B
Emerging
89/100
mnemosyne
Zero-cloud AI memory that works everywhere. SQLite-backed. One pure-Python dependency.
Emerging. No concerning findings. Grades remain capped until the project builds reputation through adoption. Grades reflect the full trust pyramid: code, verification depth, and reputation. New projects cap at C until adoption is earned.
How we verified
⚡ Live Monitored: not connected
Verified is a snapshot. Live keeps it current, and builds your track record.
⚡ Connect GitHub → continuous verification on every pushwhy connect →Who stands behind it
mnemosyne-oss
Source: github_code
Is this your MCP?
Claim it to get a verified publisher badge, a free copy of our full audit findings, and direct contact for any high-priority issues we find. Or connect your repo for our deepest verification, Live Monitored: read-only, revoke anytime. What we access →
Install from
The grade above is for the source repository. Registries can serve a different version, so we mark the ones we were not able to read.
// key findings
🚨
Secret credentials may flow to a network call
7 flows detected: MNEMOSYNE_EMBEDDING_API_KEY, MNEMOSYNE_CONFLICT_LLM_API_KEY, MNEMOSYNE_LLM_API_KEY. We can’t prove the destination matches the brand the credential belongs to.
🔐
You'll be asked for 9 credentials: OPENROUTER_API_KEY, NVIDIA_API_KEY, MNEMOSYNE_SYNC_KEY, MNEMOSYNE_EMBEDDING_API_KEY, OPENAI_API_KEY, MNEMOSYNE_LLM_API_KEY, MNEMOSYNE_CONFLICT_LLM_API_KEY, MNEMOSYNE_LLM_FALLBACK_API_KEY, OPENWEBUI_API_KEY
These are read from process.env at runtime. Make sure you trust where they’ll be sent.
// environment variables
To run this server yourself, you supply these values. They go in your own MCP client configuration and stay on your machine. The secret label means the value is sensitive, not that the server mishandles it.
config
HERMES_HOMEconfig
MNEMOSYNE_HOMEconfig
MNEMOSYNE_SHARED_DB_PATHconfig
MNEMOSYNE_AUTHOR_IDconfig
MNEMOSYNE_AUTHOR_TYPEconfig
MNEMOSYNE_CHANNEL_IDconfig
MNEMOSYNE_MCP_BANKconfig
MNEMOSYNE_DEFAULT_SCOPEconfig
MNEMOSYNE_DEFAULT_OWNERconfig
MNEMOSYNE_LLM_N_CTXconfig
MNEMOSYNE_DATA_DIRDatabase directoryconfig
MNEMOSYNE_HOST_LLM_ENABLED🔐 secret
OPENROUTER_API_KEYPreferred name for embedding API key. Falls back to OPENROUTER_API_KEY, then OPENAI_API_KEY.🔐 secret
NVIDIA_API_KEYconfig
OPENROUTER_BASE_URLPreferred name for custom embedding API endpoint (OpenAI-compatible). Falls back to OPENROUTER_BASE_URL.config
MNEMOSYNE_BENCHMARK_PURE_RECALLconfig
FULL_CONTEXT_MODEconfig
MNEMOSYNE_PREFETCH_CONTENT_CHARSconfig
MNEMOSYNE_SYNC_TURN_USER_LIMITconfig
MNEMOSYNE_SYNC_TURN_ASSISTANT_LIMITconfig
MNEMOSYNE_SYNC_ROLESconfig
MNEMOSYNE_SKIP_CONTEXTSconfig
MNEMOSYNE_PREFETCH_PROFILEconfig
MNEMOSYNE_PREFETCH_MODEL_SLOT_LIMITconfig
MNEMOSYNE_PREFETCH_MODEL_SLOT_MIN_OVERLAPconfig
MNEMOSYNE_RECALL_DIAGNOSTICSconfig
MNEMOSYNE_SYNC_HOSTconfig
MNEMOSYNE_SYNC_PORT🔐 secret
