Neo4j Server
About
Interact with and explore graph data in a Neo4j database.
Details
- Author
- dsimile
- Categories
- Database, Other, Knowledge Base
Jump to
Setup
Install Neo4j Server in your MCP client (Claude Desktop, Cursor, Windsurf, and others).
Repository: https://github.com/dsimile/mcp-neo4j-server-sse
Follow the installation instructions in the repository README, then restart your MCP client.
neo4j-server-remote is an MCP server that uses Server-Sent Events (SSE) or STDIO as the transport protocol.
A Model Context Protocol (MCP) server implementation that provides database interaction and allows for graph exploration capabilities through Neo4j. This server enables the execution of Cypher graph queries, analysis of complex domain data, and supports the selection of remotely accessible databases. Inspired byneo4j-contrib/mcp-neo4j.
The server provides a demonstration prompt:
- mcp-demo: Interactive prompt that guides users through database operations
- Generates appropriate database schemas and sample data
- Execute Cypher read queries to read data from the database
- Input:
- query(string): The Cypher query to execute
- Execute updating Cypher queries
- Input:
- query(string): The Cypher update query
- get-neo4j-schema
- Get a list of all nodes types in the graph database, their attributes with name, type and relationships to other node types
- No input required
- Returns: List of node label with two dictionaries one for attributes and one for relationships
git clone https://github.com/dsimile/mcp-neo4j-server-sse.git
cd mcp-neo4j-server-sse pip install -r requirements.txt
Run the MCP server using the UX command, and select the database of your choice. The default IP address is 0.0.0.0, and the default port is 8543.
uv run .\src\mcp-neo4j-cypher\neo4j_server_remote.py --url bolt://localhost:7687 --username neo4j --password neo4j123 --database neo4j
Run the MCP server locally using the UX command with the mode set to STDIO and the same Neo4j connection information.
Note: Please ensure that Neo4j is running and accessible for remote connections.
Add the server configuration to yourcline_mcp_settings.json.
{ "mcpServers": { "neo4j-remote": { "url": "http://0.0.0.0:8543/sse", "disabled": false, "autoApprove": [] } } }
{ "mcpServers": { "neo4j-local": { "disabled": false, "timeout": 60, "command": "uv", "args": [ "run", "/absolute/path/to/neo4j_server_remote.py", "--url", "bolt://localhost:7687", "--username", "neo4j", "--password", "neo4j123", "--database", "neo4j", "--mode", "stdio" ] } } }
This MCP server is licensed under the MIT License. This means you are free to use, modify, and distribute the software, subject to the terms and conditions of the MIT License. For more details, please see the LICENSE file in the project repository.
Neo4j graph database server (schema + read/write-cypher) and separate graph database backed memory
Query a hybrid graph (Neo4j) and vector (Qdrant) database for powerful semantic and graph-based document retrieval.
Connects to Neo4j graph databases with ability to use GDS functions ( when available), a read only mode , and set the sample size for schema detection
Integrate the Neo4j graph database with clients through natural language interactions.
MCP server for Neo4j — run Cypher queries, explore schema, and inspect database info over stdio
Cognitive memory for AI agents - persistent semantic memory with knowledge graph and adaptive recall
A server for interacting with ArangoDB, a native multi-model database system.
Manage graph-based data models, schemas, and ontologies with CoreModels. 16 MCP tools for visual data modeling with full JSON Schema support.
Query and interact with FalkorDB graph databases using AI models.
Sign in to leave a review
Use Google, GitHub, or an email account so ratings stay tied to real people.
No reviews posted yet.
