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. Jennifer Reif jennifer.reif@neo4j.com @JMHReif github.com/JMHReif jmhreif.com linkedin.com/in/jmhreif/ Agents, Tools, and MCP, oh my! Next-level AI concepts for developers
2. About Jennifer Developer advocate, Neo4j • Java champion • Builder, coder, tech learner • Tech speaker/blogger/podcaster/author • Other: reader, mom, cat mom, etc Jennifer Reif jennifer.reif@neo4j.com @JMHReif github.com/JMHReif jmhreif.com linkedin.com/in/jmhreif/
3. Layers of AI Still holds • More layers = better result • Complexity vs value
4. Example of layers In tech systems Traditional systems Vector search / naive RAG / easy RAG Advanced RAG / GraphRAG Agentic work fl ows / Agents Evals / Guardrails / Security Memory / State / History
5. Code - traditional systems
6. Recap! Problem with traditional systems • Hard-coded to answer speci fi c questions • Can’t handle/understand variations • Parameterization adds limited fl exibility
7. RAG and GraphRAG
8. Vector search for RAG
9. GraphRAG Patterns
10. Recap! Problem with RAG systems • Handles semantic similarity • Natural language variations • Answers new category of questions • Can’t handle narrow questions • In fl exible answer process • Only as good as the data Pros Cons
11. Agentic workflows / Agents
12. What is an agent? Software system “gopher” • What it does: • Accomplish task(s) to achieve a goal • How it does it: • Work fl ows -> Autonomous system
13. Agentic workflow vs Agent Make recipe vs Make meal • Complete series of steps • Handle speci fi c task • Prescriptive autonomy • Consistent, reliable outcome • Complete objective • Handle general goals • Autonomous reasoning • Flexible, variable path + outcome
14. Agentic example Work fl ow vs agent Process the migration to test env Produce a project plan for deployment
15. How do I decide? Work fl ow vs Agent • Level of autonomy you allow = • + How detailed/complex the task is • + How speci fi c outcome should be • + Criticality of quality result • + Skill of LLM for your particular domain/use case
16. AI Agents… Plan, reason, and execute tasks for users • Four Key Components: • Model: reason over goals, determine plan, generate response • Tools: fetch data, perform actions/ transactions by calling other APIs or services • Orchestration: maintain memory and state (including approach to plan), tools, data provided/fetched, etc • Runtime: execute the system when invoked
17. Demo!
18. Recap! Problem with agents • Flexibility in which tool(s) to use • Understand natural language input • Accept variations of input • Still hard-coded methods • No standard implementation • Vendor, context, tool lock-in Pros Cons
19. The solution…. Model Context Protocol (MCP) • Open protocol • Universal adapter for AI - standardizes: • How applications provide context to LLMs • Connecting AI to data sources and tools
20. MCP Solves Agent Challenges Client-server architecture 1. Independent 2. Consistent 3. Scoped 4. Composable Architecture Tools Trust
21. MCP architecture
22. Demo!
24. Resources • Code: github.com/JMHReif/agents-mcp-ohmy • Graphacademy AI courses: graphacademy.neo4j.com/knowledge-graph-rag • NODES AI 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/