In the previous module, we established a foundational understanding of the Model Context Protocol (MCP)'s core architecture, including its client-server model, transport mechanisms, and message types. With that groundwork laid, we now turn our attention to the heart of MCP: the primary capabilities that MCP servers expose to clients and, by extension, to Large Language Models (LLMs).
This module, **"Core MCP Capabilities: Context and Actions,"** will dive deep into the specific features that empower LLMs to interact with the real world and leverage external information effectively. You will learn how MCP servers provide:
* **Resources:** Structured data that LLMs can access and understand, acting as their window into relevant information.
* **Tools:** Mechanisms that enable LLMs to perform real-world actions, bridging the gap between language understanding and practical execution.
* **Prompts:** Reusable templates for interactions, ensuring consistent and effective communication with LLMs.
* **Sampling:** A feature that facilitates LLM completions, allowing for controlled and efficient generation of responses.
By the end of this module, you will have a comprehensive understanding of these core capabilities, equipping you with the knowledge to design and implement sophisticated LLM applications that can retrieve context, execute actions, and generate intelligent outputs through the power of MCP.
