@JovanHsu
Basic information
MCP Memory Server with Neo4j backend for AI knowledge graph storage
Add this server to your MCP-compatible client using the configuration below.
{
"mcpServers": {
"mcp-neo4j-memory-server-jovanhsu": {
"command": "npx",
"args": [
"@jovanhsu/mcp-neo4j-memory-server"
]
}
}
}Tool list not available yet
This listing does not currently have a tool list to display. This does not mean the server has no tools; check its documentation for supported capabilities.
Fetch the live tool list by running this server in a temporary sandbox using the button above.
MCP Neo4j Knowledge Graph Memory Server is an MCP-compatible server that uses Neo4j as its backend storage engine for persisting and retrieving knowledge graphs during AI assistant interactions. It is an enhanced version of the official Knowledge Graph Memory Server, aimed at developers who need a scalable, queryable memory layer for AI conversations.
Install via npm (npm install -g @jovanhsu/mcp-neo4j-memory-server) or Docker. Configure environment variables NEO4J_URI, NEO4J_USER, NEO4J_PASSWORD, and NEO4J_DATABASE. Integrate with Claude Desktop by adding the server configuration to claude_desktop_config.json, or use MCP Inspector for testing. The server exposes tools to create, read, update, and delete entities, relations, and observations.
It offers native graph storage, high-performance Cypher queries, first-class relationship handling, built-in visualisation, and better scalability for large knowledge graphs.
Node.js >= 22.0.0 and a Neo4j database (local or remote) are required.
Set the environment variables `NEO4J_URI`, `NEO4J_USER`, `NEO4J_PASSWORD`, and `NEO4J_DATABASE`. If not set, defaults point to `bolt://localhost:7687` with user `neo4j` and password `password`.
Data is stored in your Neo4j database. The server does not persist any data locally; all entities, relations, and observations are written into the configured Neo4j instance.
It uses the MCP protocol over stdio transport, enabling integration with Claude Desktop or any MCP client. Authentication to Neo4j is handled via environment credentials, not through the MCP layer.
AI agents start every session with amnesia — you re-explain the project, repeat your preferences, and correct the same mistakes over and over. PLUR gives them a memory that persists. Your agent's corrections, preference
Persistent memory for AI agents. Hosted MCP server with capsule-scoped key/value storage, tags, TTL expiration, bulk ops, and RBAC.
Orcha is a unified context layer for AI tools and agents. It stores and indexes and exposes organizational, team, or individual knowledge. Files, structured databases, and connected sources live in one workspace, and age
Personal context for every AI: search, read, and write back to your private Markdown library of articles, threads, PDFs, notes, and captured ChatGPT/Claude/Gemini/Grok conversations. Remote server, OAuth 2.1 paste-and-au
Exact, shared memory for AI agents: a hierarchical database where totals always add up, every write is attributed to the agent and person behind it, and any figure traces back to its source file. Agents create databases,
Comments