Training course · Model Context Protocol (MCP) · Data Engineering

Model Context Protocol (MCP) for Data Engineers

Build and connect MCP servers securely: tools, resources and prompts for Claude Code, Cursor, Copilot and your own AI agents.

Duration
2 days (14 hrs)
Format
Online or on-site
Language
German or English
Participants
open dates or exclusive for your team
Certificate
Certificate of attendance

Overview

This course connects Model Context Protocol (MCP) with the everyday processes of Data Engineering. Participants work on realistic scenarios and leave with prompts, workflows and checklists they can use straight away.

The Model Context Protocol is an open standard that gives AI applications a uniform way to access external tools, data sources and workflows. Instead of building separate integrations for every assistant, you implement an MCP server once and use it in Claude Code, Claude Desktop, Cursor, GitHub Copilot, VS Code and your own agents. In this two-day course you learn the host, client and server architecture, the three core primitives of tools, resources and prompts, and the stdio and Streamable HTTP transports, applying each of them directly in your own code.

On day one you use the official TypeScript or Python SDK to build an MCP server that exposes internal APIs, databases or files to AI assistants in a controlled way, and you test it with the MCP Inspector. Day two covers remote servers, OAuth-based authorisation, security risks such as prompt injection and tool poisoning, and operations, logging and governance in an enterprise setting. You learn to write tool descriptions that models use reliably, and you leave knowing how to integrate MCP servers safely into your development and agent landscape.

Data engineers build and run the pipelines that reporting, analytics and AI applications depend on: ingestion from source systems, transformations in dbt or Spark, orchestration with Airflow or Dagster, and data quality and governance in the warehouse or lakehouse. Much of the work involves SQL, Python, YAML and a great deal of detailed knowledge about schemas and dependencies. AI coding assistants and agents accelerate this work considerably: they write dbt models with tests and documentation, optimise slow queries, create Airflow DAGs, migrate legacy ETL and explain complex lineage. Because data is often sensitive, handling schemas, sample data and credentials responsibly is at the heart of this course.

The course is delivered live – either online in a virtual classroom or on-site in our training rooms in Munich, Salzburg, Berlin, Augsburg, Hanover, Bremen, Stuttgart and Kaiserslautern. We can also run it exclusively for your team.

Who is this course for?

  • Data engineers and analytics engineers
  • BI developers responsible for ETL and the data warehouse
  • Platform teams running lakehouse and streaming infrastructure
  • Developers modernising legacy ETL processes

Typical challenges we address

  • Ageing ETL built on stored procedures or proprietary tools with no tests
  • Slow, expensive queries and inefficient Spark jobs
  • Missing data quality checks and unclear ownership of datasets
  • Patchy documentation of data models, lineage and business logic

What you will be able to do

  • You explain the MCP architecture and choose between tools, resources and prompts for each use case.
  • You develop your own MCP server in TypeScript or Python and test it systematically.
  • You connect MCP servers to Claude Code, Cursor, Copilot and custom agents.
  • You run remote servers using Streamable HTTP and OAuth-based authorisation.
  • Use AI agents productively for dbt models, pipelines and SQL optimisation.
  • Modernise legacy ETL with AI support and safeguard results with reconciliation tests.
  • Protect sensitive data by working with schemas, synthetic samples and minimal access rights.

Course outline

Day 1

Module 1 Architecture and core concepts
  • Roles of host, client and server and the lifecycle of a connection
  • JSON-RPC messages, capability negotiation and notifications
  • Tools, resources and prompts: choosing the right primitive
  • Client features such as sampling, roots and elicitation at a glance
Module 2 Building your own MCP server
  • Setting up a server with the official TypeScript or Python SDK
  • Defining tools cleanly with JSON Schema for inputs and outputs
  • Exposing resources and resource templates for documents, records and configuration
  • Testing and debugging with the MCP Inspector and meaningful error messages
Module 3 Connecting to Claude Code, Cursor, Copilot and agents
  • Configuring local stdio servers and remote servers in clients
  • Project-level and user-level configuration, approvals and permissions
  • Writing tool descriptions that models reliably select correctly
  • Integrating MCP servers into custom agents built with the Claude Agent SDK or OpenAI Agents SDK
Module 4 Transport, authorisation and operations
  • Streamable HTTP, session management and stateless servers
  • OAuth-based authorisation, token validation and integration with existing identity providers
  • Deploying as containers, on serverless platforms or behind a gateway
  • Logging, monitoring, rate limiting and versioning tool interfaces

Day 2

Module 5 Security and governance
  • Threats: prompt injection via tool results, tool poisoning, confused deputy
  • Least privilege, confirmation requirements and sandboxing
  • Reviewing and approving third-party servers within the organisation
  • Data protection, logging of personal data and requirements under GDPR and the EU AI Act
Module 6 Practice lab: Data Engineering
  • dbt models with tests
  • Optimising SQL queries
  • Airflow and Dagster pipelines
  • Migrating legacy ETL
  • Automating data quality
  • Analysing Spark jobs
Module 7 Data protection, quality & transfer to daily work
  • Data engineering prompts should contain schemas and synthetic sample data rather than real personal records, and database credentials or connection strings must stay out of context. Apply GDPR principles such as purpose limitation and data minimisation, document data flows transparently and check new Python packages and connectors for licensing and supply-chain risk.
  • Ground rules for safe AI use in your team
  • Checking results: facts, sources, tests and the four-eyes principle
  • Personal action plan for the next 30 days
  • Open questions, outlook and resources for further learning

Practical scenarios from your field

dbt models with tests

The agent writes staging, intermediate and mart models in dbt, adds schema tests, source definitions and descriptions, and runs dbt build iteratively until models and tests pass.