MNEMOSYNE_SYNC_KEYconfig
MNEMOSYNE_BANKconfig
MNEMOSYNE_EMBEDDING_MODELEmbedding model. Low-resource multilingual: sentence-transformers/paraphrase-multilingual-MiniLM-L12-v2; larger FastEmbed E5 option: intfloat/multilingual-e5-large; BAAI/bge-m3 is another multilingual option.config
MNEMOSYNE_Xconfig
MNEMOSYNE_HEAL_JUDGE_THRESHOLDconfig
MNEMOSYNE_HEAL_MAX_RETRIESconfig
MNEMOSYNE_HEAL_MIN_LENconfig
MNEMOSYNE_HEAL_BUDGETconfig
MNEMOSYNE_HEAL_ESCALATE_AFTERconfig
MNEMOSYNE_HEAL_JUDGE_MODELconfig
MNEMOSYNE_DB_PATHconfig
MNEMOSYNE_WM_MAX_ITEMSWorking memory limitconfig
MNEMOSYNE_WM_TTL_HOURSconfig
MNEMOSYNE_WM_BUMP_CAP_HOURSconfig
MNEMOSYNE_WM_PINNED_IDSconfig
MNEMOSYNE_EP_LIMITconfig
MNEMOSYNE_SLEEP_BATCHconfig
MNEMOSYNE_SP_MAXconfig
MNEMOSYNE_RECENCY_HALFLIFEDecay halflife in hoursconfig
MNEMOSYNE_TIER2_DAYSconfig
MNEMOSYNE_TIER3_DAYSconfig
MNEMOSYNE_TIER1_WEIGHTconfig
MNEMOSYNE_TIER2_WEIGHTconfig
MNEMOSYNE_TIER3_WEIGHTconfig
MNEMOSYNE_SMART_COMPRESSconfig
MNEMOSYNE_TIER3_MAX_CHARSconfig
MNEMOSYNE_STATED_WEIGHTconfig
MNEMOSYNE_VEC_TYPEVector compression: float32, int8, or bitconfig
MNEMOSYNE_BUSY_TIMEOUT_MSconfig
MNEMOSYNE_VEC_WEIGHTVector similarity weightconfig
MNEMOSYNE_FTS_WEIGHTFTS5 keyword weightconfig
MNEMOSYNE_IMPORTANCE_WEIGHTImportance weightconfig
MNEMOSYNE_TEMPORAL_HALFLIFE_HOURSconfig
MNEMOSYNE_RECALL_EXTRA_STOPWORDSconfig
MNEMOSYNE_LEXICAL_GATE_MINconfig
MNEMOSYNE_AUTO_MIGRATEconfig
MNEMOSYNE_PROACTIVE_LINKINGconfig
MNEMOSYNE_POLYPHONIC_RECALLconfig
MNEMOSYNE_QUERY_INTENTconfig
MNEMOSYNE_FACT_RECALL_ENABLEDconfig
MNEMOSYNE_EMBEDDING_QUERY_PREFIXconfig
MNEMOSYNE_ENHANCED_RECALLconfig
MNEMOSYNE_BLOB_DIR🔐 secret
MNEMOSYNE_EMBEDDING_API_KEYPreferred name for embedding API key. Falls back to OPENROUTER_API_KEY, then OPENAI_API_KEY.🔐 secret
OPENAI_API_KEYPreferred name for embedding API key. Falls back to OPENROUTER_API_KEY, then OPENAI_API_KEY.config
MNEMOSYNE_EMBEDDING_API_URLPreferred name for custom embedding API endpoint (OpenAI-compatible). Falls back to OPENROUTER_BASE_URL.config
MNEMOSYNE_EMBEDDING_DOC_PREFIXconfig
MNEMOSYNE_NO_EMBEDDINGSconfig
MNEMOSYNE_SKIP_EMBEDDINGSconfig
MNEMOSYNE_EMBEDDINGS_OFFconfig
MNEMOSYNE_EMBEDDINGS_VIA_APIconfig
MNEMOSYNE_EMBEDDING_DIMOptional embedding dimension override (positive integer); takes precedence over the built-in model table. Blank/whitespace-only is treated as unset.config
MNEMOSYNE_EMBEDDING_THREADSconfig
SSL_CERT_FILEHTTPS in production; point SSL_CERT_FILE at a private CA for self-signed dev certs.config
REQUESTS_CA_BUNDLEconfig
MNEMOSYNE_IGNORE_PATTERNSconfig
MNEMOSYNE_WRITE_CLASSIFIERconfig
