# Server Configuration
MCP_SERVER_NAME=memory
MCP_SERVER_VERSION=1.0.0
MCP_SERVER_DISPLAY_NAME=Memory Server
MCP_SERVER_DESCRIPTION=A server for storing and retrieving memories with semantic search capabilities
MCP_SERVER_PUBLISHER=MCP
MCP_PROTOCOL_VERSION=2024-11-05
# Logging Configuration
MCP_DEBUG_LOG_PATH=memory-debug.log
# Database Configuration
DATABASE_URL=postgresql://user:password@localhost:5432/mcp_memory
DB_MAX_POOL_SIZE=20
DB_IDLE_TIMEOUT=30000
# Embeddings Configuration
EMBEDDINGS_MODEL=Xenova/all-MiniLM-L6-v2
EMBEDDINGS_POOLING=mean
EMBEDDINGS_NORMALIZE=true
# Search Configuration
SEARCH_DEFAULT_LIMIT=10
# Node Environment
NODE_ENV=production
# Optional: Port Configuration (if needed)
# PORT=3000
# Note: For local development with peer authentication, you can use:
# DATABASE_URL="postgresql:///mcp_memory"
MCP directory API
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/sdimitrov/mcp-memory'
If you have feedback or need assistance with the MCP directory API, please join our Discord server