Optimising SQL queries

The AI analyses execution plans, spots expensive joins and missing partitioning or clustering, and rewrites queries so they scan less data and run measurably faster.

Airflow and Dagster pipelines

Requirements become DAGs or assets with a clean dependency structure, retries, sensors, alerting and backfill support, along with tests for the transformation logic. Existing naming conventions are respected.

Migrating legacy ETL

Stored procedures or graphical ETL jobs are analysed, the business logic documented and moved step by step into dbt or PySpark code, safeguarded by reconciliation queries comparing old and new.

Automating data quality

The assistant defines checks for completeness, uniqueness, value ranges and freshness, implements them with dbt tests or Great Expectations and sets up notifications for violations.

Analysing Spark jobs

Spark UI information and logs are interpreted, skew, shuffles and memory issues identified and optimisations such as broadcast joins, repartitioning or caching proposed. Every optimisation is backed by runtime comparisons.

Possible hands-on projects

Data quality dashboard

A small web app that reads results from dbt tests or data quality checks and presents trends, outliers and affected tables at a glance.

Ingestion pipeline for a REST API

A Python pipeline that loads data incrementally from an API, detects schema changes and writes the results as partitioned tables to the lakehouse.

Lineage explorer

A tool that parses the dbt manifest and displays dependencies between sources, models and dashboards as an interactive graph. The impact of changes becomes visible at a glance.

Prerequisites

Solid programming skills in TypeScript/JavaScript or Python and a basic understanding of HTTP APIs and JSON. Some experience using AI assistants in day-to-day development is helpful. Confident SQL and Python skills plus practical experience with a data warehouse, dbt, Spark or an orchestration tool.

Technical requirements

A laptop with Node.js or Python, Git and a code editor, plus access to at least one MCP-capable client such as Claude Code, Claude Desktop, Cursor or VS Code with Copilot.

Data protection & compliance

Data engineering prompts should contain schemas and synthetic sample data rather than real personal records, and database credentials or connection strings must stay out of context. Apply GDPR principles such as purpose limitation and data minimisation, document data flows transparently and check new Python packages and connectors for licensing and supply-chain risk.

Suggested dates

All dates are suggestions – your preferred date is always possible.

  • Thu, 26 November 2026 – Fri, 27 November 2026 Online Request
  • Mon, 7 December 2026 – Tue, 8 December 2026 Stuttgart Request
  • Thu, 21 January 2027 – Fri, 22 January 2027 Online Request
  • Tue, 26 January 2027 – Wed, 27 January 2027 Berlin Request
  • Tue, 9 February 2027 – Wed, 10 February 2027 Online Request
  • Wed, 17 February 2027 – Thu, 18 February 2027 Munich Request

Frequently asked questions

Why would I need my own MCP server?

Whenever AI assistants need access to internal systems such as ticketing tools, databases, documentation or line-of-business applications. Your own server defines precisely which actions and data are available and can then be reused across several clients. That avoids isolated one-off integrations and keeps access firmly under your control.

Which programming language does the course use?

You can choose between TypeScript and Python, both of which have official SDKs. The concepts are identical and all exercises are available in both versions. Developers working in other languages still benefit, because the protocol is language-agnostic and SDKs for other languages follow a similar structure.

How secure is MCP for enterprise use?

The protocol provides mechanisms for authorisation and permissions, but real-world security depends on implementation and operations. Risks such as prompt injection through tool results or over-privileged servers are genuine. We cover concrete countermeasures, approval processes for third-party servers and how to handle personal data.

Does the AI need access to our production data?

No, and it usually makes little sense. For the vast majority of tasks, schemas, metadata, execution plans and synthetic sample data are sufficient. On the course you learn to give the agent exactly this context, restrict read access to development environments and still obtain reliable results.

Will this work with our data warehouse?

The working methods are platform-independent and apply equally to Snowflake, BigQuery, Databricks, Redshift, Synapse or PostgreSQL. What matters is telling the assistant about the SQL dialect and platform specifics such as partitioning or clustering. We show you how to capture this in instruction files.

How much does “Model Context Protocol (MCP) for Data Engineers” cost?

The course costs a flat €949 plus VAT per participant – whether online or on-site. This includes 2 training day(s) with a live trainer, course materials, a lab environment and a certificate of attendance.

Can I suggest my own date?

Yes. Our suggested dates are just a guide. In the request form you can always describe your preferred date or period in free text – we check availability and confirm within one working day.

Is the course online or on-site?

Both are possible: live online in a virtual classroom or on-site in Munich, Salzburg, Berlin, Augsburg, Hanover, Bremen, Stuttgart or Kaiserslautern. We can also run the course exclusively for your team.

More courses for Data Engineers

More Model Context Protocol (MCP) courses

All 29 Model Context Protocol (MCP) courses

Model Context Protocol (MCP) · MunichModel Context Protocol (MCP) · SalzburgModel Context Protocol (MCP) · BerlinModel Context Protocol (MCP) · AugsburgModel Context Protocol (MCP) · HanoverModel Context Protocol (MCP) · BremenModel Context Protocol (MCP) · StuttgartModel Context Protocol (MCP) · KaiserslauternModel Context Protocol (MCP) · Online