GenAI Cracow #25 - MCP
Agenda
Opening Ceremony
Building a Recommendations System for Integration Discovery by Bartłomiej
Technical Challenges of Developing an MCP Clients by Vladyslav
Q&A
Quiz
Networking
Abstract
Building a Recommendations System for Integration Discovery
Integration discovery sounds simple until you try to do it in production. In this talk I'll walk through how we built a recommendations system for integrations and why our initial approach based on categories didn't work as expected. We'll look at how inconsistent metadata shaped the system design, why we moved to keyword-based search and what we learned from observing real user behavior. The focus will be on engineering decisions and trade-offs that appear when a system moves from idea to production.
Technical Challenges of Developing an MCP Clients
Most available resources, tutorials, and talks focus exclusively on building MCP servers, leaving the development of remote MCP clients largely uncovered. This presentation will provide a technical overview of this missing perspective. What exactly is an MCP client? What does it really take to build a remote one? Is the official Python MCP SDK genuinely suitable for remote client development, or are developers better off rolling their own solutions? What specific challenges do connecting to and interacting with remote MCP servers impose on developers? This presentation will address these essential questions.
Speakers
Bartłomiej Czech
Software Engineer @ ActiveCampaign, working on integrations. He is interested in how systems behave in production and how engineering decisions translate into real user interactions. Outside of work, he studies cybersecurity, with a focus on securing AI systems.
LinkedIn
Vladyslav Fedoriuk
Full-Stack Engineer @ ActiveCampaign
LinkedIn
Partners
ActiveCampaign
Marketing industry has spent decades asking humans to think like machines - configure this trigger, map that workflow, repeat. At ActiveCampaign we are building the opposite: a platform where AI handles the orchestration, and our customers can focus on outcomes. Active Intelligence, our production AI layer, is what makes that real - autonomous campaign execution across email, SMS, and CRM, at the scale of tens of thousands of businesses. Our Cracow Hub is where nine engineering teams turn that ambition into working software - and where agentic workflows, RAG, MCP, and AI-assisted development are not tools we experiment with, but the way we build.
CEE AI Hub