Agents, Tools, and MCP, oh my! Next-level AI concepts for developers

AI is evolving fast, and so are the ways developers can integrate it into tech systems. A flurry of new approaches and tools surfaces every week, and it’s hard to know where to focus.

In this session, we will pull back the curtain on the next wave of AI development with agents, tool integrations, and Model Context Protocol (MCP). We will break down what AI agents are, how they interact with tools and APIs, and why context is critical for building smarter, more reliable applications. Next, we will look at MCP and how it standardizes communication between AI models and external systems.
Along the way, we will touch on related concepts and step through code and demos, giving you a complete roadmap to level up your AI skills. You won’t need a yellow brick road to follow along, but you will discover some magical new tricks to level up your AI skills!
Code: https://github.com/JMHReif/agents-mcp-ohmy

Transcript

1. Agents, Tools, and MCP, oh my! Next-level AI concepts for developers Jennifer Reif jennifer.reif@neo4j.com @JMHReif github.com/JMHReif jmhreif.com linkedin.com/in/jmhreif/
2. About Jennifer Developer advocate, Neo4j • Java champion • Builder, coder, tech learner • Tech speaker/blogger/podcaster/author • Other: reader, mom, cat mom, etc • Coming soon! ai rstprogramming.com/ Jennifer Reif fi jennifer.reif@neo4j.com @JMHReif github.com/JMHReif jmhreif.com linkedin.com/in/jmhreif/
3. The AI Stack in 2026 Complexity vs Value Evals / Guardrails / Security Memory / State / History Agentic work ows / Agents Advanced RAG / GraphRAG Vector RAG / naive RAG / easy RAG fl LLMs
4. Act 1: Overture
5. Reality The “magic” of AI • Works in demo • Hallucinated API calls • Fragile integrations • Complexity overwhelm • Optimization nightmares
6. Demo: LLM alone fi Lacks speci c context and personalization
7. Act 2: Agents + Tools
8. What is an AI Agent? Reasoning loop 1. Receive input 2. Reason 3. Select tool 4. Execute 5. Observe result 6. Respond
9. Separate the responsibilities Traditional tech + GenAI • LLM -> decision • Agent -> coordination • Application -> execution
10. AI Agents… Plan, reason, and execute tasks for users • Four Key Components: • Model: reason, plan, respond • Tools: fetch, act, call • Orchestration: remember, track • Runtime: execute
11. Prompts to structured tool calling Providing ways to ask for help • Solved -> prompt fragility • Provided: • De ned tool methods • Typed parameters • Schema enforcement fi • Deterministic execution
12. Demo: Tool calling fl Adds exibility with educated guidance
13. Shift of control Back into the hands of developers!
14. Act 3: Context is key
15. Why prompts aren’t enough -> context engineering • LLMs are taking it all • Prompt • Data • Previous highlights • Repetitive for each request! https://neo4j.com/blog/agentic-ai/hands-on-with-context-graphs-and-neo4j/
16. Retrieval strategies • Embedding-based retrieval • Structured database queries • Additional traversal (e.g. graph) • Conversation state
17. Memory is a system responsibility Doesn’t live in the model • LLMs are stateless • Every request is independent • Conversation history stored externally • Domain knowledge retrieved intentionally • Memory is infrastructure, not a prompt trick
18. Graph as application memory • Short-term memory • Conversation state • Long-term memory • Users <-> Preferences • Why graph? • Relationships are explicit • Context retrieval = deterministic and precise -> see Neo4j’s Agent Memory project
19. Demo: Conversation memory Adds context over time and repetition
20. Act 4: Decoupling
21. Agent scaling problem • Initial agent construction: • Manual tool wiring • Model-speci c integrations • Tight coupling fi • Hard to swap providers
22. The solution…. Model Context Protocol (MCP) • Open protocol • Provides: • Tool discovery • Capability descriptions • Structured invocation • Standard responses • Universal adapter for AI -> New spec release July 2026!
23. MCP architecture Stateless, request/response
24. Architecture with MCP + Neo4j
25. Demo: Tool discovery Adds modularity and agility
26. Act 5: Tying it together
27. Sneak preview… What comes next • Agent security • MCP attack vector • Evaluation harnesses • Multi-agent frameworks
28. Four layers of modern AI systems • 🧠 - LLM reasoning • ✋ - tool execution • 🗂 - graph-powered context • 🔌 - MCP standardization
30. Resources • Code: github.com/JMHReif/agents-mcp-ohmy • Graphacademy AI courses: graphacademy.neo4j.com/categories/generative-ai • NODES 2026: neo4j.com/nodes • Knowledge graph ebook: dev.neo4j.com/jmhreif-kg-ebook Jennifer Reif jennifer.reif@neo4j.com @JMHReif github.com/JMHReif jmhreif.com linkedin.com/in/jmhreif/