# MCP Neo4j Data Modeling (MCP server)

> MCP Neo4j Data Modeling is an MCP server that adds database tools to AI assistants such as Claude Desktop, Claude Code and Cursor. A simple Neo4j MCP server for creating graph data models. It has 988 GitHub stars, is released under the MIT license and runs locally with uvx mcp-neo4j-data-modeling.

mcp-name: io.github.neo4j-contrib/mcp-neo4j-data-modeling A Model Context Protocol (MCP) server implementation that provides tools for creating, visualizing, and managing Neo4j graph data models. This server enables you to define nodes, relationships, and properties to design graph database schemas that can be visualized interactively.

## Key facts

| Fact | Value |
|---|---|
| Repository | https://github.com/neo4j-contrib/mcp-neo4j |
| GitHub stars | 988 |
| License | MIT |
| Language | Python |
| Transport | stdio |
| Packages | pypi: mcp-neo4j-data-modeling |
| Remote URL | none |
| Needs API key | no |
| Official | yes |
| Works with | Claude Desktop, Claude Code, Cursor, VS Code |
| Category | Databases |
| Latest release | mcp-neo4j-cypher-v0.6.0 (Apr 10, 2026) |
| Last commit | Sep 9, 2026 |
| MCP registry name | io.github.neo4j-contrib/mcp-neo4j-data-modeling |

## Install

### Claude Desktop (claude_desktop_config.json)

```json
{
  "mcpServers": {
    "mcp-neo4j-data-modeling": {
      "command": "uvx",
      "args": [
        "mcp-neo4j-data-modeling"
      ],
      "env": {
        "NEO4J_NAMESPACE": "your-value"
      }
    }
  }
}
```

Settings > Developer > Edit Config. macOS: ~/Library/Application Support/Claude/, Windows: %APPDATA%\Claude\. Restart Claude Desktop afterwards.

### Claude Code

```sh
claude mcp add --env NEO4J_NAMESPACE=your-value --transport stdio mcp-neo4j-data-modeling -- uvx mcp-neo4j-data-modeling
```

### Cursor (.cursor/mcp.json)

```json
{
  "mcpServers": {
    "mcp-neo4j-data-modeling": {
      "type": "stdio",
      "command": "uvx",
      "args": [
        "mcp-neo4j-data-modeling"
      ],
      "env": {
        "NEO4J_NAMESPACE": "your-value"
      }
    }
  }
}
```

Project file; use ~/.cursor/mcp.json to enable it in every project.

### VS Code (.vscode/mcp.json)

```json
{
  "servers": {
    "mcp-neo4j-data-modeling": {
      "type": "stdio",
      "command": "uvx",
      "args": [
        "mcp-neo4j-data-modeling"
      ],
      "env": {
        "NEO4J_NAMESPACE": "your-value"
      }
    }
  }
}
```

Config formats checked against the official docs on 2026-10-07.

## Environment variables

- `NEO4J_NAMESPACE`: The namespace to use for the MCP server tool names.

## Tools

- `validate_node`
- `node`: The node to validate
- `return_validated`: If True, returns the validated node object instead of True
- `validate_relationship`
- `relationship`: The relationship to validate
- `validate_data_model`
- `data_model`: The data model to validate
- `get_mermaid_config_str`
- `load_from_arrows_json`
- `arrows_data_model_dict`: JSON dictionary from Arrows app export
- `export_to_arrows_json`
- `load_from_owl_turtle`
- `owl_turtle_str`: OWL Turtle string representation of an ontology
- `export_to_owl_turtle`
- `export_to_pydantic_models`
- `export_to_neo4j_graphrag_pkg_schema`
- `load_from_neo4j_graphrag_pkg_schema`
- `neo4j_graphrag_python_package_schema`: Neo4j GraphRAG Python Package schema dictionary
- `list_example_data_models`
- `get_example_data_model`
- `example_name`: Name of the example to load ('patientjourney', 'supplychain', 'softwaredependency', 'oilgasmonitoring', 'customer360',…
- `get_constraints_cypher_queries`
- `get_node_cypher_ingest_query`
- `get_relationship_cypher_ingest_query`
- `relationship_type`: The type of the relationship
- `relationship_start_node_label`: The label of the start node
- `relationship_end_node_label`: The label of the end node

## Similar MCP servers

- [Dbx](https://appsgit.com/mcp-servers/dbx): Query databases from AI agents using connections configured in DBX. (24,945 stars, Apache-2.0)
- [Butterbase AI MCP Server](https://appsgit.com/mcp-servers/butterbase-ai-mcp-server): Butterbase MCP server — manage your backend: schemas, auth, functions, storage, RAG, deploys. (3,686 stars, Apache-2.0, needs API key)
- [DBHub](https://appsgit.com/mcp-servers/dbhub): Token-efficient database MCP server for PostgreSQL, MySQL, MariaDB, SQL Server, Oracle, SQLite. (3,610 stars, MIT, needs API key)
- [LINQ to DB](https://appsgit.com/mcp-servers/linq-to-db): Inspect database schemas and execute SQL queries across multiple database providers with LINQ to DB. (3,332 stars, MIT)
- [Mindwtr](https://appsgit.com/mcp-servers/mindwtr): Task automation via SQLite, desktop Local API, or Mindwtr Cloud; read-only by default. (2,211 stars, AGPL-3.0, needs API key)
- [MCP Memory Service](https://appsgit.com/mcp-servers/mcp-memory-service): Open-source persistent memory for AI agent pipelines (LangGraph, CrewAI, AutoGen) and Claude. (1,988 stars, Apache-2.0)

---

Canonical page: https://appsgit.com/mcp-servers/mcp-neo4j-data-modeling
Source: appsgit (https://appsgit.com), the app store for github. Data from the GitHub API, refreshed nightly.
Machine access: JSON API https://appsgit.com/api/v1/apps (OpenAPI: https://appsgit.com/openapi.json), MCP server https://mcp.appsgit.com/mcp, full index https://appsgit.com/llms-full.txt.