Skip to main content

A simple Neo4j MCP server

Project description

🔍⁉️ Neo4j MCP Server

🌟 Overview

A Model Context Protocol (MCP) server implementation that provides database interaction and allows graph exploration capabilities through Neo4j. This server enables running Cypher graph queries, analyzing complex domain data, and automatically generating business insights that can be enhanced with Claude's analysis.

🧩 Components

🛠️ Tools

The server offers these core tools:

📊 Query Tools

  • read-neo4j-cypher

    • Execute Cypher read queries to read data from the database
    • Input:
      • query (string): The Cypher query to execute
      • params (dictionary, optional): Parameters to pass to the Cypher query
    • Returns: Query results as JSON serialized array of objects
  • write-neo4j-cypher

    • Execute updating Cypher queries
    • Input:
      • query (string): The Cypher update query
      • params (dictionary, optional): Parameters to pass to the Cypher query
    • Returns: A JSON serialized result summary counter with { nodes_updated: number, relationships_created: number, ... }

🕸️ Schema Tools

  • get-neo4j-schema
    • Get a list of all nodes types in the graph database, their attributes with name, type and relationships to other node types
    • No input required
    • Returns: JSON serialized list of node labels with two dictionaries: one for attributes and one for relationships

🔧 Usage with Claude Desktop

💾 Released Package

Can be found on PyPi https://pypi.org/project/mcp-neo4j-cypher/

Add the server to your claude_desktop_config.json with configuration through environment variables:

"mcpServers": {
  "neo4j-aura": {
    "command": "uvx",
    "args": [ "mcp-neo4j-cypher@0.2.1" ],
    "env": {
      "NEO4J_URI": "bolt://localhost:7687",
      "NEO4J_USERNAME": "neo4j",
      "NEO4J_PASSWORD": "<your-password>",
      "NEO4J_DATABASE": "neo4j"
    }
  }
}

Here is an example connection for the movie database with Movie, Person (Actor, Director), Genre, User and ratings:

{
  "mcpServers": {
    "movies-neo4j": {
      "command": "uvx",
      "args": ["mcp-neo4j-cypher@0.2.1"],
      "env": {
        "NEO4J_URI": "neo4j+s://demo.neo4jlabs.com",
        "NEO4J_USERNAME": "recommendations",
        "NEO4J_PASSWORD": "recommendations"
      }
    }   
  }
}

Syntax with --db-url, --username and --password command line arguments is still supported but environment variables are preferred:

Legacy Syntax
"mcpServers": {
  "neo4j": {
    "command": "uvx",
    "args": [
      "mcp-neo4j-cypher@0.1.1",
      "--db-url",
      "bolt://localhost",
      "--username",
      "neo4j",
      "--password",
      "<your-password>"
    ]
  }
}

Here is an example connection for the movie database with Movie, Person (Actor, Director), Genre, User and ratings:

{
  "mcpServers": {
    "movies-neo4j": {
      "command": "uvx",
      "args": ["mcp-neo4j-cypher@0.1.1", 
      "--db-url", "neo4j+s://demo.neo4jlabs.com", 
      "--user", "recommendations", 
      "--password", "recommendations"]
    }   
  }
}

🐳 Using with Docker

"mcpServers": {
  "neo4j": {
    "command": "docker",
    "args": [
      "run",
      "--rm",
      "-e", "NEO4J_URI=bolt://host.docker.internal:7687",
      "-e", "NEO4J_USERNAME=neo4j",
      "-e", "NEO4J_PASSWORD=<your-password>",
      "mcp/neo4j-cypher:latest"
    ]
  }
}

🚀 Development

📦 Prerequisites

  1. Install uv (Universal Virtualenv):
# Using pip
pip install uv

# Using Homebrew on macOS
brew install uv

# Using cargo (Rust package manager)
cargo install uv
  1. Clone the repository and set up development environment:
# Clone the repository
git clone https://github.com/yourusername/mcp-neo4j-cypher.git
cd mcp-neo4j-cypher

