ClaudeCodeMod

All shelves / MCP servers

Mcp Neo4j Aura Manager

io.github.neo4j-contrib/mcp-neo4j-aura-manager · 958 stars · Python · MIT

MCP server MCP server for Neo4j Aura Database Instance Manager.

Install

In your shell
pip install mcp-neo4j-aura-manager

These repos do not share one command. When an entry shows a command, it was copied as published. Check the repo's README before you run it.

Published as

  • PyPImcp-neo4j-aura-managerstdio

From the server's entry in the official MCP Registry.

Configuration

NameSet asWhat it is
NEO4J_AURA_CLIENT_IDRequired · SecretEnv varNeo4j Aura API Client ID
NEO4J_AURA_CLIENT_SECRETRequired · SecretEnv varNeo4j Aura API Client Secret
NEO4J_NAMESPACEOptionalEnv varNamespace for tools

Files

README.md

🚀💖☁️ Neo4j Aura Database Manager MCP Server

mcp-name: io.github.neo4j-contrib/mcp-neo4j-aura-manager

🌟 Overview

A Model Context Protocol (MCP) server implementation that provides tools for managing Neo4j Aura database instances through the Neo4j Aura API.

This server allows you to create, monitor, and manage Neo4j Aura instances directly through Claude, making it easy to provision and maintain your graph database infrastructure.

🔑 Authentication

Authentication with the Neo4j Aura API requires:

  • Client ID
  • Client Secret

You can obtain these credentials from the Neo4j Aura console, see the documentation of the Aura API

Here is the API Specification

📦 Components

🔧 Tools

The server offers these core tools:

#### 🛠️ Instance Management

  • list_instances
  • List all Neo4j Aura database instances
  • No input required
  • Returns: List of all instances with their details
  • get_instance_details
  • Get details for a specific instance or multiple instances by ID
  • Input:
  • instance_ids (string or array): ID of the instance to retrieve, or array of instance IDs
  • Returns: Detailed information about the instance(s)
  • get_instance_by_name
  • Find an instance by name
  • Input:
  • name (string): Name of the instance to find
  • Returns: Instance details if found
  • create_instance
  • Create a new Neo4j Aura database instance
  • Input:
  • tenant_id (string): ID of the tenant/project where the instance will be created
  • name (string): Name for the new instance
  • memory (integer): Memory allocation in GB
  • region (string): Region for the instance (e.g., 'us-east-1')
  • version (string): Neo4j version (e.g., '5.15')
  • type (string, optional): Instance type (enterprise or professional)
  • vector_optimized (boolean, optional): Whether the instance is optimized for vector operations
  • Returns: Created instance details
  • update_instance_name
  • Update the name of an instance
  • Input:
  • instance_id (string): ID of the instance to update
  • name (string): New name for the instance
  • Returns: Updated instance details
  • update_instance_memory
  • Update the memory allocation of an instance
  • Input:
  • instance_id (string): ID of the instance to update
  • memory (integer): New memory allocation in GB
  • Returns: Updated instance details
  • update_instance_vector_optimization
  • Update the vector optimization setting of an instance
  • Input:
  • instance_id (string): ID of the instance to update
  • vector_optimized (boolean): Whether the instance should be optimized for vector operations
  • Returns: Updated instance details
  • pause_instance
  • Pause a database instance
  • Input:
  • instance_id (string): ID of the instance to pause
  • Returns: Instance status information
  • resume_instance
  • Resume a paused database instance
  • Input:
  • instance_id (string): ID of the instance to resume
  • Returns: Instance status information
  • delete_instance
  • Delete a database instance
  • Input:
  • tenant_id (string): ID of the tenant/project where the instance exists
  • instance_id (string): ID of the instance to delete
  • Returns: Deletion status information

