neo4j-contrib/mcp-neo4j

Overview

An open-source Model Context Protocol (MCP) server that connects AI agents to Neo4j graph databases. It translates MCP requests into Cypher queries, enabling agents to read and write graph data. Developed by Neo4j Labs, written in Python.

Best for

Best for
Developers building Python-based AI agents that need structured access to Neo4j graph databases via the Model Context Protocol

Use cases

• Allow an AI coding assistant to query a Neo4j knowledge graph for context
• Let a conversational agent retrieve and update graph-based data during a session
• Enable autonomous agents to explore database schema and execute read-only Cypher queries

How to use

Tested with

Claude Desktop, VS Code, Cursor, Windsurf, Gemini CLI

Notes

An open-source Model Context Protocol (MCP) server that connects AI agents to Neo4j graph databases. It translates MCP requests into Cypher queries, enabling agents to read and write graph data. Developed by Neo4j Labs, written in Python.

951 stars on GitHub. Last updated 2026-04-10. Licensed MIT.

Use cases

• Allow an AI coding assistant to query a Neo4j knowledge graph for context
• Let a conversational agent retrieve and update graph-based data during a session
• Enable autonomous agents to explore database schema and execute read-only Cypher queries

Pros

• Leverages the emerging MCP standard for tool interoperability
• Maintained by Neo4j Labs with 950+ GitHub stars
• Straightforward Python implementation easy to extend or debug

Cons

• Requires a running Neo4j database instance to function
• MCP ecosystem is still maturing, so integration options are limited
• No built-in support for authentication or multi-user scenarios

Indexed from awesome-mcp-servers-punkpeye and enriched against its public facts.