Neo4j MCP

Neo4j MCP gives AI assistants and LLM-powered tools direct, structured access to your Neo4j graph database. By implementing the Model Context Protocol (MCP), it acts as a bridge between any MCP-compatible client, such as Claude, Cursor, or VS Code with MCP support, and your Neo4j instance.

Features

• Explore your graph schema - discover node labels, relationship types, and property keys
• Let AI reason on your data model without prior knowledge
• Run Cypher queries - execute, read, and write queries against your database in response to natural language prompts
• Inspect and analyze data - retrieve nodes, relationships, and paths to answer questions, generate summaries, or feed data to other workflows

Tools

• get-schema — introspect labels, relationship types, property keys
• read-cypher — execute read-only Cypher queries that do not modify database data, enforced via EXPLAIN and Neo4j's query-type classification. Note: custom procedures or functions incorrectly classified as read-only by Neo4j may bypass this check; ensuring correct classification is the responsibility of the procedure/function maintainer.
• write-cypher — execute write Cypher queries (disabled if NEO4J_MCP_READ_ONLY=true)
• list-gds-procedures — list available GDS procedures

Installation

Install with PyPI:

pip install neo4j-mcp-server

For manual installation or using brew, please see MCP documentation -> Installation.

Server configuration (VSCode - STDIO)

Create / edit mcp.json:

{
  "servers": {
    "neo4j": {
      "type": "stdio",
      "command": "python",
      "args": ["-m", "neo4j_mcp_server"],
      "env": {
        "NEO4J_MCP_URI": "bolt://localhost:7687",
        "NEO4J_MCP_USERNAME": "neo4j",
        "NEO4J_MCP_PASSWORD": "password",
        "NEO4J_MCP_DATABASE": "neo4j",
      }
    }
  }
}

See MCP documentation > Configuration for more details.

Links

• Documentation: The official Neo4j MCP documentation.
• Discord: The Neo4j discord channel.
• Contributing Guide: Contribution workflow, development environment, mocks and testing.

For issues and feedback, you can also create a GitHub issue with reproduction details (omit sensitive data).