#### 🏢 Tenant/Project Management

  • list_tenants
  • List all Neo4j Aura tenants/projects
  • No input required
  • Returns: List of all tenants with their details
  • get_tenant_details
  • Get details for a specific tenant/project
  • Input:
  • tenant_id (string): ID of the tenant/project to retrieve
  • Returns: Detailed information about the tenant/project

🔧 Usage with Claude Desktop

💾 Installation

pip install mcp-neo4j-aura-manager

⚙️ Configuration

Add the server to your claude_desktop_config.json:

"mcpServers": {
  "neo4j-aura": {
    "command": "uvx",
    "args": [
      "mcp-neo4j-aura-manager@0.4.8",
      "--client-id",
      "<your-client-id>",
      "--client-secret",
      "<your-client-secret>"
      ]
  }
}

Alternatively, you can set environment variables:

"mcpServers": {
  "neo4j-aura": {
    "command": "uvx",
    "args": [ "mcp-neo4j-aura-manager@0.4.8" ],
    "env": {
      "NEO4J_AURA_CLIENT_ID": "<your-client-id>",
      "NEO4J_AURA_CLIENT_SECRET": "<your-client-secret>"
    }
  }
}

🐳 Using with Docker

"mcpServers": {
  "neo4j-aura": {
    "command": "docker",
    "args": [
      "run",
      "--rm",
      "-e", "NEO4J_AURA_CLIENT_ID=${NEO4J_AURA_CLIENT_ID}",
      "-e", "NEO4J_AURA_CLIENT_SECRET=${NEO4J_AURA_CLIENT_SECRET}",
      "mcp-neo4j-aura-manager:0.4.8"
    ]
  }
}

🏷️ Namespacing for Multi-tenant Deployments

The server supports namespacing to prefix tool names for multi-tenant deployments:

"mcpServers": {
  "neo4j-aura-app1": {
    "command": "uvx",
    "args": [
      "mcp-neo4j-aura-manager@0.4.8",
      "--client-id", "<your-client-id>",
      "--client-secret", "<your-client-secret>",
      "--namespace", "app1"
    ]
  },
  "neo4j-aura-app2": {
    "command": "uvx", 
    "args": [
      "mcp-neo4j-aura-manager@0.4.8",
      "--client-id", "<your-client-id>",
      "--client-secret", "<your-client-secret>",
      "--namespace", "app2"
    ]
  }
}

#### CLI Usage

# With namespace
mcp-neo4j-aura-manager --client-id <id> --client-secret <secret> --namespace myapp

# Tools become: myapp-list_instances, myapp-create_instance, etc.

#### Environment Variables

export NEO4J_AURA_CLIENT_ID=your_client_id
export NEO4J_AURA_CLIENT_SECRET=your_client_secret  
export NEO4J_NAMESPACE=myapp
mcp-neo4j-aura-manager

#### Docker with Namespacing

docker run -e NEO4J_AURA_CLIENT_ID=<id> \
           -e NEO4J_AURA_CLIENT_SECRET=<secret> \
           -e NEO4J_NAMESPACE=myapp \
           mcp-neo4j-aura-manager

🌐 HTTP Transport Mode

The server supports HTTP transport for web-based deployments and microservices:

# Basic HTTP mode (defaults: host=127.0.0.1, port=8000, path=/mcp/)
mcp-neo4j-aura-manager --transport http

# Custom HTTP configuration
mcp-neo4j-aura-manager --transport http --host 127.0.0.1 --port 8080 --path /api/mcp/

Environment variables for HTTP configuration:

export NEO4J_TRANSPORT=http
export NEO4J_MCP_SERVER_HOST=127.0.0.1
export NEO4J_MCP_SERVER_PORT=8080
export NEO4J_MCP_SERVER_PATH=/api/mcp/
export NEO4J_MCP_SERVER_ALLOWED_HOSTS="localhost,127.0.0.1"
export NEO4J_MCP_SERVER_ALLOW_ORIGINS="http://localhost:3000"
export NEO4J_NAMESPACE=myapp
mcp-neo4j-aura-manager

🔄 Transport Modes

The server supports three transport modes:

  • STDIO (default): Standard input/output for local tools and Claude Desktop
  • SSE: Server-Sent Events for web-based deployments
  • HTTP: Streamable HTTP for modern web deployments and microservices

🔒 Security Protection

The server includes comprehensive security protection with secure defaults that protect against common web-based attacks while preserving full MCP functionality when using HTTP transport.

