Neo4j MCP Server Integration

What does “Neo4j” MCP Server do?

The Neo4j MCP (Model Context Protocol) Server is a specialized tool that bridges AI assistants with the Neo4j graph database. It enables seamless interactions between large language models (LLMs) and Neo4j, allowing developers and users to perform graph database operations through natural language instructions. By acting as an intermediary, the Neo4j MCP Server empowers AI-driven workflows to execute Cypher queries, manage nodes and relationships, and retrieve structured results from the database. This integration enhances productivity by making complex database operations accessible, automatable, and secure within various AI-powered development environments.

List of Prompts

No explicit prompt templates are mentioned in the available repository documentation.

List of Resources

No explicit resources are documented in the repository.

List of Tools

• execute_query: Executes Cypher queries on the Neo4j database. Supports all Cypher operations (READ, CREATE, UPDATE, DELETE), allows parameter passing to prevent injection, and returns structured results.
• create_node: Creates a new node in the graph database. Users can specify node labels and properties, with support for all Neo4j data types. Returns the created node and its internal ID.
• create_relationship: Establishes a relationship between two existing nodes. Users can define the relationship type and direction, add properties, and must provide node IDs for source and target nodes.

Use Cases of this MCP Server

• Graph Database Querying: Enables users to run complex Cypher queries on Neo4j using natural language, facilitating data retrieval, analysis, and reporting.
• Graph Data Creation & Management: Allows developers to programmatically create nodes and relationships, supporting data modeling, migration, and enrichment tasks.
• AI-Assisted Data Exploration: Empowers AI assistants to help users explore and understand graph structures, uncovering insights without manual query writing.
• Automated Data Operations: Integrates with development workflows to automate repetitive database operations, improving consistency and saving time.
• Secure Parameterized Actions: Provides a secure interface for managing data, with support for parameterized queries to prevent injection attacks and ensure safe data manipulation.

How to set it up

Windsurf

1. Ensure you have Node.js installed on your system.
2. Open your Windsurf configuration file.
3. Add the Neo4j MCP Server entry in your mcpServers object:

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

4. Save the configuration and restart Windsurf.
5. Verify the server is running and accessible in your MCP client.

Claude

1. Install Node.js if not already present.
2. Open your Claude Desktop configuration file.
3. Insert the Neo4j MCP Server configuration as follows:

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

4. Save and restart Claude Desktop.
5. Confirm successful connection to your Neo4j database.

Cursor

1. Ensure Node.js is installed.
2. Open the Cursor configuration file.
3. Add the following MCP server configuration:

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

4. Save your changes and restart Cursor.
5. Test the connection to verify it works.

Cline

1. Make sure Node.js is available on your system.
2. Locate and open the Cline configuration file.
3. Add the Neo4j MCP Server configuration:

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

4. Save and restart Cline.
5. Check the MCP integration to ensure it is functioning.

Securing API Keys:
Always store sensitive credentials (such as NEO4J_PASSWORD) using environment variables, not hardcoded values. For example:

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

How to use this MCP inside flows

Using MCP in FlowHunt

To integrate MCP servers into your FlowHunt workflow, start by adding the MCP component to your flow and connecting it to your AI agent:

Click on the MCP component to open the configuration panel. In the system MCP configuration section, insert your MCP server details using this JSON format:

{
  "neo4j": {
    "transport": "streamable_http",
    "url": "https://yourmcpserver.example/pathtothemcp/url"
  }
}

Once configured, the AI agent is now able to use this MCP as a tool with access to all its functions and capabilities. Remember to change “neo4j” to whatever the actual name of your MCP server is and replace the URL with your own MCP server URL.

Overview

Roots support: ⛔ (not documented)

Between the available documentation and features, this MCP server is highly specialized and functional for Neo4j operations, but lacks documentation on prompts, resources, roots, and sampling. For database-focused tasks, it scores well for utility and clarity, but less for extensibility or broader MCP features.

MCP Score