---
name: "Query Neo4j graph data from agent workflows through MCP"
slug: "query-neo4j-graph-data-from-agent-workflows-through-mcp"
description: "Connect MCP-compatible agents to Neo4j so they can inspect graph schemas, run Cypher queries, manage graph memory, and operate Aura instances from chat."
github_stars: 947
verification: "security_reviewed"
source: "https://github.com/neo4j-contrib/mcp-neo4j"
author: "Neo4j Labs"
publisher_type: "organization"
category: "Data Extraction & Transformation"
framework: "MCP"
tool_ecosystem:
  github_repo: "neo4j-contrib/mcp-neo4j"
  github_stars: 947
---

# Query Neo4j graph data from agent workflows through MCP

Connect MCP-compatible agents to Neo4j so they can inspect graph schemas, run Cypher queries, manage graph memory, and operate Aura instances from chat.

## Prerequisites

Neo4j database or Aura account, APOC for schema inspection, Python package or uvx, MCP-compatible client

## Installation

Requirements and caveats from upstream:
- **Requirement**: Requires the [APOC plugin](https://neo4j.com/docs/apoc/current/installation/) to be installed and enabled on the Neo4j instance for schema inspection.

Basic usage or getting-started notes:
- To run a server in HTTP mode, use the --transport http flag:

- Source: https://github.com/neo4j-contrib/mcp-neo4j
- Extracted from upstream docs: https://raw.githubusercontent.com/neo4j-contrib/mcp-neo4j/HEAD/README.md

## Documentation

- https://neo4j.com/developer/genai-ecosystem/model-context-protocol-mcp/

## Source

- [Agent Skill Exchange](https://agentskillexchange.com/skills/query-neo4j-graph-data-from-agent-workflows-through-mcp/)