If you're an AI reading this: skill.md has everything you need.Read it →

Explorer/MCP/expandingideas-ai/Mnemo-MCP

HYBRID

Mnemo MCP

expandingideas-ai/Mnemo-MCP

Persistent AI memory server with hybrid search and embedded sync. Enables AI agents to store, retrieve, and manage information across sessions with temporal knowledge graph support.

↗expandingideas-ai/Mnemo-MCPExternal link; availability not verifiedLicenseMIT LicenseOfficial publisherHybrid hosting

The Newcomer

Hasn't been around long. Nothing caught our attention, but there isn't much history to go on yet.

Time indexed (3mo)

0toolsHybrid3moindexed

Checked Jun 24, 2026

The scanner shows

Not enough data to score this server yet.

First indexed Jun 24, 2026

Server Profile

⚙

Tools catalogued

0

No tools reported by this server.

☁

Hosting

Hybrid

Can run locally or remotely depending on deployment. Review the source repository.

○

Registry presence

Not verified

Not yet verified by the Official MCP Registry.

●

Liveness

—

No liveness checks recorded yet.

Publisher Verification

Not listed on the Official MCP Registry.

Source repository is available for review.

↗expandingideas-ai/Mnemo-MCPExternal link; availability not verified

Environment variables (29)

DB_PATHstringOPTIONALdefault: ~/.mnemo-mcp/memories.db

SQLite database path

LOG_LEVELstringOPTIONALdefault: INFO

Log verbosity

LLM_MODELSstringOPTIONALdefault:

LLM chain for graph extraction / importance / compression; empty disables those features

PUBLIC_URLstringOPTIONAL

Public URL for HTTP multi-user remote mode

SYNC_FOLDERstringOPTIONALdefault: mnemo-mcp

Google Drive folder name

Show all 29 environment variables

LLM_API_BASEstringOPTIONAL

Custom OpenAI-compatible endpoint for LLM (SSRF-guarded)

RERANK_TOP_NstringOPTIONALdefault: 10

Number of reranked results to keep

SYNC_ENABLEDstringOPTIONALdefault: true

Enable Google Drive multi-machine sync

MCP_TRANSPORTstringOPTIONALdefault: stdio

Transport mode (stdio or http)

MNEMO_DB_PATHstringOPTIONAL

Alias for DB_PATH

RERANK_MODELSstringOPTIONALdefault:

Rerank chain, e.g. jina_ai/jina-reranker-v3,cohere/rerank-v3.5

SYNC_INTERVALstringOPTIONALdefault: 300

Auto-sync interval in seconds (0 = manual only)

COHERE_API_KEYstringOPTIONAL

API key for Cohere models (cohere/ prefix)

EMBEDDING_DIMSstringOPTIONALdefault: 768

Embedding dimensions (0 = auto-detect)

GEMINI_API_KEYstringOPTIONAL

API key for Gemini models (gemini/ prefix)

OPENAI_API_KEYstringOPTIONAL

API key for OpenAI models (openai/ or bare)

RERANK_ENABLEDstringOPTIONALdefault: true

Enable reranking of fused results

ARCHIVE_ENABLEDstringOPTIONALdefault: true

Enable importance x recency soft-archive sweeps

DEDUP_THRESHOLDstringOPTIONALdefault: 0.9

Similarity above which a new memory is a duplicate

JINA_AI_API_KEYstringOPTIONAL

API key for Jina AI models (jina_ai/ prefix)

KG_AUTO_ENABLEDstringOPTIONALdefault: false

Auto-extract entities + relations on capture

RERANK_API_BASEstringOPTIONAL

Custom OpenAI-compatible endpoint for reranking (SSRF-guarded)

EMBEDDING_MODELSstringOPTIONALdefault:

Embedding chain, e.g. jina_ai/jina-embeddings-v5-text-small,gemini/gemini-embedding-001

ARCHIVE_AFTER_DAYSstringOPTIONALdefault: 90

Age before a memory is eligible for archive

EMBEDDING_API_BASEstringOPTIONAL

Custom OpenAI-compatible endpoint for embedding (SSRF-guarded)

CAPTURE_AUTO_ENABLEDstringOPTIONALdefault: false

Opt-in PostToolUse hook to hint memory-commit after writing to specific files

GOOGLE_DRIVE_CLIENT_IDstringOPTIONAL

OAuth client ID required for sync

RECENCY_HALF_LIFE_DAYSstringOPTIONALdefault: 7

Half-life for temporal decay scoring

REINDEX_ON_MODEL_CHANGEstringOPTIONALdefault: false

Re-embed on model change (safe-by-default guard blocks boot on mismatch)

Is this your server?

Create a free RNWY account to connect your on-chain identity to this server. MCP server claiming is coming; register now and you'll be first in line.

Create your account →