From Single-Shot LLMs to Intelligent Agents: Building Scalable AI Systems with Spring AI and MCP
summary
Shows a practical stack for building agentic systems using Spring AI, the Model Context Protocol (MCP) and the MCP Java SDK, with live code: a chat client with advisors and chat memory, an audio roundtrip demo (Marvin) that produces playable speech, and a weather tool that the model invokes via tool calling rather than static prompts. Demonstrates wiring MCP servers (Brave search, local filesystem), dynamic capabilities discovery, thousands of public MCP servers, and writing a generated summary file — integrations run end-to-end.
AI-written summary · about
chapters (11)
- 0:00Scalable AI systems intro
- 3:37What defines agentic systems
- 12:08Spring AI prompt features
- 15:39Multimodality in Spring AI
- 20:36Tools and tool calling
- 27:18Model Context Protocol role
- 31:59Creating MCP servers
- 41:14Third-party MCP servers
- 45:34Agentic patterns workflows
- 49:50Orchestrator workflow
- 53:00Demo and closing
related talks
27mBuilding AI Agents with Spring & MCP
52mBeyond local tools: Deep dive into MCP with Spring AI
32mFrom Monolith to AI Agent Modernizing Java Systems with MCP
26mBuilding AI-Enabled Spring Applications with Model Context Protocol (MCP)
24mBuilding Agentic Applications with Spring AI
40mBuilding AI Agents with Spring & MCP
49mBuilding AI Agents with Spring & MCP
30mComposable AI: Building Next-Gen AI Agents with MCP