The Fastest Path To Building An Agent For Your Knowledge Graph Is By Using MCP
summary
Claim: the fastest practical route to a knowledge-graph agent is to expose Neo4j as MCP tools and use an Aura/agent front end to call them. The demo wires up the Neo4j Cipher MCP server (Python/TypeScript SDK) to Cursor and Cloud Desktop, exposes three tools (get schema, read Cypher, write Cypher), loads sample data, finds and fixes a syntax error via the MCP inspector, and runs queries (recommendation returns none because the user has no overlapping purchases). Notes: memory MCP builds a KG of memories, models vary on tool-calling, and authorization and token bloat are real risks. Aura agent
AI-written summary · about
chapters (8)
- 0:00Introduction and speaker intro
- 2:38What is MCP overview
- 8:19Neo4j MCP ecosystem
- 14:24Exploratory data analysis demo
- 17:19Schema assisted coding demo
- 25:13AI agent memory overview
- 25:33MCP challenges and solutions
- 28:48Summary and resources
related talks
53mAgents, Tools, and Mcp, Oh My! Next Level AI Concepts for Developers
45mAgents, Tools, and MCP, oh my! Next-level AI concepts for developers
46mMCP for LLM Agents, Infrastructure APIs & Data Services
30mAgentic RAG with Knowledge Graphs Explained
18mExposing Agents as MCP servers with mcp-agent
28mSmarter MCP Servers: Using a Graph to Solve the Context Window Problem
36mPutting AI Agents to Work: A New Era of Open Source Connectivity with MCP
40mBuilding Agents with Agent Bricks and MCP