# Neo4j Data Modeling MCP server

> Design, validate, visualize and export Neo4j graph data models, with Arrows, OWL, Pydantic and GraphRAG import and export.

- Listing: https://mcp.tc/i/neo4j-data-modeling
- Connect: this is a local (stdio) server; install it on your machine (see Install). The listing link is a page, not an MCP endpoint.
- Type: local (stdio)
- Auth: no API key needed
- Category: [Databases & Backend](https://mcp.tc/c/databases)
- Vendor: Neo4j Labs (neo4j-contrib)
- Homepage: <https://neo4j.com/developer/genai-ecosystem/model-context-protocol-mcp/>
- Repository: <https://github.com/neo4j-contrib/mcp-neo4j/tree/HEAD/servers/mcp-neo4j-data-modeling>
- Package: pypi `mcp-neo4j-data-modeling`

## About

Provides tools for creating and managing Neo4j graph data models. You define nodes, relationships and properties, validate them, generate Mermaid diagrams, and convert models to and from Arrows app JSON, OWL Turtle, Pydantic models and the Neo4j GraphRAG Python package schema. It also ships example models such as patient journey, supply chain, fraud and AML, and customer 360.

Runs locally over stdio as the PyPI package mcp-neo4j-data-modeling, started with uvx. No sign-in or API key is documented, and no database connection is needed to model. An optional NEO4J\_NAMESPACE variable prefixes tool names.

## What it can do

- Validate nodes, relationships and whole data models
- Generate Mermaid diagrams of a data model
- Import and export Arrows app JSON
- Convert models to and from OWL Turtle (lossy)
- Export Pydantic models and Neo4j GraphRAG schema
- Browse example models for common domains
- Read JSON schemas and the data ingest process guide

## Example prompts

- "Design a Neo4j data model for a supply chain and validate it"
- "Generate a Mermaid diagram for this graph data model"
- "Export my data model as Pydantic models"
- "Load this Arrows JSON export and convert it to OWL Turtle"

## Install

### Claude Code

1. Run this in a terminal, in your project folder:

```bash
claude mcp add --transport stdio neo4j-data-modeling -- uvx mcp-neo4j-data-modeling
```

2. Start Claude Code and type `/mcp`. **neo4j-data-modeling** should show as connected.

Add `--scope user` to make it available in every project.

### Claude Desktop

1. Open **Settings → Developer → Edit Config**. It opens `claude_desktop_config.json`. Add:

`claude_desktop_config.json`:

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

2. Save the file and restart Claude Desktop.

Needs uv (Python) on your computer. The file lives in `~/Library/Application Support/Claude/` on macOS and `%APPDATA%\Claude\` on Windows.

### Cursor

[Add to Cursor](<https://cursor.com/install-mcp?name=neo4j-data-modeling&config=eyJjb21tYW5kIjoidXZ4IiwiYXJncyI6WyJtY3AtbmVvNGotZGF0YS1tb2RlbGluZyJdfQ%3D%3D>) (opens Cursor)

Or add it by hand to `~/.cursor/mcp.json` (all projects) or `.cursor/mcp.json` (this project):

`mcp.json`:

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

Needs uv (Python) on your computer.

### VS Code

[Install in VS Code](<https://vscode.dev/redirect/mcp/install?name=neo4j-data-modeling&config=%7B%22type%22%3A%22stdio%22%2C%22command%22%3A%22uvx%22%2C%22args%22%3A%5B%22mcp-neo4j-data-modeling%22%5D%7D>) (opens VS Code)

Or from a terminal:

```bash
code --add-mcp '{"name":"neo4j-data-modeling","type":"stdio","command":"uvx","args":["mcp-neo4j-data-modeling"]}'
```

Or commit it to the repo in `.vscode/mcp.json`:

`.vscode/mcp.json`:

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

Needs uv (Python) on your computer.

### Devin Desktop

1. Add it to `~/.config/devin/mcp_config.json` (macOS and Linux) or `%APPDATA%\devin\mcp_config.json` (Windows):

`mcp_config.json`:

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

2. Refresh the MCP server list in Cascade.

Devin Desktop is the new name for Windsurf.

### Codex

```bash
codex mcp add neo4j-data-modeling -- uvx mcp-neo4j-data-modeling
```

Or edit `~/.codex/config.toml` directly:

`config.toml`:

```toml
[mcp_servers.neo4j-data-modeling]
command = "uvx"
args = ["mcp-neo4j-data-modeling"]
```

Needs uv (Python) on your computer.

### Gemini CLI

```bash
gemini mcp add neo4j-data-modeling uvx mcp-neo4j-data-modeling
```

This adds it to the current project. Add `-s user` to use it everywhere.

### Any client

Most clients that start local servers accept this shape:

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

Zed puts servers under `context_servers` in its settings, with the same `command`, `args` and `env` fields.

Needs uv (Python) on your computer.

## Recent changes

- 2026-10-18 04:21 UTC: Tracking started: version 0.8.2. Source: automatic check.

More on the History tab, with descriptions before and after for the newest entries: https://mcp.tc/i/neo4j-data-modeling#history (Atom feed: https://mcp.tc/i/neo4j-data-modeling/history.xml). It records what mcp.tc's anonymous checks saw, every 3 hours where the tool list can be read without sign-in; it is not a security review.

## Details

- Server version: 0.8.2
- Last checked: 2026-10-18
- Listed: 2026-10-18
- Updated: 2026-10-18

---
Source: https://mcp.tc/i/neo4j-data-modeling (mcp.tc is an independent directory, not affiliated with this server's publisher). Corrections: https://mcp.tc/report
