MCP Resources & Prompts Explained | Beyond MCP Tools | FDE Full Course #15

FDE Full Course #15 In the last video, we learned how an MCP Server exposes **Tools** that an LLM can discover and call. But Tools are only one part of MCP. In this video, we complete the MCP Server picture by understanding **Resources and Prompts** — what they are, why they exist, and how they are different from Tools. We’ll first understand MCP Resources from first principles: how a server can expose contextual information such as documentation, policies, application data, or project information, and how an MCP Client can discover and read those Resources. Then we’ll look at an important question: **If Resources are application-controlled, how does an AI application decide which Resource should become part of the LLM context?** We’ll discuss different approaches including user selection, application state, retrieval, and LLM-based routing. After that, we’ll explore **MCP Prompts** — reusable prompt templates exposed by an MCP Server. We’ll see how prompt arguments work and how Prompts can provide reusable workflows such as “Plan My Day”. Finally, we’ll combine all three MCP primitives in one simple project: **Tools → Model Controlled** **Resources → Application Controlled** **Prompts → User Controlled** ### Topics covered - Quick recap of MCP Tools - Why MCP Resources are needed - Tools vs Resources - Resource URI, name, description and MIME type - `resources/list` and `resources/read` - Static and dynamic Resources - Resource Templates - How applications select relevant Resources - Creating Resources with Spring AI - What MCP Prompts are - Prompt arguments - `prompts/list` and `prompts/get` - Creating Prompts with Spring AI - Using Tools, Resources and Prompts together - Model-controlled vs application-controlled vs user-controlled MCP primitives By the end of this video, you’ll have a clear mental model of what an MCP Server can expose and how **Tools, Resources and Prompts work together inside an AI application**. This series focuses on the core concepts behind Forward Deployed Engineering and AI application development. Spring Boot and Spring AI are used for the implementation, but the concepts remain language-independent. #MCP #ModelContextProtocol #SpringAI #GenerativeAI #AIEngineering #LLM #SpringBoot #FDE #ForwardDeployedEngineer ------------------------------------------------------------------------------------------------------------- Code and Notes: Github : https://github.com/adityatandon15/Forward-Deployed-Engineer-Full-Course Spring Boot Full Course : https://youtube.com/playlist?list=PLEYgx5hMdopw&si=o1Njda0XgYXwg4xs JAVA Full Course Series : https://youtube.com/playlist?list=PLQEaRBV9gAFsR15tNo2QLF9d2qc-c018p&si=4qQP_euMTZMvAwNu Join our WhatsApp Group: https://www.whatsapp.com/channel/0029VbBF1XKF1YlMyYuPM23s We have paid courses on DSA, Web Development , Blockchain, System Design & GenAI. Join Courses: https://strikes.in/ Coder Army Website: https://coderarmy.in/#home Coder Army App: https://play.google.com/store/apps/details?id=com.rohit.negi Connect with Aditya Tandon Instagram : https://www.instagram.com/itsadityatandon LinkedIn : https://www.linkedin.com/in/adityatandon2 Twitter : https://x.com/adityatandon02 Timestamps: