years he's gone from co-founding startups to building software for energy, telecom, and healthcare — and he still gets more excited about the building part than the managing part. Active in javaBin Bergen and speaking at Booster Conference 2026.

Most AI agent tutorials stop at "call the API and print the response." That's not an agent — that's autocomplete with better marketing.

In this workshop you build a real agent system: three services in Docker that work together so the AI can discover and call external tools on its own. The protocol that makes this work is MCP (Model Context Protocol), the open standard from Anthropic that's already integrated into Claude Desktop, VS Code, and Cursor.

You'll build a chat UI, an orchestration layer (Python/FastAPI + OpenAI), and an MCP server where you register your own tools. The agent discovers what's available at startup via JSON-RPC — add a tool, restart, it picks it up. No glue code.

After a short architecture intro, you code. Environment runs in GitHub Codespaces, so setup is a fork and a docker compose up. You'll build two tools from scratch, debug failures, and watch the agent combine multiple tools in one response.

The workshop uses Python, but the MCP protocol and JSON-RPC patterns are language-agnostic — they map directly to any JVM language. For developers and architects who want to understand how AI tool-calling works under the hood, not just consume an API.

Bring a GitHub account and basic programming skills. You leave with a running system to fork and extend.

developers, architects,devops

reliable WiFi (Codespaces + Docker image pulls). We send setup instructions a week before the event.

  1. From Streams to SQL to AI. Build an Open Source HTAP Platform in 4 Hours Workshop A
  2. Event Sourcing: From Chaos to Control Workshop B
  3. From data to OGC API (Features) service using Geoserver Workshop D