a-s-g93/ai-engineer-neo4j-memory-demo
If you are the rightful owner of ai-engineer-neo4j-memory-demo and would like to certify it and/or have it hosted online, please leave a comment on the right or send an email to henry@mcphub.com.
The Neo4j Memory MCP Server is a Python-based server that integrates with Claude Desktop to provide agentic memory capabilities using a Neo4j database.
The Neo4j Memory MCP Server is designed to enhance the capabilities of Claude Desktop by integrating a memory system that leverages the power of Neo4j databases. This server allows for the storage and retrieval of semantic memories, enabling more contextually aware interactions. By using a knowledge graph, the server can store entities, relationships, and observations, which can be accessed and updated during interactions. This setup not only improves the continuity of conversations but also allows for the sharing of memories across different clients configured with the same Neo4j instance. The server is managed using the uv Python Package Manager, ensuring a streamlined installation and configuration process. Users can choose between a cloud-hosted Neo4j Aura instance or a local Neo4j Desktop instance for their database needs. The integration with Claude Desktop is facilitated through a configuration file, where users can specify their database credentials and set up memory retrieval and update protocols.
Features
- Integration with Neo4j Database for memory storage and retrieval.
- Agentic memory capabilities for enhanced conversational context.
- Support for both cloud-hosted and local Neo4j instances.
- Seamless integration with Claude Desktop through configuration files.
- Ability to share memories across different clients using the same database.
Usages
usage with Claude Desktop
{ "mcpServers": { "neo4j-memory-store": { "command": "uvx", "args": [ "mcp-neo4j-memory@0.1.4" ], "env": { "NEO4J_URL": "bolt://localhost:7687", "NEO4J_USERNAME": "neo4j", "NEO4J_PASSWORD": "password", "NEO4J_DATABASE": "neo4j" } } } }