mcp-neo4j-data-modeling — Claude Code MCP server
This MCP server helps agents build, validate, and visualize Neo4j graph models. Use it when a schema needs nodes, relationships, and properties.
claude mcp add --env NEO4J_NAMESPACE=<NEO4J_NAMESPACE> --transport stdio mcp-neo4j-data-modeling -- uvx mcp-neo4j-data-modelingWhat mcp-neo4j-data-modeling does
mcp-neo4j-data-modeling gives an agent tools for working with Neo4j graph models. It can validate nodes, relationships, or a complete data model, then produce a Mermaid configuration for visualization. Resources include JSON schemas for model objects, example models, and a guide to the Neo4j data ingest process.
The server imports and exports models through Arrows JSON and OWL Turtle. It can also generate Pydantic models and schemas for the Neo4j GraphRAG Python Package. During OWL conversion, classes are mapped to nodes; relationship-attached properties are dropped when a model is exported to OWL.
The environment-based setup uses uvx and NEO4J_NAMESPACE. Without NEO4J_NAMESPACE, the command using that setting will not start the server with the required configuration.
What it helps with
- design a Neo4j graph model
- validate a node or relationship
- render a model as Mermaid configuration
- import a schema from Arrows JSON
- export a model as Pydantic classes
Example prompts for the agent
- Design a Neo4j model for orders, products, and warehouses, then validate it with
validate_data_model. - Validate this node with
validate_nodeand create a Mermaid configuration withget_mermaid_config_str. - Load the model from OWL Turtle with
load_from_owl_turtle, then export it to Arrows format withexport_to_arrows_json.
How to install mcp-neo4j-data-modeling
Platform CLI
claude mcp add --env NEO4J_NAMESPACE=<NEO4J_NAMESPACE> --transport stdio mcp-neo4j-data-modeling -- uvx mcp-neo4j-data-modelingReplace <…> with your own values. uvx runs the command named after the package; if the README names another one, use uvx --from mcp-neo4j-data-modeling <command>
Platform CLI
codex mcp add mcp-neo4j-data-modeling --env NEO4J_NAMESPACE=<NEO4J_NAMESPACE> -- uvx mcp-neo4j-data-modelingReplace <…> with your own values. uvx runs the command named after the package; if the README names another one, use uvx --from mcp-neo4j-data-modeling <command>
Config file
{
"mcpServers": {
"mcp-neo4j-data-modeling": {
"command": "uvx",
"args": [
"mcp-neo4j-data-modeling"
],
"env": {
"NEO4J_NAMESPACE": "<NEO4J_NAMESPACE>"
}
}
}
}Replace <…> with your own values. uvx runs the command named after the package; if the README names another one, use uvx --from mcp-neo4j-data-modeling <command>
Config file
{
"servers": {
"mcp-neo4j-data-modeling": {
"type": "stdio",
"command": "uvx",
"args": [
"mcp-neo4j-data-modeling"
],
"env": {
"NEO4J_NAMESPACE": "<NEO4J_NAMESPACE>"
}
}
}
}Replace <…> with your own values. uvx runs the command named after the package; if the README names another one, use uvx --from mcp-neo4j-data-modeling <command>
Platform CLI
gemini mcp add -e NEO4J_NAMESPACE=<NEO4J_NAMESPACE> mcp-neo4j-data-modeling uvx mcp-neo4j-data-modelingReplace <…> with your own values. uvx runs the command named after the package; if the README names another one, use uvx --from mcp-neo4j-data-modeling <command>
Step by step, with commands for each platform: How to add an MCP server to Claude Code, Codex, Cursor, VS Code, Gemini CLI and more
Questions about mcp-neo4j-data-modeling
How do I install mcp-neo4j-data-modeling in Claude Code?
Run claude mcp add --env NEO4J_NAMESPACE=<NEO4J_NAMESPACE> --transport stdio mcp-neo4j-data-modeling -- uvx mcp-neo4j-data-modeling.
What does mcp-neo4j-data-modeling do?
It provides tools for creating, validating, and visualizing Neo4j graph models. It also supports model import and export in several formats.
What happens when a model is converted to OWL Turtle?
Nodes and relationships are mapped to OWL constructs, but properties attached to relationships are left out during export.
