Skip to content
EDWartens UK

Free course · AI and machine learning

AI Agents and MCP for Engineers

Build AI agents that read plant data safely: the agent loop, tool calling from Python, the Model Context Protocol, FastMCP servers for a SQL historian, OPC UA and Modbus that are read only by design, hosts from Claude to a local Ollama model, the OpenAI Agents SDK, LangGraph and Microsoft Agent Framework, a maintenance triage agent with human approval, guardrails, evaluation and deployment across network zones.

See the modules

Free to learn. Verifiable certificate £19 when you pass the final exam (optional, VAT included).

Level
Intermediate
Modules
13
Video
18 hours
Price
Free

Outcome

What you will be able to do

Explain what an AI agent is and when a plain workflow is better; write tool definitions and a tool-calling loop in Python against hosted and local models; describe the Model Context Protocol's hosts, clients, servers, tools, resources and prompts as of the 2026-07-28 specification; build and test FastMCP servers for a SQL historian, OPC UA and Modbus that are read only by design; connect them to Claude, VS Code and a local Ollama model; choose between the OpenAI Agents SDK, LangGraph and Microsoft Agent Framework; build a maintenance triage agent that stops at a draft for human approval; add allow-lists, rate limits, audit logs and defences against prompt injection; evaluate an agent for success, latency and tokens; and deploy it for a team with containers, secrets and IEC 62443 zones.

  • Explain the agent loop and choose between a workflow and an agent
  • Write tool definitions and a tool-calling loop in Python, including against a local model in Ollama
  • Describe MCP hosts, clients, servers, tools, resources and prompts as of the 2026-07-28 specification
  • Build and test FastMCP servers for a SQL historian, OPC UA and Modbus that are read only by design
  • Connect MCP servers to Claude Code, Claude Desktop, VS Code and an OpenAI Agents SDK agent
  • Build a maintenance triage agent that cites evidence and stops at a draft a person approves
  • Add allow-lists, rate limits, step budgets, audit logs and defences against prompt injection
  • Evaluate an agent for success, refusals, latency and tokens, and deploy it in IEC 62443 zones

Software

Python 3.10 or later with FastMCP, asyncua, pymodbus, the OpenAI Agents SDK and LangGraph (all free, installed with pip), VS Code, SQLite, and at least one MCP host: Claude Desktop or Claude Code, VS Code with GitHub Copilot, or a local model in Ollama. Every exercise can be done with free tools and a local model.

Hardware

A computer with 16 GB of memory is enough for a small local model; 8 GB works if you use a hosted model instead. No PLC or plant equipment: every exercise runs against simulators and a sample historian.

Syllabus

13 modules

Each module has video lessons, notes and a short quiz. The final exam closes the course.

  1. 1What an agent is: model, tools, memory and stop conditions2 lessons
  2. 2Tool calling from Python3 lessonsLab
  3. 3The Model Context Protocol: hosts, clients, servers and primitives2 lessons
  4. 4Your first MCP server with FastMCP1 lesson
  5. 5An MCP server for a SQL historian, read only by design1 lessonLab
  6. 6MCP for OPC UA and Modbus: browse, read, and why writes stay off4 lessonsLab
  7. 7Using MCP servers from Claude, VS Code and local models4 lessons
  8. 8Agent frameworks compared: OpenAI Agents SDK, LangGraph, Microsoft Agent Framework3 lessons
  9. 9A multi-step maintenance triage agent3 lessonsLab
  10. 10Guardrails: approval, allow-lists, rate limits, audit logs and prompt injection3 lessonsLab
  11. 11Evaluating agents: task success, traces, cost and latency3 lessons
  12. 12Deploying agents for a team: containers, secrets and network zones3 lessons
  13. 13Final Assessment1 lesson

How it works

How this course works

  1. Watch the video lessonsOne module at a time, at your own pace.
  2. Take the module quizA short quiz at the end of each module shows what stuck.
  3. Keep your notesWrite in My notes beside each module and ask the trainer if you are stuck.
  4. Practise in the labOptionalTry a task from the module in the EDWartens Lab, in your browser.
  5. Sit the final examPass it once you have been through the modules.
  6. Certificate, if you want oneOptionalPaid, and only after you pass. Anyone can check it online.

EDWartens Lab

Practise this in the EDWartens Lab

Practise the guardrails behind a plant agent in the AI Workbench: tool calls within limits, approval before action, citing evidence and resisting planted instructions.

Works alongside AI Agents and MCP for Engineers. The Lab is ai for industry practice in your browser: no install, no hardware, free to use. Sign in as a learner and it opens with your account.

Open the free lab See the Lab
AI for industry: Build AI models.

Levels to try with this course

Optional. Skip it whenever you like: it never blocks your progress or your certificate.

Why practise in a lab

Technical work is judged on what you can do: wiring, commissioning, finding a fault. Doing a task yourself teaches more than watching it a second time, and a lab lets you try it safely before you meet real equipment. It does not replace working on real hardware.

  • Practise safely, so a mistake costs nothing.
  • The lab checks your work like a site test, so you know when it is right.
  • Free, in your browser, with nothing to install.

