Real World MCP: Augmenting Model Context from Existing Data Sources
Saturday, April 18, 2026 · 1:30 PM – 3:00 PM · Classroom 305
Every organization and an increasing number of open source tools are pitching their solution’s AI integration with MCP. And while it’s nice that there is a standard for adding context to LLMs - wouldn’t it be great if we could easily wrap our existing database in MCP without having to build an entire RAG pipeline?
We’ll learn how to do this on an existing PostgreSQL database of Olympians and their Olympic results along with a MongoDB database of Olympian bios and other Olympic documents.
Using MCP Toolbox, an open source MCP server toolkit for databases by Google, we’ll wrap our two databases in an MCP server, create tools and toolsets for specific queries, and add prompts and resources. Once MCP is up and running, we’ll start to integrate our MCP server into our favorite agent using OpenRouter – quickly adding context and tool calls to our prompts.
Along the way, we’ll dive into some of the details about how MCP works, where it shines and where it’s not so good. We’ll talk about human in the loop for authorizing MCP queries, and get into some of the devops niceties such as authorization and logging. By the end of the tutorial, you should feel comfortable connecting your existing databases to your GenAI and Agentic workflows for science and for internal organizational analysis!
Attendees will need laptops with Docker, git, and Python 3.12 or later installed on their machines. Attendees will also need an OpenRouter API key to access the models used in the tutorials, including free Llama or Mistral models.
About the Speaker
Benjamin Bengfort
Open source hacker and data nerd, currently building AI governance tools with Rotational Labs
Dr. Benjamin Bengfort is the co-founder and CEO of Rotational Labs, where he orchestrates the integration of innovative machine learning techniques with advanced distributed computing systems. A seasoned expert in systems engineering, programming, and data science, he has a proven record of developing AI-driven solutions that support globally distributed data architectures and address the complex challenges of multi-region organizations. Under his leadership, Rotational has focused on not just the implementation but also the responsibility of participating in an AI driven economy; a believer in open source, Dr. Bengfort pays special attention to the ethics and outcomes of AI, ensuring humans are at the center of our solutions.