Skip to main content
Glama
gregpriday

Memory MCP Server

by gregpriday

Server Configuration

Describes the environment variables required to run the server.

NameRequiredDescriptionDefault
OPENAI_API_KEYYesOpenAI API key for embeddings and LLM orchestration
MEMORY_LOG_LEVELNoLog level: debug, info, warn, error (default: info)
MEMORY_DEBUG_MODENoDebug flags (true/false)
MEMORY_LOG_FORMATNoLog format: json, pretty (default: pretty)
MEMORY_ACTIVE_PROJECTYesActive project identifier
MEMORY_EMBEDDING_MODELYesEmbedding model (determines vector dimensions). Default: text-embedding-3-smalltext-embedding-3-small
MEMORY_DB_SLOW_QUERY_MSNoSlow query threshold in milliseconds (default: 200)
MEMORY_DEBUG_OPERATIONSNoDebug operations (true/false)
MEMORY_DEBUG_REPOSITORYNoDebug repository (true/false)
MEMORY_DEBUG_VALIDATIONNoDebug validation (true/false)
MEMORY_CHUNK_CHAR_LENGTHNoChunk character length (default: 16000)
MEMORY_CHUNK_CHAR_OVERLAPNoChunk character overlap (default: 2000)
MEMORY_MCP_SYSTEM_MESSAGENoHost/system context (inline text or file path)
MEMORY_MAX_CHUNKS_PER_FILENoMax chunks per file (default: 24)
MEMORY_REFINE_ALLOW_DELETENoAllow delete in refinement (true/false)
MEMORY_EMBEDDING_DIMENSIONSNoEmbedding dimensions (auto-detected from model, manual override available)
MEMORY_ACCESS_PRIORITY_BOOSTNoAccess priority boost (default: 0.01)
MEMORY_ACCESS_TRACKING_TOP_NNoAccess tracking top N (default: 3)
MEMORY_DEBUG_ACCESS_TRACKINGNoDebug access tracking (true/false)
MEMORY_MAX_MEMORIES_PER_FILENoMax memories per file (default: 50)
MEMORY_QUERY_EXPANSION_COUNTNoQuery expansion count (default: 2)
MEMORY_REFINE_DEFAULT_BUDGETNoDefault refinement budget (default: 100)
MEMORY_ACCESS_TRACKING_ENABLEDNoAccess tracking enabled (true/false)
MEMORY_QUERY_EXPANSION_ENABLEDNoQuery expansion enabled (true/false)
MEMORY_POSTGRES_PROJECT_REGISTRYYesPath to the project registry JSON file
MEMORY_LARGE_FILE_THRESHOLD_BYTESNoLarge file threshold bytes (default: 262144)

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/gregpriday/memory-mcp-legacy'

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