# Create and activate virtual environment using uv
uv venv
source .venv/bin/activate  # On Unix/macOS
.venv\Scripts\activate     # On Windows

# Install dependencies including dev dependencies
uv pip install -e ".[dev]"
  1. Run Integration Tests

CLOSE ANY LOCAL NEO4J DATABASES BEFORE RUNNING TESTS

  • Tests will deploy a local docker container containing the test Neo4j instance.
  • However if a Neo4j database is running locally, then the test driver may connect here instead.
  • This will result in you local Neo4j database having its contents erased.
./tests.sh

🔧 Development Configuration

# Add the server to your claude_desktop_config.json
"mcpServers": {
  "neo4j": {
    "command": "uv",
    "args": [
      "--directory", "parent_of_servers_repo/servers/mcp-neo4j-cypher/src",
      "run", "mcp-neo4j-cypher"],
    "env": {
      "NEO4J_URI": "bolt://localhost",
      "NEO4J_USERNAME": "neo4j",
      "NEO4J_PASSWORD": "<your-password>"
    }
  }
}

🐳 Docker

Build and run the Docker container:

# Build the image
docker build -t mcp/neo4j-cypher:latest .

# Run the container
docker run -e NEO4J_URI="bolt://host.docker.internal:7687" \
          -e NEO4J_USERNAME="neo4j" \
          -e NEO4J_PASSWORD="your-password" \
          mcp/neo4j-cypher:latest

📄 License

This MCP server is licensed under the MIT License. This means you are free to use, modify, and distribute the software, subject to the terms and conditions of the MIT License. For more details, please see the LICENSE file in the project repository.

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

mcp_neo4j_cypher-0.2.1.tar.gz (26.7 kB view details)

Uploaded Source

Built Distribution

If you're not sure about the file name format, learn more about wheel file names.

mcp_neo4j_cypher-0.2.1-py3-none-any.whl (6.0 kB view details)

Uploaded Python 3

File details

Details for the file mcp_neo4j_cypher-0.2.1.tar.gz.

File metadata

  • Download URL: mcp_neo4j_cypher-0.2.1.tar.gz
  • Upload date:
  • Size: 26.7 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? Yes
  • Uploaded via: twine/6.1.0 CPython/3.12.9

File hashes

Hashes for mcp_neo4j_cypher-0.2.1.tar.gz
Algorithm Hash digest
SHA256 5b11516a6d513e7a39ffb055ba82289f8bfacc6e6e447a73111c5af3bbb46ac0
MD5 893612bff46a34672fee51887584d0b8
BLAKE2b-256 4ee6d0d70cf3f6468b4e98ef4864fdab3810412baca044d6ea6a91df2f82714c

See more details on using hashes here.

Provenance

The following attestation bundles were made for mcp_neo4j_cypher-0.2.1.tar.gz:

Publisher: publish.yml on neo4j-contrib/mcp-neo4j

Attestations: Values shown here reflect the state when the release was signed and may no longer be current.

File details

Details for the file mcp_neo4j_cypher-0.2.1-py3-none-any.whl.

File metadata

File hashes

Hashes for mcp_neo4j_cypher-0.2.1-py3-none-any.whl
Algorithm Hash digest
SHA256 9542591022d1a86ad3d164a0e3a53b8fc9f8c3e510f4f116e037d232c01690be
MD5 ac35e6bd2c6752257aee8b741561c22a
BLAKE2b-256 4557e9b729e46edef44736643ea09e3d8914f32f61d8b881a1220e2019851e42

See more details on using hashes here.

Provenance

The following attestation bundles were made for mcp_neo4j_cypher-0.2.1-py3-none-any.whl:

Publisher: publish.yml on neo4j-contrib/mcp-neo4j

Attestations: Values shown here reflect the state when the release was signed and may no longer be current.

Supported by

AWS Cloud computing and Security Sponsor Datadog Monitoring Depot Continuous Integration Fastly CDN Google Download Analytics Pingdom Monitoring Sentry Error logging StatusPage Status page