Neo4j Knowledge Graph Memory Server

🚀 MCP Neo Knowledge Graph Storage Server

MCP Neo is a high - performance, scalable, and reliable knowledge graph storage server based on Neo4j, providing easy - to - use data storage and query capabilities.

✨ Features

• High Performance: Implemented with Neo4j's native graph database, offering efficient graph data storage and query capabilities.
• Scalable: Supports the construction and query of large - scale knowledge graphs.
• High Reliability: Uses ACID transactions to ensure data consistency.
• Ease of Use: Performs entity creation, relationship connection, and observation record storage operations through the MCP protocol interface.

📦 Installation

Install

npm install @jovanhsu/mcp-neo4j-memory-server

Start

npx mcp-neo4j-memory-server

💻 Main Functions

• Entity Storage: Supports the storage of different types of knowledge graph entities.
• Relationship Connection: Can establish various types of relationships between entities.
• Observation Recording: Can add factual observation content to entities or relationships.
• Fuzzy Search: Provides flexible search capabilities based on names and types.
• Complex Query: Supports complex associated data queries.

💻 Usage Examples

Basic Usage

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

// Create client configuration
const transport = new StdioClientTransport({
  command: 'npx',
  args: ['-y', 'mcp-neo4j-memory-server'],
});

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

// Create new entities
const resultCreate = await client.callTool('create_entities', {
  entities: [
    {
      name: '张三',
      entityType: '人物',
      observations: ['喜欢编程', '使用TypeScript']
    },
    {
      name: 'Google',
      entityType: '公司',
      observations: ['总部位于美国加利福尼亚州']
    }
  ]
});

console.log('Entity creation result:', resultCreate);

// Establish relationships
const resultRelation = await client.callTool('create_relationships', {
  relationships: [
    {
      fromEntityId: resultCreate.entities[0].id, // ID of 张三
      toEntityId: resultCreate.entities[1].id,   // ID of Google
      relationType: '工作于'
    }
  ]
});

console.log('Relationship establishment result:', resultRelation);

🔧 Technical Details

Data Model

The storage structure in Neo4j is as follows:

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

Query Examples

Search for 张三 and their relationships

MATCH (a:人物 {name: '张三'}) 
OPTIONAL MATCH (a)-[r]->(b) 
RETURN a, r, b;

Find all entities associated with Google

MATCH (a)-[:工作于]->(Google:公司 {name: 'Google'})
RETURN a;

🤝 Contribution Guidelines

We welcome code contributions, issue reports, or improvement suggestions! Please follow these steps:

1. Fork this repository.
2. Create your feature branch (git checkout -b feature/amazing-feature).
3. Commit your changes (git commit -m 'Add some amazing feature').
4. Push to the branch (git push origin feature/amazing-feature).
5. Create a Pull Request.

🔗 Related Projects

• Model Context Protocol
• MCP Inspector

📄 License

This project is licensed under the MIT License - see the LICENSE file for details.

📞 Contact Information

• GitHub: https://github.com/JovanHsu/mcp-neo4j-memory-server
• NPM: https://www.npmjs.com/package/@jovanhsu/mcp-neo4j-memory-server
• Author: JovanHsu