All Aboard: Reasoning with LLMs and Neo4j via MCP

Session Track: Knowledge Graphs

Session Time: 04:00 pm - 04:15 pm November 6

Session description

Ever wondered how an AI agent could navigate the London Underground? This lightning session introduces the official MCP server for Neo4j—your bridge between LLMs, agents, and the graph. We’ll explore how graphs unlock more powerful reasoning for analysis questions, using a graph model of the London Tube as our test case. Watch as an agent queries Neo4j via MCP to answer real questions about the network, and get a preview of upcoming features that make it easier than ever to bring graphs into your AI workflows. You’ll leave ready to try the MCP server yourself and start building graph-powered AI experiences.

Speakers

Jonathan Giffard

Senior Product Manager, Neo4j

Jonathan Giffard is a Senior Product Manager at Neo4j, focused on developer surfaces—the tools and interfaces that connect developers to the graph. His work spans MCP servers, platform drivers, web services, and the GraphQL library. Originally trained as a software engineer, he jokingly describes his degree as a “Drinker’s Degree.” Outside of work, Jonathan can usually be found running, riding his Triumph motorcycle, or serving as both financier and chauffeur to his children.

Michael Webb

Software Engineer, Neo4j

Michael is a Software Engineer at Neo4j working on the GraphQL team. https://github.com/neo4j/graphql/