🛡️ DNS Rebinding Protection

TrustedHost Middleware validates Host headers to prevent DNS rebinding attacks:

Secure by Default:

  • Only localhost and 127.0.0.1 hosts are allowed by default
  • Malicious websites cannot trick browsers into accessing your local server

Environment Variable:

export NEO4J_MCP_SERVER_ALLOWED_HOSTS="example.com,www.example.com"

🌐 CORS Protection

Cross-Origin Resource Sharing (CORS) protection blocks browser-based requests by default:

Environment Variable:

export NEO4J_MCP_SERVER_ALLOW_ORIGINS="https://example.com,https://example.com"

🔧 Complete Security Configuration

Development Setup:

mcp-neo4j-aura-manager --transport http \
  --allowed-hosts "localhost,127.0.0.1" \
  --allow-origins "http://localhost:3000"

Production Setup:

mcp-neo4j-aura-manager --transport http \
  --allowed-hosts "example.com,www.example.com" \
  --allow-origins "https://example.com,https://example.com"

🚨 Security Best Practices

For allow_origins:

  • Be specific: ["https://example.com", "https://example.com"]
  • Never use "*" in production with credentials
  • Use HTTPS origins in production

For allowed_hosts:

  • Include your actual domain: ["example.com", "www.example.com"]
  • Include localhost only for development
  • Never use "*" unless you understand the risks

🐳 Docker Deployment

The Neo4j Aura Manager MCP server can be deployed using Docker for remote deployments. Docker deployment should use HTTP transport for web accessibility. In order to integrate this deployment with applications like Claude Desktop, you will have to use a proxy in your MCP configuration such as mcp-remote.

🐳 Using with Docker for Claude Desktop

Facts

Kind
MCP server
Repo
io.github.neo4j-contrib/mcp-neo4j-aura-manager
Group
Uncategorized
Stars
958
License
MIT
Language
Python
Last push
2026-09-09
Forks
262
MCP Registry
io.github.neo4j-contrib/mcp-neo4j-aura-manager
Homepage
neo4j.com/developer/genai-ecosystem/model-context-protocol-mcp
Topics
database, mcp, mcp-server, neo4j, stdio

More on this shelf

  1. 1Everythingmodelcontextprotocol/serversThis MCP server attempts to exercise all the features of the MCP protocol. It is not intended to be a useful server, but rather a test server for builders of MCP clients. It implements prompts, tools, resources, sampling, and more to showcase MCP capabilities.85.8k
  2. 2Fetchmodelcontextprotocol/serversA Model Context Protocol server that provides web content fetching capabilities. This server enables LLMs to retrieve and process content from web pages, converting HTML to markdown for easier consumption.85.8k
  3. 3Gitmodelcontextprotocol/serversA Model Context Protocol server for Git repository interaction and automation. This server provides tools to read, search, and manipulate Git repositories via Large Language Models.85.8k
  4. 4Memorymodelcontextprotocol/serversA basic implementation of persistent memory using a local knowledge graph. This lets Claude remember information about the user across chats.85.8k
  5. 5Sequential Thinkingmodelcontextprotocol/serversAn MCP server implementation that provides a tool for dynamic and reflective problem-solving through a structured thinking process.85.8k
  6. 6Timemodelcontextprotocol/serversA Model Context Protocol server that provides time and timezone conversion capabilities. This server enables LLMs to get current time information and perform timezone conversions using IANA timezone names, with automatic system timezone detection.85.8k