Large language models are powerful, but without access to your data and tools, they’re blind. The Model Context Protocol (MCP) is an open standard that bridges that gap, allowing LLMs to interact with your APIs, databases, and internal systems.
In this hands-on workshop, you’ll focus on turning an existing service or API into an MCP server that can be used by AI-powered tools and assistants. We’ll go from concept to code, covering the essential building blocks of MCP servers and how Tools, Resources, and Prompts are described so that AI clients can understand and safely use them.
The session is highly practical, with guided exercises where you implement and test an MCP server in .NET and C#. Along the way, you’ll explore how AI tools discover capabilities, interpret structured metadata, and interact with real services through MCP.
What you’ll learn:
• How to build your first MCP server from an existing API
• Implementing and describing Tools, with an overview of Resources and Prompts
• Structuring types and metadata for effective AI interaction
• Hosting and security options
• Testing and iterating on MCP servers during development
Prerequisites:
• Basic familiarity with C# and APIs
• A laptop with .NET 10 and VS Code installed (starter code will be provided)
