Happy slice of mcp pizzaMCP.pizza

neo4j-contrib_mcp-neo4j

MCP.Pizza Chef: MCP-Mirror

The neo4j-contrib_mcp-neo4j server is an MCP server implementation that integrates Neo4j graph database capabilities with the Model Context Protocol. It enables natural language queries to be translated into Cypher queries, allowing LLMs and MCP clients like Claude Desktop to interact with Neo4j graphs seamlessly. This server supports knowledge graph memory stored in Neo4j and JSON files, facilitating advanced graph-based memory and context management for AI workflows. It is ideal for developers looking to leverage graph databases in AI-enhanced applications using standardized MCP interfaces.

Use This MCP server To

Translate natural language to Cypher queries for Neo4j Store and retrieve knowledge graph memory in Neo4j Manage graph-based memory for AI agents Integrate Neo4j with MCP clients like Claude Desktop Query Neo4j Aura accounts via natural language Model knowledge graphs as MCP memory servers Enable LLMs to interact with graph databases Use JSON files for graph memory storage

README

Neo4j MCP Clients & Servers

Model Context Protocol (MCP) is a standardized protocol for managing context between large language models (LLMs) and external systems.

This lets you use Claude Desktop, or any MCP Client, to use natural language to accomplish things with Neo4j and your Aura account, e.g.:

  • What is in this graph?

Servers

mcp-neo4j-cypher - natural language to Cypher queries

mcp-neo4j-memory - knowledge graph memory stored in Neo4j

mcp-json-memory - knowledge graph memory stored in a file

A reference server for modeling memory as a knowledge graph.

Contributing

Contributions are welcome! Please feel free to submit a Pull Request.

neo4j-contrib_mcp-neo4j FAQ

How do I connect the neo4j-contrib_mcp-neo4j server to my Neo4j Aura account?
You configure the server with your Aura credentials and connection URI, enabling secure access to your Neo4j instance for natural language queries.
Can this server convert natural language queries into Cypher automatically?
Yes, the mcp-neo4j-cypher component translates natural language inputs into Cypher queries for Neo4j graph traversal and data retrieval.
Is it possible to store AI memory as a knowledge graph using this server?
Absolutely, the mcp-neo4j-memory server stores knowledge graph memory directly in Neo4j, supporting advanced context management for AI agents.
Does this server support storing memory in formats other than Neo4j?
Yes, the mcp-json-memory server allows storing knowledge graph memory in JSON files as an alternative to Neo4j storage.
How can I integrate this MCP server with different MCP clients?
The server follows the MCP standard, making it compatible with any MCP client such as Claude Desktop, enabling seamless interaction.
Are contributions to the neo4j-contrib_mcp-neo4j project welcome?
Yes, contributions are encouraged via pull requests on the GitHub repository to improve features and compatibility.
What are the security considerations when using this server?
Secure connection credentials and access controls should be used to protect your Neo4j Aura account and data when interfacing through MCP.
Can this server be used with multiple LLM providers?
Yes, it is designed to work with various LLMs including OpenAI, Claude, and Gemini through MCP clients.