Skip to main content
Glama

Server Configuration

Describes the environment variables required to run the server.

NameRequiredDescriptionDefault
LOG_LEVELNoLogging verbosity levelINFO
CURSOR_MODENoPlatform-specific optimizations for Cursor IDEtrue
ENVIRONMENTNoCurrent environment modedevelopment
MONGODB_URINoDatabase connection for persistent memory storagemongodb://localhost:27017
SERVER_MODENoArchitecture mode (universal for modern unified server)universal
ML_MODEL_TYPENoType of ML model (huggingface for transformer models)huggingface
EMBEDDING_MODELNoLightweight, fast embedding modelall-MiniLM-L6-v2
ML_TRIGGER_MODENoCombines ML model + deterministic ruleshybrid
MEMORY_THRESHOLDNoMemory importance filtering (70%)0.7
MONGODB_DATABASENoDatabase name for memory collectionsmcp_memory_dev
PRELOAD_ML_MODELNoLoads ML model at startup for faster response timestrue
TRIGGER_THRESHOLDNoGeneral trigger activation sensitivity (15%)0.15
EMBEDDING_PROVIDERNoVector embedding enginesentence_transformers
SEMANTIC_THRESHOLDNoContext similarity matching (80%)0.8
ML_RETRAIN_INTERVALNoRetrain model after 50 new samples50
ML_TRAINING_ENABLEDNoEnables model improvement over timetrue
AUTO_TRIGGER_ENABLEDNoEnables automatic memory operations without user commandstrue
SIMILARITY_THRESHOLDNoSemantic search matching threshold (30%)0.3
BEHAVIOR_HISTORY_LIMITNoMaximum behavior samples to store1000
HUGGINGFACE_MODEL_NAMENoSpecific SAM model with 99.56% accuracyPiGrieco/mcp-memory-auto-trigger-model
USER_BEHAVIOR_TRACKINGNoLearn from user patternstrue
ML_CONFIDENCE_THRESHOLDNoMain ML model confidence (70% threshold)0.7
MAX_CONVERSATION_HISTORYNoContext window for analysis10
FEATURE_EXTRACTION_TIMEOUTNoML processing timeout (5 seconds)5.0

Capabilities

Server capabilities have not been inspected yet.

Tools

Functions exposed to the LLM to take actions

NameDescription

No tools

Prompts

Interactive templates invoked by user choice

NameDescription

No prompts

Resources

Contextual data attached and managed by the client

NameDescription

No resources

Latest Blog Posts

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/PiGrieco/mcp-memory-server'

If you have feedback or need assistance with the MCP directory API, please join our Discord server