Skip to main content
Glama

Server Configuration

Describes the environment variables required to run the server.

NameRequiredDescriptionDefault
DB_PATHNoSQLite database path~/.mnemo-mcp/memories.db
LOG_LEVELNoLog verbosityINFO
LLM_MODELSNoLLM chain for graph extraction / importance / compression; empty disables those features
PUBLIC_URLNoPublic URL for HTTP multi-user remote mode
SYNC_FOLDERNoGoogle Drive folder namemnemo-mcp
LLM_API_BASENoCustom OpenAI-compatible endpoint for LLM (SSRF-guarded)
RERANK_TOP_NNoNumber of reranked results to keep10
SYNC_ENABLEDNoEnable Google Drive multi-machine synctrue
MCP_TRANSPORTNoTransport mode (stdio or http)stdio
MNEMO_DB_PATHNoAlias for DB_PATH
RERANK_MODELSNoRerank chain, e.g. jina_ai/jina-reranker-v3,cohere/rerank-v3.5
SYNC_INTERVALNoAuto-sync interval in seconds (0 = manual only)300
COHERE_API_KEYNoAPI key for Cohere models (cohere/ prefix)
EMBEDDING_DIMSNoEmbedding dimensions (0 = auto-detect)768
GEMINI_API_KEYNoAPI key for Gemini models (gemini/ prefix)
OPENAI_API_KEYNoAPI key for OpenAI models (openai/ or bare)
RERANK_ENABLEDNoEnable reranking of fused resultstrue
ARCHIVE_ENABLEDNoEnable importance x recency soft-archive sweepstrue
DEDUP_THRESHOLDNoSimilarity above which a new memory is a duplicate0.9
JINA_AI_API_KEYNoAPI key for Jina AI models (jina_ai/ prefix)
KG_AUTO_ENABLEDNoAuto-extract entities + relations on capturefalse
RERANK_API_BASENoCustom OpenAI-compatible endpoint for reranking (SSRF-guarded)
EMBEDDING_MODELSNoEmbedding chain, e.g. jina_ai/jina-embeddings-v5-text-small,gemini/gemini-embedding-001
ARCHIVE_AFTER_DAYSNoAge before a memory is eligible for archive90
EMBEDDING_API_BASENoCustom OpenAI-compatible endpoint for embedding (SSRF-guarded)
CAPTURE_AUTO_ENABLEDNoOpt-in PostToolUse hook to hint memory-commit after writing to specific filesfalse
GOOGLE_DRIVE_CLIENT_IDNoOAuth client ID required for sync
RECENCY_HALF_LIFE_DAYSNoHalf-life for temporal decay scoring7
REINDEX_ON_MODEL_CHANGENoRe-embed on model change (safe-by-default guard blocks boot on mismatch)false

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/expandingideas-ai/Mnemo-MCP'

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