Model Context Protocol (MCP) in VS Code with Microsoft Learn
The Model Context Protocol is an open standard that enables developers to build secure, two-way connections between their data sources and AI-powered tools. The architecture is straightforward: Developers can expose their data through MCP servers or build AI applications (MCP clients) that connect to these servers.
There are different types of primitives that an MCP server can expose, which extend the ability of your AI applications and clients to create, read: Resources are a core primitive in the Model Context Protocol (MCP) that allows servers to expose data and content that clients can read and use as context for LLM interactions. Prompts enable servers to define reusable prompt templates and workflows that clients can quickly surface to users and LLMs. They provide a powerful way to standardize and share everyday LLM interactions. Tools are a powerful primitive in the Model Context Protocol (MCP) that enable servers to expose executable functionality to clients. Through tools, LLMs can interact with external systems, perform computations, and take actions in the real world.
In our demo, the client will be Visual Studio Code. It will connect to an MCP server over HTTPS to utilize the document search tool. This tool allows us to retrieve duplicate content that services like Copilot for Azure have access to in the Microsoft Learn semantic search index. By using this index, we can ground our responses in the current documentation. For example, the system will know that Azure Active Directory is now called Entra ID or which services are generally available within a specific region.