The Model Context Protocol (MCP) standardizes how AI applications connect with external resources, providing a framework for interoperability. Spring AI heavily supports MCP, offering Spring Boot Starters and annotations for building both MCP servers and clients in Java. This document introduces MCP, explaining its client-server architecture where servers expose capabilities and clients consume them. AI developers build applications utilizing MCP clients, while server developers create services. The MCP features enable seamless communication, including tools, resources, prompts, and real-time updates. The guide provides a practical example, showcasing the development of a Streamable-HTTP MCP weather server. Developers can use the MCP Inspector and Java SDK to interact with the server. Advanced features like logging, progress tracking, and sampling are presented to improve the capabilities. The advanced server implementation integrates logging, progress updates, and, most importantly, sampling.