広告掲載
MCP.so
ログイン

MCP Neo4j Remote Server

@artur-nohup

リポジトリ

基本情報

カテゴリ

開発者ツール

トランスポート

stdio

作者

artur-nohup

MCP Neo4j Remote Server について

Remote MCP Neo4j Memory Server with OAuth 2.1 and API Key Authentication - TypeScript implementation using FastMCP

#mcp-neo4j#neo4j#remote-server

MCP Neo4j Remote Server の設定

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-remote": {
      "command": "docker",
      "args": [
        "build",
        "-t",
        "mcp-neo4j-remote",
        "."
      ]
    }
  }
}

MCP Neo4j Remote Server のツール

ツール一覧はまだありません

この掲載には表示できるツール一覧がまだありません。サーバーにツールがないという意味ではありません。対応機能はプロジェクトのドキュメントをご確認ください。

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 Remote Server?

A remote Model Context Protocol (MCP) server that provides persistent memory capabilities through Neo4j graph database integration with OAuth 2.1 and API Key authentication.

How to use MCP Neo4j Remote Server?

Install with npm install, copy .env.example to .env, configure Neo4j credentials and authentication keys, then start with npm run dev or deploy via Docker Compose. The server exposes an MCP endpoint at /stream and provides tools such as read_graph, search_nodes, create_entities, create_relations, and more.

Key features of MCP Neo4j Remote Server

  • Remote HTTP access with dual authentication (OAuth 2.1 via Descope and API Key)
  • Persistent graph-based memory storage using Neo4j
  • Docker support with containerized deployment
  • Health monitoring and built-in endpoints
  • Full TypeScript implementation with type safety

Use cases of MCP Neo4j Remote Server

  • Persistent memory storage for AI agents using knowledge graphs
  • Query and manage large graph databases remotely
  • Create, update, and delete entities and relationships
  • Add and manage observations on existing entities
  • Integrate with MCP-compatible clients for graph-based operations

よくある質問

1

How do I authenticate with the server?

Use an API Key via the `x-api-key` header, `Authorization: ApiKey <key>`, or the `?api_key=` query parameter. For OAuth 2.1, use `Authorization: Bearer <token>` with a Descope-issued token.

2

What dependencies does the server require?

You need a running Neo4j database and Node.js (or Docker). Environment variables for Neo4j URI, username, and password are required; API keys and Descope credentials are optional.

3

How do I deploy the server?

You can run it locally with `npm run dev`, build for production with `npm run build` then `npm start`, or use Docker Compose with `docker-compose up --build`.

4

What tools are available for managing the graph?

Tools include `read_graph`, `search_nodes`, `find_nodes`, `open_nodes`, `create_entities`, `delete_entities`, `create_relations`, `delete_relations`, `add_observations`, and `delete_observations`.

5

Where can I find server status and authentication information?

Server status is available at the resource URI `mcp-neo4j://status`, and authentication details at `mcp-neo4j://auth-info`.

コメント

「開発者ツール」の他のコンテンツ

ArtiBot Cloud MCP - Zhijiangyun 智匠云

bofob

ArtiBot Cloud MCP (Zhijiangyun 智匠云) — cloud MCP server for robot manipulation data & GPU workloads. 15 tools: robot fleet management, data collection & video recording, post-processing pipelines, and benchmark evaluation

1

Vibgrate MCP

Vibgrate

Query your team's drift, vulnerability, and migration data from any AI assistant. Vibgrate MCP connects Cursor, Claude, ChatGPT, Windsurf, or VS Code to Vibgrate Cloud: 51 tools for DriftScores, CVEs and EOL runtimes, up

3

Capgo MCP

Cap-go

Console, Backend and CLI to manage Capgo Instant update and Native build for Capacitor apps Build and upload to app store your mobile app

Ramen

bkraad47

Multi-zone MCP server for GKE/EKS/AKS: Python tools from git, NeMo guardrails, SSO, autoscaling.

Testiny MCP server

Mategra GmbH

Testiny is a test case management platform. Its remote MCP server lets AI assistants such as Claude, ChatGPT, GitHub Copilot, Cursor and other MCP clients work directly with your Testiny data. Browse and search projects,

広告掲載