Neo4j Memory
Provides AI assistants with persistent graph-based memory capabilities using Neo4j, enabling semantic search, relationship tracking, and knowledge organization across multiple project contexts.
What is Neo4j Memory?
Neo4j Memory is a Model Context Protocol (MCP) server that allows AI assistants like Claude, Cursor, and VS Code to provides ai assistants with persistent graph-based memory capabilities using neo4j, enabling semantic search, relationship tracking, and knowledge organization across multiple project contexts.
Provides AI assistants with persistent graph-based memory capabilities using Neo4j, enabling semantic search, relationship tracking, and knowledge organization across multiple project contexts.
This server falls under the Knowledge & Memory category on MCPgee, the world's largest MCP server directory with 33,000+ servers.
Features
- Provides AI assistants with persistent graph-based memory ca
Use Cases
Maintainer
Works with
Installation
Manual Installation
npx neo4j-memory-serverConfiguration
Configuration Details
claude_desktop_config.json
Performance
Response Metrics
Resource Usage
How to Set Up and Use Neo4j Memory
The Neo4j Memory MCP Server gives AI assistants durable, graph-based long-term memory backed by a Neo4j database, enabling them to store observations, form relationships between concepts, and retrieve context across sessions using semantic vector search, exact matching, and graph traversal. Unlike flat-file or in-process memory solutions, it persists structured knowledge that survives conversation resets and can be organized across multiple project databases. It is ideal for developers who want their AI assistant to accumulate knowledge about a codebase, project decisions, or personal context over time.
Prerequisites
- A running Neo4j or DozerDB instance with the Graph Data Science (GDS) plugin enabled (required for vector/semantic search)
- Docker (recommended for running DozerDB with GDS in a single command)
- Node.js and npx available for running the MCP server package
- NEO4J_URI, NEO4J_USERNAME, and NEO4J_PASSWORD credentials for your database
- An MCP-compatible client such as Claude Desktop
Start a Neo4j/DozerDB instance with GDS
Use Docker to run DozerDB (a Neo4j-compatible distribution with GDS pre-installed). This is required for the semantic vector search capability.
docker run -p 7474:7474 -p 7687:7687 \
-v $HOME/neo4j/data:/data \
--env NEO4J_AUTH=neo4j/your-password \
graphstack/dozerdb:latestVerify the database is running
Open the Neo4j Browser at http://localhost:7474 and log in with your credentials to confirm the database is healthy.
open http://localhost:7474Install the MCP server package
Install the Neo4j memory MCP server from npm so it is available via npx.
npm install -g @sylweriusz/mcp-neo4j-memory-serverConfigure Claude Desktop
Add the server to your Claude Desktop config file with the three required Neo4j environment variables.
# See the configuration example belowRestart Claude Desktop and verify memory tools
After saving the config file, restart Claude Desktop. The tools memory_store, memory_find, memory_modify, and database_switch should appear in the available tools list.
Neo4j Memory Examples
Client configuration
Claude Desktop configuration for the Neo4j Memory MCP server with database connection credentials.
{
"mcpServers": {
"memory": {
"command": "npx",
"args": ["-y", "@sylweriusz/mcp-neo4j-memory-server"],
"env": {
"NEO4J_URI": "bolt://localhost:7687",
"NEO4J_USERNAME": "neo4j",
"NEO4J_PASSWORD": "your-password"
}
}
}
}Prompts to try
Example prompts that leverage persistent graph memory across conversations.
- "Remember that we decided to use PostgreSQL for the user service because of ACID compliance requirements."
- "What architectural decisions have we recorded for the payments project?"
- "Store an observation that the API rate limit is 100 requests per minute and link it to the Stripe integration entity."
- "Find all memories related to authentication from the last 7 days."
- "Switch to the 'mobile-app' project database and recall our UI design decisions."Troubleshooting Neo4j Memory
Semantic search returns no results even though memories were stored
Semantic vector search requires the Graph Data Science (GDS) plugin. Use DozerDB instead of standard Neo4j Community Edition, or install GDS manually on your Neo4j Enterprise instance.
Connection refused when npx tries to reach bolt://localhost:7687
Ensure the Docker container is running with port 7687 mapped. If Neo4j started on a different port or host, update NEO4J_URI accordingly. Check with 'docker ps' to confirm the container is up.
Authentication error: NEO4J_AUTH credentials rejected
The username and password in your .env or config must exactly match the value passed to --env NEO4J_AUTH when starting Docker. The default format is 'username/password' for Docker but the env vars for the MCP server are separate (NEO4J_USERNAME and NEO4J_PASSWORD).
Frequently Asked Questions about Neo4j Memory
What is Neo4j Memory?
Neo4j Memory is a Model Context Protocol (MCP) server that provides ai assistants with persistent graph-based memory capabilities using neo4j, enabling semantic search, relationship tracking, and knowledge organization across multiple project contexts. It connects AI assistants to external tools and data sources through a standardized interface.
How do I install Neo4j Memory?
Follow the installation instructions on the Neo4j Memory GitHub repository. Clone the repo, install dependencies, and add the server config to your AI client.
Which AI clients work with Neo4j Memory?
Neo4j Memory works with all major MCP-compatible AI clients including Claude Desktop, Claude Code, Cursor, VS Code (GitHub Copilot), Windsurf, and Cline.
Is Neo4j Memory free to use?
Yes, Neo4j Memory is open source and available under the MIT License license. You can use it freely in both personal and commercial projects.
Neo4j Memory Alternatives — Similar Knowledge & Memory Servers
Looking for alternatives to Neo4j Memory? Here are other popular knowledge & memory servers you can use with Claude, Cursor, and VS Code.
MemPalace
★ 52.6kA local AI memory system that stores all conversations verbatim and organizes them into navigable structures. It provides 19 MCP tools for AI assistants to search and retrieve past decisions, debugging sessions, and architecture debates automatically
Kratos
★ 25.7k🏛️ Memory System for AI Coding Tools - Never explain your codebase again. MCP server with perfect project isolation, 95.8% context accuracy, and the Four Pillars Framework.
Context Mode
★ 15.4kAn MCP server that preserves LLM context by intercepting large data outputs and returning only concise summaries or relevant sections. It enables efficient sandboxed code execution, file processing, and documentation indexing across multiple programm
Memu
★ 13.7kMemory for 24/7 proactive agents like OpenClaw.
MemOS
★ 9.3kMemOS (Memory Operating System) is a memory management operating system designed for AI applications. Its goal is: to enable your AI system to have long-term memory like a human, not only remembering what users have said but also actively invoking, u
Everos
★ 5.4kBuild, evaluate, and integrate long-term memory for self-evolving agents.
Browse More Knowledge & Memory MCP Servers
Explore all knowledge & memory servers available in the MCPgee directory. Each server includes setup guides for Claude, Cursor, and VS Code.
Set Up Neo4j Memory in Your Editor
Choose your AI client for step-by-step setup instructions.
Quick Config Preview
Add this to your claude_desktop_config.json or .cursor/mcp.json
Ready to use Neo4j Memory?
Browse our complete directory of 33,000+ MCP servers, read setup guides for your editor, and start building with the Model Context Protocol.