How Can AI Talk to My Database?

Location Virtual
Dates Jan 23, 2026
Presentation Jan 23, 2026
Speaker
Fernando Laudares Camargos
Fernando Laudares Camargos

Percona, Senior Support Engineer

Abstract

What if we want to give AI access to our database, so it is able to actually query it?

The most common way to provide an AI model access to different data sources (and tools!) is through the use of an intermediate server that implements the Model Context Protocol (MCP), which is an open standard. We call those intermediate MCP servers, and you can somewhat easily build one for different purposes. Having said that, chances are there’s already an open source MCP server available out there that will cover your needs, including database access.

In this short presentation, I’ll show how to use the FastMCP Python framework to deploy MCP servers that allow AI assistants like Claude and Gemini interact with MySQL and PostgreSQL databases.

Speaker Bios

Fernando Laudares Camargos

Percona, Senior Support Engineer

Fernando joined Percona in early 2013 after 8 years working for a Canadian company specialized in Linux and Open Source technologies. As a member of Percona’s Support team, Fernando works closely with customers helping them troubleshoot issues with MySQL, PostgreSQL, and MongoDB servers and looking for answers to various database-related questions and challenges. He also has a personal interest in education in general and loves to read and talk about this subject.

See all talks by Fernando Laudares Camargos »

✎ Edit this page on GitHub