@gannonh/memento-mcp

@gannonh419

A scalable, high-performance knowledge graph memory system for LLMs with semantic retrieval, contextual recall, and temporal awareness, using Neo4j as its storage backend.

knowledge graphmemoryLLMssemantic searchtemporal awarenessNeo4jcontext

Installation & Configuration

{
  "mcpServers": {
    "memento": {
      "command": "npx",
      "args": [
        "-y",
        "@gannonh/memento-mcp"
      ],
      "env": {
        "MEMORY_STORAGE_TYPE": "neo4j",
        "NEO4J_URI": "bolt://127.0.0.1:7687",
        "NEO4J_USERNAME": "neo4j",
        "NEO4J_PASSWORD": "memento_password",
        "NEO4J_DATABASE": "neo4j",
        "NEO4J_VECTOR_INDEX": "entity_embeddings",
        "NEO4J_VECTOR_DIMENSIONS": "1536",
        "NEO4J_SIMILARITY_FUNCTION": "cosine",
        "OPENAI_API_KEY": "your-openai-api-key",
        "OPENAI_EMBEDDING_MODEL": "text-embedding-3-small",
        "DEBUG": "true"
      }
    }
  }
}

Information

Transport

stdio

Language

TypeScript

Created

2025/3/30

Updated

2026/6/8

Homepage

https://github.com/gannonh/memento-mcp