Neo4j MCP Server
Connect to Neo4j graph databases. Allow AI models to execute Cypher queries and traverse intricate network relationships.
Quick Answer / TL;DR
The Neo4j MCP server establishes a secure, local or remote JSON-RPC 2.0 communication tunnel, allowing AI models (like Claude or Cursor) to automatically discover and execute capabilities (tools, prompts, and resources) within the Neo4j ecosystem with extremely low latency.
Key Takeaways
- Map graph database nodes
- Analyze fraud networks
- Retrieve path connections
Core Integration Concept
Connecting the model to Neo4j bypasses complex setup. The LLM can auto-discover what endpoints are active, what input variables are expected, and how answers will be delivered.
Verified Use Cases
Setup Overview
Connection Setup Checklist
- Prepare Credentials: Obtain your Neo4j Auth Credentials credentials directly from your Neo4j settings.
- Update Config: Add the executable tool command structure directly to your Claude config file.
- Restart & Confirm: Reload the desktop model client to complete the connection handshake sequence.
Sample Connection Schema
{
"jsonrpc": "2.0",
"method": "tools/call",
"params": {
"name": "execute_neo4j",
"arguments": {
"query": "status_check"
}
},
"id": 1
}Security Considerations
To guarantee perfect data isolation, safeguard the Neo4j Auth Credentials credentials. Always run integrations in sandboxed contexts to block unsolicited access.
Best Practices
- Configure exact resource boundaries for the Cypher queries execution feature.
- Configure exact resource boundaries for the Graph metadata map feature.
- Configure exact resource boundaries for the Node count tallies feature.
- Configure exact resource boundaries for the Relationship insights feature.
Required Auth Keys
Neo4j Auth Credentials
Deploy Neo4j Server
Deploy this Neo4j integration to our global edge container cluster. Zero DevOps, instant SSE.
Related Connectors
Neo4j - FAQ
Contextual information and technical support details regarding Model Context Protocol integration