MCP Memory Bank

🚀 Running with Docker

This project is fully prepared for simple deployment via Docker and local development. The provided Dockerfile and docker-compose.yml configuration files can simultaneously set up the main application and its required ChromaDB vector database.

🚀 Quick Start

Prerequisites

• Docker (latest stable version)
• Docker Compose (v2 or higher recommended)

Environment Variables

By default, the following environment variables are used (which can be overridden via your environment or docker-compose.yml):

CHROMADB_URL=http://chromadb:8000
TRANSPORT=http
HTTP_PORT=3000
MCP_MEMBANK_EMBEDDING_MODEL=Xenova/all-MiniLM-L6-v2
NODE_ENV=production
NODE_OPTIONS=--max-old-space-size=4096

Building and Running

To build and start all services:

docker-compose up --build -d

This will:

• Build the main TypeScript application (based on Node.js v22.13.1-slim)
• Start the ts-app service (listening on port 3000)
• Start the ChromaDB service chromadb (listening on port 8000)
• Create a persistent storage volume for ChromaDB data
• Set up a shared Docker network for inter-service communication

Ports

• 3000: Main application HTTP API (ts-app)
• 8000: ChromaDB vector database (chromadb)

Data Persistence

• ChromaDB data is persisted in a named Docker volume called chromadb-data.
• The application data directory (/app/data) will be created and owned by a non-root user inside the container.

Special Notes

• This application requires ChromaDB to be available at the URL specified by CHROMADB_URL (default: http://chromadb:8000).
• The embedding model can be changed via the MCP_MEMBANK_EMBEDDING_MODEL environment variable.
• If you need to customize environment variables, you can edit the docker-compose.yml file or use a .env file.