Neo4j Knowledge Graph MCP server

The MCP Neo4j Knowledge Graph Memory Server leverages Neo4j's graph database capabilities to store and retrieve information from AI assistant-user interactions. It provides enhanced functionality compared to the official Knowledge Graph Memory Server by offering more powerful graph querying, better performance, and scalability - ideal for complex knowledge graph applications.

Installation Requirements

Prerequisites

• Node.js >= 22.0.0
• Neo4j database (local or remote)

Installing via npm

# Global installation
npm install -g @jovanhsu/mcp-neo4j-memory-server

# Or as a project dependency
npm install @jovanhsu/mcp-neo4j-memory-server

Using Docker

# Start Neo4j and Memory Server with docker-compose
git clone https://github.com/JovanHsu/mcp-neo4j-memory-server.git
cd mcp-neo4j-memory-server
docker-compose up -d

Environment Configuration

The server uses the following environment variables:

Integrating with Claude

Configuring in Claude Desktop

Add the following to your claude_desktop_config.json:

{
  "mcpServers": {
    "graph-memory": {
      "command": "npx",
      "args": [
        "-y",
        "@izumisy/mcp-neo4j-memory-server"
      ],
      "env": {
        "NEO4J_URI": "neo4j://localhost:7687",
        "NEO4J_USER": "neo4j",
        "NEO4J_PASSWORD": "password",
        "NEO4J_DATABASE": "memory"
      }
    }
  }
}

Using with Claude Web via MCP Inspector

1. Install MCP Inspector
2. Start the Neo4j Memory Server:

   npx @jovanhsu/mcp-neo4j-memory-server
   

3. In another terminal, start MCP Inspector:

   npx @modelcontextprotocol/inspector npx @jovanhsu/mcp-neo4j-memory-server
   

4. Access the MCP Inspector interface in your browser

Usage Guide

Claude Custom Instructions

Add the following to your Claude custom instructions:

Follow these steps for each interaction:

1. User Identification:
   - You should assume that you are interacting with default_user
   - If you have not identified default_user, proactively try to do so.

2. Memory Retrieval:
   - Always begin your chat by saying only "Remembering..." and search relevant information from your knowledge graph
   - Create a search query from user words, and search things from "memory". If nothing matches, try to break down words in the query at first ("A B" to "A" and "B" for example).
   - Always refer to your knowledge graph as your "memory"

3. Memory
   - While conversing with the user, be attentive to any new information that falls into these categories:
     a) Basic Identity (age, gender, location, job title, education level, etc.)
     b) Behaviors (interests, habits, etc.)
     c) Preferences (communication style, preferred language, etc.)
     d) Goals (goals, targets, aspirations, etc.)
     e) Relationships (personal and professional relationships up to 3 degrees of separation)

4. Memory Update:
   - If any new information was gathered during the interaction, update your memory as follows:
     a) Create entities for recurring organizations, people, and significant events
     b) Connect them to the current entities using relations
     b) Store facts about them as observations

API Usage Example

To use this server in your own application via the MCP protocol:

import { McpClient } from '@modelcontextprotocol/sdk/client/mcp.js';
import { StdioClientTransport } from '@modelcontextprotocol/sdk/client/stdio.js';

// Create client
const transport = new StdioClientTransport({
  command: 'npx',
  args: ['-y', '@izumisy/mcp-neo4j-memory-server'],
  env: {
    NEO4J_URI: 'bolt://localhost:7687',
    NEO4J_USER: 'neo4j',
    NEO4J_PASSWORD: 'password',
    NEO4J_DATABASE: 'neo4j'
  }
});

const client = new McpClient();
await client.connect(transport);

// Create entities
const result = await client.callTool('create_entities', {
  entities: [
    {
      name: 'User',
      entityType: 'Person',
      observations: ['Likes programming', 'Uses TypeScript']
    }
  ]
});

console.log(result);

Neo4j Data Model

The knowledge graph is stored in Neo4j using the following model:

(Entity:EntityType {name: "Entity Name"})
(Entity)-[:HAS_OBSERVATION]->(Observation {content: "Observation content"})
(Entity1)-[:RELATION_TYPE]->(Entity2)

How to add this MCP server to Cursor

There are two ways to add an MCP server to Cursor. The most common way is to add the server globally in the ~/.cursor/mcp.json file so that it is available in all of your projects.

If you only need the server in a single project, you can add it to the project instead by creating or adding it to the .cursor/mcp.json file.

Adding an MCP server to Cursor globally

To add a global MCP server go to Cursor Settings > MCP and click "Add new global MCP server".

When you click that button the ~/.cursor/mcp.json file will be opened and you can add your server like this:

{
    "mcpServers": {
        "cursor-rules-mcp": {
            "command": "npx",
            "args": [
                "-y",
                "cursor-rules-mcp"
            ]
        }
    }
}

Adding an MCP server to a project

To add an MCP server to a project you can create a new .cursor/mcp.json file or add it to the existing one. This will look exactly the same as the global MCP server example above.

How to use the MCP server

Once the server is installed, you might need to head back to Settings > MCP and click the refresh button.

The Cursor agent will then be able to see the available tools the added MCP server has available and will call them when it needs to.

You can also explictly ask the agent to use the tool by mentioning the tool name and describing what the function does.