This Week in Neo4j: MCP, Snowflake, GenAI, GraphRAG and more

Senior Developer Marketing Manager

April 26, 2025

3 min read

Welcome to This Week in Neo4j, your fix for news from the world of graph databases!

The dominating topic these days is MCP (Model Context Protocol) with a recent announcement by Docker where the Neo4j MCP server is part of their catalogue and toolkit.
Also, this week, we dive into integrating Neo4j with Snowflake, enhance RAG systems with Pinecone and deploy GraphRAG on Databricks.

NODES 2025 is back on November 6 — our global, 24-hour graph dev conference spotlighting real-world apps, intelligent systems and all things Neo4j. The Call for Papers is open through June 15, so take the chance to share your code, models and graph-powered insights with the community!

Happy Graphing,

Alexander Erdl

COMING UP!

Livestream: Neo4j Live: How to Build a Knowledge Graph on April 30
Conferences: Find us at JAX, Mainz & Knowledge Graph Conference, NYC on May 5-9, AI Agent Conference, NYC on May 6-7 & Data Innovation Summit, Stockholm on May 7-8
Meetup: Meet us in Cologne, DE on April 29
All Neo4j Events: Webinars and More
GraphSummit Series: Transform Your Enterprise with Graph and GenAI – Next Stop: Singapore on May 20

FEATURED COMMUNITY MEMBER: Yoan Sallami

Yoan is an expert in neuro-symbolic cognitive architectures and is building tomorrow’s LLM-based agent system using graphs and symbolic AI.

Connect with him on LinkedIn.

In a livestream “Neo4j Live: HybridAGI – Graph-Powered, Self-Programmable AI”, he combined graph and LLM capabilities, allowing users to create secure, memory-centric AI applications with deterministic behaviour and extensive customisation through Cypher.

MCP: Everything a Developer Needs to Know About the Model Context Protocol (MCP)

Michael Hunger introduces MCP as a universal protocol designed to seamlessly connect AI models with external tools, data sources, and APIs. The article also discusses MCP’s architecture, its integration with Neo4j and its potential for creating more interactive and context-aware AI systems.

He also shared more details in our MCP Developer Pages and our latest episode of Discover Neo4j AuraDB.

SNOWFLAKE: Querying data from Neo4j to Snowflake

Mauricio Rojas provides a practical guide on integrating Neo4j with Snowflake in this article. He outlines a step-by-step process for exporting graph data from Neo4j and importing it into Snowflake, facilitating seamless data analysis across both platforms.

GENAI: GenAI blood, sweat, and tears: Loading data to Pinecone

In her blog post, Jennifer Reif explores the integration of vector search and graph traversal to improve Retrieval-Augmented Generation (RAG) systems. She discusses how combining these methods can enhance the retrieval of relevant information, particularly in complex domains where understanding relationships between entities is crucial. The post provides insights into the benefits of this hybrid approach and its potential applications in knowledge-intensive tasks.

GRAPHRAG: Building, Improving, and Deploying Knowledge Graph RAG Systems on Databricks

Andrea Santurbano, Chandhana Padmanabhan, Jiayi Wu and Dan Pechi enhance Retrieval-Augmented Generation (RAG) applications by integrating Neo4j knowledge graphs with Databricks. They combine structured graph data with unstructured sources and showcase a hybrid approach that applies vector search and graph traversal for more precise and context-aware AI outputs.

CONTINUOUS LEARNING

GraphAcademy: Learn to build apps with Neo4j in our Development Courses using drivers and frameworks like Python, Java or Spring Data
Workshops: Learn with us in San Francisco, US on May 5 & Sunnyvale, US on May 6
Get to Know Graph: Level up your graph skills with webinars packed with practical insights to help you build powerful apps
Learn on Your Schedule: Go deeper into graph technology on Neo4j’s On-Demand webinar library
New Webinar: Customer Conversations: Cummins – AI-Ready Data Stack With Graph – AMER, EMEA, Asia Pacific