MCP.so
ログイン

MCP Neo4j Knowledge Graph Memory Server

@JovanHsu

MCP Neo4j Knowledge Graph Memory Server について

MCP Memory Server with Neo4j backend for AI knowledge graph storage

基本情報

カテゴリ

メモリとナレッジ

ライセンス

MIT

ランタイム

node

トランスポート

stdio

公開者

JovanHsu

設定

以下の設定を使って、このサーバーを MCP 対応クライアントに追加してください。

{
  "mcpServers": {
    "mcp-neo4j-memory-server-jovanhsu": {
      "command": "npx",
      "args": [
        "@jovanhsu/mcp-neo4j-memory-server"
      ]
    }
  }
}

ツール

ツールは検出されませんでした

ツールは README から自動的に抽出されます。メンテナーは ## Tools という見出しの下に記載することで、このタブに反映できます。

概要

What is MCP Neo4j Knowledge Graph Memory Server?

MCP Neo4j Knowledge Graph Memory Server is an MCP-compatible server that uses Neo4j as its backend storage engine for persisting and retrieving knowledge graphs during AI assistant interactions. It is an enhanced version of the official Knowledge Graph Memory Server, aimed at developers who need a scalable, queryable memory layer for AI conversations.

How to use MCP Neo4j Knowledge Graph Memory Server?

Install via npm (npm install -g @jovanhsu/mcp-neo4j-memory-server) or Docker. Configure environment variables NEO4J_URI, NEO4J_USER, NEO4J_PASSWORD, and NEO4J_DATABASE. Integrate with Claude Desktop by adding the server configuration to claude_desktop_config.json, or use MCP Inspector for testing. The server exposes tools to create, read, update, and delete entities, relations, and observations.

Key features of MCP Neo4j Knowledge Graph Memory Server

  • Neo4j-based high-performance graph database storage
  • Powerful fuzzy search and exact matching capabilities
  • Complete CRUD operations for entities, relations, and observations
  • Fully compatible with the MCP protocol
  • Supports complex graph queries and traversals
  • Docker support for easy deployment

Use cases of MCP Neo4j Knowledge Graph Memory Server

  • Persistent memory for AI assistants to remember user identities, preferences, and goals
  • Build complex knowledge graphs with native relationship querying
  • Scale conversational memory storage to large datasets with Neo4j’s clustering
  • Visualise and debug knowledge graphs using Neo4j’s built-in tools

FAQ from MCP Neo4j Knowledge Graph Memory Server

What advantages does this Neo4j version have over the official JSON-file version?

It offers native graph storage, high-performance Cypher queries, first-class relationship handling, built-in visualisation, and better scalability for large knowledge graphs.

What are the runtime requirements?

Node.js >= 22.0.0 and a Neo4j database (local or remote) are required.

How do I configure the server to connect to my Neo4j instance?

Set the environment variables NEO4J_URI, NEO4J_USER, NEO4J_PASSWORD, and NEO4J_DATABASE. If not set, defaults point to bolt://localhost:7687 with user neo4j and password password.

Where does the knowledge graph data live?

Data is stored in your Neo4j database. The server does not persist any data locally; all entities, relations, and observations are written into the configured Neo4j instance.

What transport protocol does the server use?

It uses the MCP protocol over stdio transport, enabling integration with Claude Desktop or any MCP client. Authentication to Neo4j is handled via environment credentials, not through the MCP layer.

コメント

「メモリとナレッジ」の他のコンテンツ