Certificate

An optional certificate when you pass

Learning is free. Pass the final exam and you can have a certificate for £19, including VAT, with a number employers can check online. It records that you completed a free online course; it is not a regulated qualification or a CPD certificate.

  • Your name, the course, its study time and your final exam score
  • A unique certificate number and a QR code to its verification page
  • Issued by Wartens Ltd; add it to your LinkedIn profile in one click
  • Pay now or after you pass: it is issued the moment you pass the final

How the certificate works

Sample certificate for AI Agents and MCP for Engineers

Credits

Who made the lessons

The video lessons belong to their creators. EDWartens wrote the study plan, notes, quizzes and the final exam.

  • IBM Technology

    the explainers on what AI agents are and what tool calling is

  • Anthropic

    the talk with tips for building AI agents, and the session on building with MCP and the Claude API

  • Claude

    the short lesson on adding MCP servers to Claude Code

  • Dave Ebbelaar

    the full beginner tutorial on OpenAI function calling, and the practical guide to human-in-the-loop for AI agents

  • Mervin Praison

    tool calling with a local model in Ollama

  • Google Cloud Tech

    how the Model Context Protocol works, and how to evaluate agents in practice

  • freeCodeCamp.org

    the introduction to MCP servers with Python course

  • Microsoft Reactor

    the Python + MCP session on building servers with FastMCP, the Python + Agents session on a first agent, and getting started with Microsoft Agent Framework

  • Tech With Tim

    the advanced MCP server build with databases and authentication, and connecting local models in Ollama to MCP

  • Industry40tv

    building an MCP server for industrial data with FastMCP and OPC UA

  • APMonitor.com

    OPC UA with Python

  • IoT Frontier

    using Claude and MCP with an OPC UA industrial IoT system

  • Fusion Automate

    building a basic Modbus TCP server in Python with pymodbus, used as a simulator

  • Visual Studio Code

    MCP servers in VS Code and GitHub Copilot

  • OpenAI

    the Build Hour on the Agents SDK

  • LangChain

    building effective agents with LangGraph, and LangGraph interrupt for human-in-the-loop agents

  • N3uron

    an MCP server that makes plant data accessible to AI agents

  • SAS FSA

    Mika Karaila of Valmet on an AI agent using MCP and OPC UA

  • AAIF Live

    the Agentic AI Foundation session on MCP security exploits and how to stop them

  • Langfuse

    the walkthrough of agent tracing, evaluations and experiments

  • Aishwarya Srinivasan

    the explanation of AI evals and how to evaluate agents

  • Docker

    configuring MCP servers securely with the Docker MCP Toolkit, and the MCP Toolkit and gateway explained

  • Automation World

    partitioning an OT network into security zones

  • ByteByteGo

    the short review of what AI agents are really about, before the final

Questions

About this course

Who is this AI agents and MCP course for?
It is for automation, controls, maintenance, reliability and data engineers who want AI agents that read plant data safely, including engineers at plants, system integrators and EPC contractors worldwide. You should be able to read and run a short Python program.
What is MCP and why does an engineer need it?
The Model Context Protocol is an open standard, now governed by the Agentic AI Foundation under the Linux Foundation, for connecting AI hosts and agents to tools and data. Wrapping a historian, an OPC UA server or a maintenance log once as an MCP server lets Claude, VS Code or your own agent use it without a custom connector each time.
Is the course free to learn, and what software do I need?
Yes. Every module, the notes, the code, the project and the final assessment are free to learn. The software is free too: Python with FastMCP, asyncua, pymodbus, LangGraph or the OpenAI Agents SDK, and either a free MCP host or a local model in Ollama.
Will an agent from this course write to my PLC?
No. Every tool that touches plant data is read only by design, every exercise runs against simulators and a sample historian, and anything with consequences stops at a draft that a person approves. Agent actions are never run on a live plant without review and testing.
How is this different from the n8n, RAG and AI coding courses?
AI Agents and Workflow Automation with n8n builds agents without code, RAG and Chatbots with LangChain covers answering from documents, and AI Coding for Engineers covers coding agents such as Claude Code. This course is code-first and industrial: you build MCP servers and agents in Python over historian, OPC UA and Modbus data, with guardrails and evaluation.
How long does the course take?
About 17 hours of video, notes and practice at your own pace, of which about 12.6 hours is video. The optional trip-analysis agent project takes about 14 hours more.
What certificate do I get?
An EDWartens Certificate of Completion, issued when you pass the 15-question final at 60 percent, with a number anyone can verify on our site. It is not a certification from Anthropic, OpenAI, Microsoft, LangChain or the Agentic AI Foundation.
What job does this course lead to?
It builds the skills of an industrial AI or automation software engineer: connecting AI agents to plant systems through MCP, with the guardrails, evaluation and OT security placement that plants and integrators ask for. Go on to AI Security and the OWASP Top 10 for LLMs and ICS Security Foundations to deepen the security side.

The Professional Module is five live days of Siemens PLC, HMI and SCADA with an instructor, then a resume session and a CPD certificate.

See the Professional Module