Neo4j Labs MCP Servers

1# Neo4j Labs MCP Servers
2 
3## Neo4j Labs
4 
5These MCP servers are a part of the [Neo4j Labs](https://neo4j.com/labs/) program. 
6They are developed and maintained by the Neo4j Field GenAI team and welcome contributions from the larger developer community. 
7These servers are frequently updated with new and experimental features, but are not supported by the Neo4j product team. 
8 
9**They are actively developed and maintained, but we don’t provide any SLAs or guarantees around backwards compatibility and deprecation.**
10 
11If you are looking for the official product Neo4j MCP server please find it [here](https://github.com/neo4j/mcp).
12 
13## Overview
14 
15Model Context Protocol (MCP) is a [standardized protocol](https://modelcontextprotocol.io/introduction) for managing context between large language models (LLMs) and external systems. 
16 
17This lets you use Claude Desktop, or any other MCP Client (VS Code, Cursor, Windsurf, Gemini CLI), to use natural language to accomplish things with Neo4j and your Aura account, e.g.:
18 
19* What is in this graph?
20* Render a chart from the top products sold by frequency, total and average volume
21* List my instances
22* Create a new instance named mcp-test for Aura Professional with 4GB and Graph Data Science enabled
23* Store the fact that I worked on the Neo4j MCP Servers today with Andreas and Oskar
24 
25## Servers
26 
27### `mcp-neo4j-cypher` - natural language to Cypher queries
28 
29[Details in Readme](./servers/mcp-neo4j-cypher/)
30 
31Get database schema for a configured database and execute generated read and write Cypher queries on that database.
32 
33**Requirement**: Requires the [APOC plugin](https://neo4j.com/docs/apoc/current/installation/) to be installed and enabled on the Neo4j instance for schema inspection.
34 
35### `mcp-neo4j-memory` - knowledge graph memory stored in Neo4j
36 
37[Details in Readme](./servers/mcp-neo4j-memory/)
38 
39Store and retrieve entities and relationships from your personal knowledge graph in a local or remote Neo4j instance.
40Access that information over different sessions, conversations, clients.
41 
42### `mcp-neo4j-cloud-aura-api` - Neo4j Aura cloud service management API
43 
44[Details in Readme](./servers/mcp-neo4j-cloud-aura-api//)
45 
46Manage your [Neo4j Aura](https://console.neo4j.io) instances directly from the comfort of your AI assistant chat.
47 
48Create and destroy instances, find instances by name, scale them up and down and enable features.
49 
50### `mcp-neo4j-data-modeling` - interactive graph data modeling and visualization
51 
52[Details in Readme](./servers/mcp-neo4j-data-modeling/)
53 
54Create, validate, and visualize Neo4j graph data models. Allows for model import/export from Arrows.app.
55 
56## Transport Modes
57 
58All servers support multiple transport modes:
59 
60- **STDIO** (default): Standard input/output for local tools and Claude Desktop integration
61- **SSE**: Server-Sent Events for web-based deployments
62- **HTTP**: Streamable HTTP for modern web deployments and microservices
63 
64### HTTP Transport Configuration
65 
66To run a server in HTTP mode, use the `--transport http` flag:
67 
68```bash
69# Basic HTTP mode
70mcp-neo4j-cypher --transport http
71 
72# Custom HTTP configuration
73mcp-neo4j-cypher --transport http --host 127.0.0.1 --port 8080 --path /api/mcp/
74```
75 
76Environment variables are also supported:
77 
78```bash
79export NEO4J_TRANSPORT=http
80export NEO4J_MCP_SERVER_HOST=127.0.0.1
81export NEO4J_MCP_SERVER_PORT=8080
82export NEO4J_MCP_SERVER_PATH=/api/mcp/
83mcp-neo4j-cypher
84```
85 
86## Cloud Deployment
87 
88All servers in this repository are containerized and ready for cloud deployment on platforms like AWS ECS Fargate and Azure Container Apps. Each server supports HTTP transport mode specifically designed for scalable, production-ready deployments with auto-scaling and load balancing capabilities.
89 
90📋 **[Complete Cloud Deployment Guide →](README-Cloud.md)**
91 
92The deployment guide covers:
93- **AWS ECS Fargate**: Step-by-step deployment with auto-scaling and Application Load Balancer
94- **Azure Container Apps**: Serverless container deployment with built-in scaling and traffic management
95- **Configuration Best Practices**: Security, monitoring, resource recommendations, and troubleshooting
96- **Integration Examples**: Connecting MCP clients to cloud-deployed servers
97 
98## Contributing
99 
100Contributions are welcome! Please feel free to submit a Pull Request.
101 
102## Blog Posts
103 
104* [Everything a Developer Needs to Know About the Model Context Protocol (MCP)](https://neo4j.com/blog/developer/model-context-protocol/)
105* [Claude Converses With Neo4j Via MCP - Graph Database & Analytics](https://neo4j.com/blog/developer/claude-converses-neo4j-via-mcp/)
106* [Building Knowledge Graphs With Claude and Neo4j: A No-Code MCP Approach - Graph Database & Analytics](https://neo4j.com/blog/developer/knowledge-graphs-claude-neo4j-mcp/)
107* [Using the Neo4j Extension in Gemini CLI](https://cloud.google.com/blog/topics/developers-practitioners/using-the-neo4j-extension-in-gemini-cli)
108 
109## License
110 
111MIT License
112