Neo4j

Provides an MCP bridge to Neo4j to run Cypher queries and manage graph data from your MCP client.
  • javascript

0

GitHub Stars

javascript

Language

7 months ago

First Indexed

3 months ago

Catalog Refreshed

Documentation & install

Readme and setup notes from the catalogue, plus a client-ready config you can copy for your MCP host.

Installation

Add the following to your MCP client configuration file.

Configuration

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

This MCP server enables natural-language interactions to run Cypher queries against a Neo4j graph database from Claude Desktop. You can execute queries, create nodes, and establish relationships without writing Cypher directly in your client.

How to use

Connect to the MCP server from your Claude Desktop configuration to start issuing graph database operations through natural language. You will use three core tools: execute_query to run Cypher queries, create_node to add nodes with labels and properties, and create_relationship to link existing nodes with a relationship type and optional properties.

Typical workflows you can perform include querying for specific graph patterns, creating nodes with rich properties, and establishing relationships between nodes. You provide natural language prompts, and the MCP server translates them into Cypher operations behind the scenes, returning structured results that you can inspect and refine.

How to install

Prerequisites you need before installing or running the server:

  • Node.js and npm installed on your machine

  • A Neo4j database accessible at a Bolt URI with a valid username and password

Install and run the MCP Neo4j Server directly with npx or configure Claude Desktop to launch it via npx with environment variables

npx @alanse/mcp-neo4j

Configuration

Set up the MCP server configuration in Claude Desktop to point to the MCP package and to provide the required Neo4j credentials.

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

Usage examples

Query data with natural language prompts, such as finding entities and relationships, or aggregating properties across nodes.

Create nodes with labeled properties by describing the desired entity, then confirm the creation to receive the internal node ID.

Link existing nodes by specifying the relationship type and direction, and optionally attach properties to the relationship.

Notes on security and best practices

Always pass parameters to Cypher queries to prevent injection attacks. Ensure your Neo4j instance is secured and reachable only from trusted clients.

Store credentials securely and rotate passwords regularly. Use environment variables to avoid hard-coding secrets in any configuration files.

Testing and troubleshooting

Run the test suite if provided by the project to verify the MCP server integration with Neo4j.

If you encounter connection errors, verify the NEO4J_URI, NEO4J_USERNAME, and NEO4J_PASSWORD values, and ensure the Neo4j database is reachable from the machine running the MCP server.

Available tools

execute_query

Execute Cypher queries against the Neo4j database. Supports READ, CREATE, UPDATE, and DELETE operations and returns structured results. Parameters can be passed to prevent injection.

create_node

Create a new node in the graph with specified labels and properties. Returns the created node with its internal ID and supports all Neo4j data types for properties.

create_relationship

Create a relationship between two existing nodes. Define the relationship type, direction, and optional properties. Requires source and target node IDs.

Built by
VeilStrat
AI signals for GTM teams
© 2026 VeilStrat. All rights reserved.All systems operational