We can't find the internet
Attempting to reconnect
Something went wrong!
Hang in there while we get back on track
Connect your coding agents to your own APIs, databases and documents, so they finish the work they now hand back to your engineers.
Rebuilt on your team's work
Run privately for your team, on dates and at a length that suit you.
Every module ends with something participants can repeat on Monday morning in their own work and tools, so the team gets more done without adding people.
Stand up an MCP server from an empty directory and have an agent calling it before lunch.
Put an internal API, a database or a document store behind a tool an agent is allowed to call.
Name, describe and shape a tool so the model picks it and calls it correctly.
Decide between stdio and HTTP for a given server, and know what each one costs you operationally.
Hold secrets outside the agent's reach and scope every tool to the least it needs.
Version, package and roll out a server so colleagues run the same one you built.
Most of the time goes on hands-on exercises. Module order and depth are set for your group before the first day.
Your version builds a server against one of your own systems, such as an internal API, a database or your ticketing tool, in the language your team writes. Authentication and deployment follow the way you already run services, so the server can stay in use after the course.
How a booking worksIn your office, with the team in the room. Best for a first rollout.
Live over video, in shorter blocks across several days.
A day on site to start, then shorter remote sessions on real work.
Every course runs privately for one team, on dates we agree together.
Every module can be rebuilt on your team's own work and tools. Tell me what the team works on and I will tell you what I would change.
AI agent trainer and software engineer
MCP integrations are part of the Claude Code work I teach engineering teams, and connectors are a topic of the seminar series on Claude I run for cimdata. The backend systems these servers talk to are what I build every day, in Elixir and Python.
From engineering teams I trained to work with AI agents.
I worked closely with Luka as the topic sponsor for a workshop on integrating AI meaningfully into everyday development work.
He took the time to understand our participants' needs and adapted his approach to the tools and working environments available.
Participant feedback reinforced my own positive experience, with especially strong recognition of his subject expertise and the balance between theory and practice.
I wholeheartedly recommend Luka as a trainer to any team looking to build practical AI skills.
What teams ask before they book.
No, and most groups have not. The course assumes you already use a coding agent and have hit something it cannot reach. We start at the protocol and have a server running within the first two hours.
Python or TypeScript, whichever your team writes. The protocol is the same either way, so a mixed room is fine and usually instructive.
Yes, that is how the course is meant to run. Before the day, name one or two systems you want an agent to reach, and the exercises are built against them.
No. Everything runs locally on the participants' machines. Hosting and distribution are covered in the last module so you leave knowing the options, but nothing has to be provisioned beforehand.
Little. The Claude Code course is about using an agent well. This one is about writing the servers that agent connects to.
Have a question about your team's setup?
Tell me what your team works on and how it uses AI today. A few lines are enough. I reply myself, usually within a day, and if this course is the wrong one I will point you to the one that fits.
In English or German, on site, remote or hybrid.
MCP Server Training
A few lines are enough
Engineering teams and providers I have delivered AI training for