What is Neo4j Server

The MCP Neo4j Server is a server that facilitates integration between a Neo4j graph database and Claude Desktop. It allows users to perform graph database operations using natural language, making it easier for non-technical users to interact with complex data structures.

Use cases

Use cases for the MCP Neo4j Server include querying data from the Neo4j database, creating new nodes and relationships, and conducting complex operations like aggregations or multi-hop queries. Users can ask questions or provide commands in natural language, enabling quick and intuitive access to database functionalities.

How to use

To use the MCP Neo4j Server, you can run it directly from the command line using npx: npx @alanse/mcp-neo4j. Alternatively, it can be added to the Claude Desktop configuration by including it in the mcpServers section with appropriate environment variables for database connection.

Key features

Key features of the MCP Neo4j Server include the ability to execute Cypher queries, create nodes with specified properties, and form relationships between nodes. It supports various Cypher commands, returns structured results, and allows the passing of parameters to prevent injection attacks.

Where to use

The MCP Neo4j Server is designed for use within environments where Claude Desktop is deployed. It is suitable for applications requiring data-driven insights or relationship mapping through a Neo4j database, especially in domains like sales, marketing, or any field that leverages graph-based data representations.

MCP Neo4j Server

An MCP server that provides integration between Neo4j graph database and Claude Desktop, enabling graph database operations through natural language interactions.

Quick Start

You can run this MCP server directly using npx:

npx @alanse/mcp-neo4j

Or add it to your Claude Desktop configuration:

{
  "mcpServers": {
    "neo4j": {
      "command": "npx",
      "args": [
        "@alanse/mcp-neo4j-server"
      ],
      "env": {
        "NEO4J_URI": "bolt://localhost:7687",
        "NEO4J_USERNAME": "neo4j",
        "NEO4J_PASSWORD": "your-password"
      }
    }
  }
}

Features

This server provides tools for interacting with a Neo4j database:

Tools

• execute_query: Execute Cypher queries on the Neo4j database

  • Supports all types of Cypher queries (READ, CREATE, UPDATE, DELETE)
  • Returns query results in a structured format
  • Parameters can be passed to prevent injection attacks

• create_node: Create a new node in the graph database

  • Specify node labels and properties
  • Returns the created node with its internal ID
  • Supports all Neo4j data types for properties

• create_relationship: Create a relationship between two existing nodes

  • Define relationship type and direction
  • Add properties to relationships
  • Requires node IDs for source and target nodes

Installation

Installing via Smithery

To install MCP Neo4j Server for Claude Desktop automatically via Smithery:

npx -y @smithery/cli install @alanse/mcp-neo4j-server --client claude

For Development

1. Clone the repository:

git clone https://github.com/da-okazaki/mcp-neo4j-server.git
cd mcp-neo4j-server

2. Install dependencies:

npm install

3. Build the project:

npm run build

Configuration

The server requires the following environment variables:

• NEO4J_URI: Neo4j database URI (default: bolt://localhost:7687)
• NEO4J_USERNAME: Neo4j username (default: neo4j)
• NEO4J_PASSWORD: Neo4j password (required)

Usage Examples

Here are examples of how you can interact with the Neo4j database using natural language:

Querying Data

You can ask questions like:

• “Show me all employees in the Sales department”
• “Find the top 5 oldest customers”
• “Who has purchased more than 3 products in the last month?”

Example:

User: "Show me all employees in the Sales department"

Claude: Let me query the database for Sales department employees.

[Executes query internally: MATCH (e:Employee)-[:WORKS_IN]->(d:Department {name: 'Sales'}) RETURN e.name, e.position]

Result:
- John Smith (Sales Manager)
- Sarah Johnson (Sales Representative)
- Mike Brown (Account Executive)

Creating Data

You can give instructions like:

• “Add a new person named John Doe who is 30 years old”
• “Create a product called ‘Premium Coffee’ with price $24.99”
• “Add a new department called ‘Research & Development’”

Example:

User: "Add a new person named John Doe who is 30 years old"

Claude: I'll create a new Person node with the provided information.

[Creates node internally with label 'Person' and properties {name: 'John Doe', age: 30}]

Result: Created new person node with ID: 123

Creating Relationships

You can request relationships like:

• “Make John Doe friends with Jane Smith”
• “Set Product A as a component of Product B”
• “Assign John Doe to the Sales department”

Example:

User: "Make John Doe friends with Jane Smith"

Claude: I'll create a friendship relationship between these two people.

[Creates relationship internally: MATCH (a:Person {name: 'John Doe'}), (b:Person {name: 'Jane Smith'})
CREATE (a)-[:FRIENDS_WITH {since: '2024-01-05'}]->(b)]

Result: Created friendship relationship between John Doe and Jane Smith

Complex Operations

You can perform more complex operations with natural language:

• “Find all products purchased by customers who live in New York”
• “Show me friends of friends of John Doe”
• “Calculate the average age of employees in each department”

Example:

User: "Find all products purchased by customers who live in New York"

Claude: I'll query the database for this information.

[Executes query internally:
MATCH (c:Customer {city: 'New York'})-[:PURCHASED]->(p:Product)
RETURN c.name, collect(p.name) as products]

Result:
- Alice Wilson: [Premium Coffee, Tea Set, Cookies]
- Bob Miller: [Premium Coffee, Water Bottle]

Testing

Run the test suite:

npm test

License

MIT