Memento

🚀 Memento MCP Usage Guide

Memento MCP is an advanced knowledge graph implementation that provides persistent memory capabilities for conversational AI. Through natural language processing and semantic search, it enables AI to understand and retrieve long - term stored information.

🚀 Quick Start

✨ Features

Memento MCP is an advanced knowledge graph implementation, offering persistent memory capabilities for conversational AI. It leverages natural language processing and semantic search, empowering AI to understand and retrieve long - term stored information.

📦 Installation

Basic Installation

Automatically install Memento MCP using Smithery:

npx -y @smithery/cli install @gannonh/memento-mcp --client claude

Global Installation (Recommended)

Run directly via npx:

npx -y @gannonh/memento-mcp

Local Installation

Clone the repository and install dependencies:

git clone https://github.com/gannonh/memento-mcp.git
cd memento-mcp
npm install

Configuration Guide

Basic Configuration

Edit the config.json file and add the following content:

{
  "neo4j": {
    "uri": "bolt://localhost:7687",
    "user": "neo4j",
    "password": "password"
  }
}

Debug Settings (DEBUG=true)

Enable debug mode to get more log information:

DEBUG=memento npm start

Integration and Development

Initialize the Knowledge Graph

Run the following command to initialize the database schema:

npm run neo4j:init

Developer Reset

Stop and delete the Docker container, clean the data directory, and then restart the database.

Troubleshooting

Vector Search Diagnosis

Use the following tools to check the vector index status and entity embeddings:

• diagnose_vector_search
• force_generate_embedding
• debug_embedding_config

Embedding Validation

The system will automatically check and generate missing entity embeddings.

Testing and Building

Run the test suite and check the coverage:

npm test
npm run test:coverage

💻 Usage Examples

Basic Usage

1. Create a knowledge graph entity:

User: "Remember that Python is a high - level programming language known for its readability and JavaScript is primarily used for web development."

2. Perform a semantic search:

User: "What programming languages do you know about that are good for web development?"

3. Retrieve specific information:

User: "Tell me everything you know about Python."

📄 License

MIT License

With the above guide, you can easily configure and use Memento MCP to enhance the memory function of conversational AI.