Neo4j MCP Server for Cursor

@ezedinff

Basic information

About Neo4j MCP Server for Cursor

A Cursor MCP (Model Context Protocol) server that enables seamless interaction with Neo4j databases directly from the Cursor IDE.

#ai #mcp #cursor

Neo4j MCP Server for Cursor config

Add this server to your MCP-compatible client using the configuration below.

{
  "mcpServers": {
    "neo4j-mcp": {
      "command": "bun",
      "args": [
        "run",
        "index.ts"
      ]
    }
  }
}

Neo4j MCP Server for Cursor tools

Tool list not available yet

This listing does not currently have a tool list to display. This does not mean the server has no tools; check its documentation for supported capabilities.

We auto-extract tools from the README. The maintainer can list them under a ## Tools heading to populate this section.

Overview

What is Neo4j MCP Server for Cursor?

The Neo4j MCP Server for Cursor is a Model Context Protocol server that allows users to interact with Neo4j databases directly from the Cursor IDE. It enables executing Cypher queries, retrieving database metrics, and monitoring connection status through standard MCP tools.

How to use Neo4j MCP Server for Cursor?

Clone the repository, install dependencies with Bun (v1.0.0+), and configure Neo4j credentials in a .env file. The server uses stdio transport and is launched by Cursor. Six tools are available: connect with explicit credentials, connect with environment variables, execute a Cypher query, get database information, get connection status, and disconnect. For testing, run bun run index.ts or ./run-mcp-server.sh.

Key features of Neo4j MCP Server for Cursor

Connect to local or remote Neo4j databases
Execute Cypher queries with optional parameters
Transform Neo4j data types to JavaScript objects
Retrieve database version, node counts, and labels
Monitor connection state and diagnostics
Manage credentials securely via environment variables

Use cases of Neo4j MCP Server for Cursor

Run Cypher queries to explore a graph database while coding
Inspect database schema (labels, relationship types) without leaving Cursor
Automate integration tests that interact with a Neo4j database
Monitor database health and connection status during development

Frequently asked questions

What are the prerequisites for using Neo4j MCP Server for Cursor?

Bun v1.0.0 or higher and a Neo4j database (local or remote) are required. A Docker Compose file is included to run Neo4j locally.

How do I connect to a Neo4j database?

You can connect using explicit credentials (URI, username, password) or by setting environment variables (`NEO4J_URI`, `NEO4J_USERNAME`, `NEO4J_PASSWORD`, `NEO4J_DATABASE`) in a `.env` file.

What transport does the server use?

The server uses stdio transport via the official MCP SDK, designed for seamless integration with Cursor’s MCP support.

Can I run the server outside of Cursor for testing?

Yes, you can run `bun run index.ts` or the provided shell script `./run-mcp-server.sh` to test the server manually.

How are credentials secured?

Credentials can be stored in a `.env` file or passed as parameters to the “Connect” tool. The README advises using a secure password in production.

Comments

More Developer Tools MCP servers

Kaiva Bridge

Kaiva Bridge turns your API, database or documents into a managed MCP server for Claude, ChatGPT, Cursor and VS Code. Point it at an OpenAPI or Swagger spec, an API docs link, a cURL command, a Postman collection, a Grap

Cronwatch

cronwatchdev

CronWatch records every run of your scheduled jobs in your own database, and speaks up when one is missed, fails, gets stuck, runs slow or costs too much. CronWatch is free and open-source.

Eddyter AI Rich Text Editor MCP

EddyterAI

Set up and manage the Eddyter AI rich text editor by talking to your AI agent — for Claude, Cursor, Codex and other MCP tools. A Model Context Protocol server that lets AI tools add Eddyter to a React, Next.js, Vite or R

Routebase

Routebase keeps your API's design, docs, contract tests, mocks and monitoring in one living OpenAPI spec so they can't drift apart. Agents work on that same source of truth, under your team's permissions.