MCP: Connecting AI to Tools & Data

AI applications become much more useful when they can interact with the systems around them, including databases, APIs, files, developer tools, and external services.
In this meetup, we’ll explore Model Context Protocol (MCP), an open protocol for connecting AI applications to tools and data sources through a standardized interface.
We’ll break down how MCP works, where it fits within modern AI and agent architectures, and what actually happens when a model discovers and calls tools through an MCP server.
We’ll cover:

• What MCP is and the problem it is designed to solve
• MCP clients, servers, tools, resources, and prompts
• How MCP differs from traditional APIs and direct tool calling
• How an AI application discovers and invokes MCP tools
• Building a simple MCP server
• Real-world use cases and architecture patterns

The session will include a practical demo and discussion, so you’ll leave with a clearer understanding of how MCP can be used to build more connected and capable AI applications.

Who is this for?
Software engineers, AI/ML practitioners, technical founders, students, and anyone curious about building with modern AI infrastructure.
No prior MCP experience is required.

Women in the Loop is a Montréal community for women who want to stay in the loop on emerging technology and build with it.