io.github.neo4j-contrib/mcp-neo4j-memory MCP Server
io.github.neo4j-contrib/mcp-neo4j-memory
Store and retrieve personal knowledge graphs in Neo4j across sessions and clients.
What is the io.github.neo4j-contrib/mcp-neo4j-memory MCP server?
The Neo4j Memory MCP server stores and retrieves entities and relationships from a personal knowledge graph in a local or remote Neo4j instance. It enables persistent memory access across different sessions, conversations, and clients, allowing AI assistants to maintain and query contextual information over time.
This server provides a knowledge graph memory layer for AI assistants, letting you store facts, entities, and relationships in Neo4j and access them across multiple conversations and sessions. Use it to build persistent context that your AI assistant can reference and update, creating a growing knowledge base of information you've shared.
How to install io.github.neo4j-contrib/mcp-neo4j-memory
Copy-paste configuration for popular MCP clients.
NEO4J_URIrequiredNeo4j connection URI
NEO4J_USERNAMErequiredNeo4j username
NEO4J_PASSWORDrequiredsecretNeo4j password
NEO4J_DATABASENeo4j database name
NEO4J_NAMESPACETool namespace prefix
Tools & capabilities
Tools this server exposes to the agent.
Store entities and relationships— Add facts, entities, and relationships to your personal knowledge graph in Neo4jRetrieve entities and relationships— Query and retrieve stored entities and relationships from your knowledge graphAccess across sessions— Retrieve stored knowledge graph data across different sessions, conversations, and clients
Use cases
- Build a persistent knowledge base of facts and relationships that Claude remembers across conversations
- Store information about people, projects, and work you've done for later reference
- Maintain a personal graph of entities and their connections that grows over time
- Query your knowledge graph to retrieve contextual information in new conversations
- Create a unified memory system accessible from Claude Desktop, Cursor, or other MCP clients
io.github.neo4j-contrib/mcp-neo4j-memory MCP server FAQ
It's an MCP server that stores and retrieves entities and relationships in a Neo4j knowledge graph, enabling persistent memory across multiple AI assistant sessions and conversations.
Yes, the server is open-source under the MIT License. You'll need access to a Neo4j instance (local or remote) to store your knowledge graph.
Install via PyPI: `pip install mcp-neo4j-memory`, then configure it in your MCP client's settings to connect to your Neo4j instance.
You need a local or remote Neo4j instance. The server connects to your Neo4j database to store and retrieve graph data.
Yes, since the knowledge graph is stored in a central Neo4j instance, you can access the same data from Claude Desktop, Cursor, Windsurf, or other MCP clients.
No, this is part of Neo4j Labs and is maintained by the Field GenAI team. It's actively developed but not officially supported by the Neo4j product team. The official product server is available separately.
README (reference)
Source of truth, from the repository.
Neo4j Labs MCP Servers
Neo4j Labs
These MCP servers are a part of the Neo4j Labs program. They are developed and maintained by the Neo4j Field GenAI team and welcome contributions from the larger developer community. These servers are frequently updated with new and experimental features, but are not supported by the Neo4j product team.
They are actively developed and maintained, but we don’t provide any SLAs or guarantees around backwards compatibility and deprecation.
If you are looking for the official product Neo4j MCP server please find it here.
Overview
Model Context Protocol (MCP) is a standardized protocol for managing context between large language models (LLMs) and external systems.
This lets you use Claude Desktop, or any other MCP Client (VS Code, Cursor, Windsurf, Gemini CLI), to use natural language to accomplish things with Neo4j and your Aura account, e.g.:
- What is in this graph?
- Render a chart from the top products sold by frequency, total and average volume
- List my instances
- Create a new instance named mcp-test for Aura Professional with 4GB and Graph Data Science enabled
- Store the fact that I worked on the Neo4j MCP Servers today with Andreas and Oskar
Servers
mcp-neo4j-cypher - natural language to Cypher queries
Get database schema for a configured database and execute generated read and write Cypher queries on that database.
Requirement: Requires the APOC plugin to be installed and enabled on the Neo4j instance for schema inspection.
mcp-neo4j-memory - knowledge graph memory stored in Neo4j
Store and retrieve entities and relationships from your personal knowledge graph in a local or remote Neo4j instance. Access that information over different sessions, conversations, clients.
mcp-neo4j-cloud-aura-api - Neo4j Aura cloud service management API
Manage your Neo4j Aura instances directly from the comfort of your AI assistant chat.
Create and destroy instances, find instances by name, scale them up and down and enable features.
mcp-neo4j-data-modeling - interactive graph data modeling and visualization
Create, validate, and visualize Neo4j graph data models. Allows for model import/export from Arrows.app.
Transport Modes
All servers support multiple transport modes:
- STDIO (default): Standard input/output for local tools and Claude Desktop integration
- SSE: Server-Sent Events for web-based deployments
- HTTP: Streamable HTTP for modern web deployments and microservices
HTTP Transport Configuration
To run a server in HTTP mode, use the --transport http flag:
# Basic HTTP mode
mcp-neo4j-cypher --transport http
# Custom HTTP configuration
mcp-neo4j-cypher --transport http --host 127.0.0.1 --port 8080 --path /api/mcp/
Environment variables are also supported:
export NEO4J_TRANSPORT=http
export NEO4J_MCP_SERVER_HOST=127.0.0.1
export NEO4J_MCP_SERVER_PORT=8080
export NEO4J_MCP_SERVER_PATH=/api/mcp/
mcp-neo4j-cypher
Cloud Deployment
All servers in this repository are containerized and ready for cloud deployment on platforms like AWS ECS Fargate and Azure Container Apps. Each server supports HTTP transport mode specifically designed for scalable, production-ready deployments with auto-scaling and load balancing capabilities.
📋 Complete Cloud Deployment Guide →
The deployment guide covers:
- AWS ECS Fargate: Step-by-step deployment with auto-scaling and Application Load Balancer
- Azure Container Apps: Serverless container deployment with built-in scaling and traffic management
- Configuration Best Practices: Security, monitoring, resource recommendations, and troubleshooting
- Integration Examples: Connecting MCP clients to cloud-deployed servers
Contributing
Contributions are welcome! Please feel free to submit a Pull Request.
Blog Posts
- Everything a Developer Needs to Know About the Model Context Protocol (MCP)
- Claude Converses With Neo4j Via MCP - Graph Database & Analytics
- Building Knowledge Graphs With Claude and Neo4j: A No-Code MCP Approach - Graph Database & Analytics
- Using the Neo4j Extension in Gemini CLI
License
MIT License
Related MCP servers
Neo4j GDS Agent
Run Neo4j Graph Data Science algorithms through Claude, Cursor, and other LLMs via MCP.
Manage Neo4j Aura database instances via natural language through Claude and other MCP clients.
io.github.neo4j-contrib/mcp-neo4j-cypher
Run Cypher queries against Neo4j databases using natural language.
Create, validate, and visualize Neo4j graph data models with interactive tools and Arrows.app integration.
Opinionated sprint tracker. Read/update tickets, sprints, velocity from Claude/Cursor/Zed.