Migrating Legacy Languages to Python & MCP Principles and Practice

✨ 🚀 Migrating Legacy Languages to Python & MCP: Principles & Practice 🐍 ✨

Ready to bridge the gap between decades-old legacy systems and the cutting-edge future of AI?

Join us at Talent Garden Calabiana for a deep-dive technical night, co-hosted by Scops.ai and TAG.

We'll tackle two major frontiers in modern engineering: the complex realities of rescuing business logic from legacy code to modern Python, and the hands-on mechanics of Model Context Protocol (MCP). Whether you're modernizing the past or building the future, this meetup is for you.

Agenda

• 👋 18:30 Doors Open
• 🤝 19:00 Introduction
• 🐍 19:10 Talk: Migrating from legacy languages to Python with Federico Tomassetti
• 🧠 19:50 Talk: Model Context Protocol: Principles and Practice
• 🍻 After the meetup we will organize a dinner close to the venue, anybody who wants to join is welcome!

📍 Venue: Talent Garden, Via Arcivescovo Calabiana 6 (M3 Lodi or Brenta)
📺 The event will be recorded and streamed on Python Milano Youtube channel (links will appear here close to the event)

🐦🐍 Migrating from legacy languages to Python
Python today has a vast ecosystem and an active community which makes it a great choice for many organizations. However, many companies still rely on critical software written decades ago in languages such as RPG, Visual Basic 6, or SAS. While these systems continue to work, they increasingly limit maintainability, hiring, integration, and long-term evolution. In this talk we want to discuss how the systems can be automatically migrated to Python.

We will discuss the real technical and organizational challenges involved: understanding legacy semantics, preserving business logic, validating behavior, and managing incremental migration. The goal is to provide a clear overview of the techniques, trade-offs, and feasibility boundaries involved in translating legacy codebases into modern Python systems. The attendees will get a realistic understanding of what is possible today, when Python is a good target, and how to reason about migration projects without underestimating their complexity.

Federico Tomassetti, Language Engineering Architect @ Strumenta
Federico Tomassetti is the founder of Strumenta, a company specialized in Language Engineering. At Strumenta he builds Domain Specific Languages, editors, parsers, compilers, and interpreters. In other words languages and tooling to help professionals to work betterm.

After getting his PhD he has worked in Italy, Germany, Ireland, and France. He worked for small companies and large ones like TripAdvisor and Groupon.

🧠🦾 Model Context Protocol: Principles and Practice

Large‑language‑model agents are only as useful as the context and tools they can reach.

Anthropic’s Model Context Protocol (MCP) proposes a universal, bidirectional interface that turns every external system—SQL databases, Slack, Git, web browsers, even your local file‑system—into first‑class “context providers.”

In just 30 minutes we’ll step from high‑level buzzwords to hands‑on engineering details:
How MCP’s JSON‑RPC message format, streaming channels, and version‑negotiation work under the hood.
Why per‑tool sandboxing via isolated client processes hardens security (and what happens when an LLM tries rm ‑rf /).
Techniques for hierarchical context retrieval that stretch a model’s effective window beyond token limits.

Real‑world patterns for accessing multiple tools—Postgres, Slack, GitHub—and plugging MCP into GenAI applications.
Expect code snippets and lessons from early adoption.
You’ll leave ready to wire your own services into any MCP‑aware model and level‑up your GenAI applications—without the N×M integration nightmare.

Luca Baggi, AI Engineer @ xtream

✋ Please use your real Name and Surname to register, we cannot assure you will be able to access the venue if not.
👻 If you have a last minute issue please remember to cancel the RSVP.
🙏 Thanks for your cooperation