MNEMOSYNE_JOURNAL_MODESQLite journal mode for store connections (memory, beam, query cache, veracity consolidator; the sync client rides the beam connection). Valid: delete, truncate, persist, memory, wal, off; the value is trimmed and lower-cased, unset or blank falls back to wal, and non-blank invalid values warn and fall back to wal. Set delete on filesystems where WAL corrupts reads (Linux containers on macOS virtiofs). Only wal persists in the database file; every other mode is per-connection and reverts to SQLite's default (delete) on reopen, so each connection re-applies the mode itself. memory and off remove disk-backed rollback protection and can corrupt the database after a crash.config
MNEMOSYNE_LLM_CONFLICT_DETECTIONconfig
MNEMOSYNE_LLM_BASE_URL🔐 secret
MNEMOSYNE_LLM_API_KEYconfig
MNEMOSYNE_LLM_MODELconfig
MNEMOSYNE_CONFLICT_LLM_BASE_URL🔐 secret
MNEMOSYNE_CONFLICT_LLM_API_KEYconfig
MNEMOSYNE_CONFLICT_LLM_MODELconfig
MNEMOSYNE_LLM_ENABLEDconfig
MNEMOSYNE_LLM_MAX_TOKENSconfig
MNEMOSYNE_LLM_N_THREADSconfig
MNEMOSYNE_LLM_REPOconfig
MNEMOSYNE_LLM_FILEconfig
MNEMOSYNE_MODEL_CACHE_DIRconfig
MNEMOSYNE_LLM_PROVIDERconfig
MNEMOSYNE_LLM_REGIONconfig
MNEMOSYNE_LLM_TIMEOUTconfig
MNEMOSYNE_LLM_FALLBACK_MODELSconfig
MNEMOSYNE_LLM_FALLBACK_BASE_URL🔐 secret
MNEMOSYNE_LLM_FALLBACK_API_KEYconfig
MNEMOSYNE_HOST_LLM_PROVIDERconfig
MNEMOSYNE_HOST_LLM_MODELconfig
MNEMOSYNE_HOST_LLM_TIMEOUTconfig
MNEMOSYNE_HOST_LLM_N_CTXconfig
MNEMOSYNE_SLEEP_PROMPTconfig
MNEMOSYNE_FORCE_LOCALconfig
MNEMOSYNE_MODALITY_PROMPTconfig
MNEMOSYNE_SLEEP_MODEL_REFRESH_CATEGORIESconfig
MNEMOSYNE_SLEEP_MODEL_REFRESH_MAX_TOKENSconfig
MNEMOSYNE_SLEEP_MODEL_REFRESH_TEMPERATUREconfig
MNEMOSYNE_SLEEP_MODEL_REFRESH_AUTO_APPLY_MIN_CONFIDENCEconfig
MNEMOSYNE_SLEEP_MODEL_REFRESH_MIN_EVIDENCEconfig
MNEMOSYNE_SLEEP_MODEL_REFRESH_CONFLICT_MIN_CONFIDENCEconfig
MNEMOSYNE_SLEEP_MODEL_REFRESH_CONFLICT_MIN_EVIDENCEconfig
MNEMOSYNE_PERSONA_INTERVALconfig
MNEMOSYNE_PERSONA_DAILY_SYNC_HOURconfig
MNEMOSYNE_PERSONA_TOKEN_CAPconfig
MNEMOSYNE_USE_CAVEMANconfig
MNEMOSYNE_BEAM_MODEconfig
MNEMOSYNE_SHMR_BATCH_SIZEconfig
MNEMOSYNE_SHMR_MAX_ITERATIONSconfig
MNEMOSYNE_SHMR_SIMILARITY_THRESHOLDconfig
MNEMOSYNE_SHMR_HARMONY_THRESHOLDconfig
MNEMOSYNE_SHMR_MODELconfig
MNEMOSYNE_SHMR_MIN_CLUSTER_SIZEconfig
MNEMOSYNE_SHMR_TEMPERATUREconfig
MNEMOSYNE_SELF_ECHO_ENABLEDconfig
MNEMOSYNE_BACKUP_DIRconfig
OPENWEBUI_URL🔐 secret
OPENWEBUI_API_KEYconfig
AUTO_SAVE_BANKconfig
AUTO_SAVE_INTERVALconfig
VIRTUAL_ENV// quality suggestions
Shell command execution
4 calls in production code run through a shell (integrations/obsidian-mnemosyne/main.ts:180, integrations/obsidian-mnemosyne/main.ts:200, integrations/vscode-mnemosyne/src/client.ts:29)
Prefer library functions over shell-outs. If you must shell out, ensure all inputs are properly escaped.
Claim the listing to review these findings one by one and send us a correction where you disagree, straight to the team. Claiming also means we tell you when the grade moves, and reach you first if we find anything urgent.
// full audit trail
The findings above are the summary. The full trail, every check we ran, each deduction, the network hosts observed and the dependency advisories, goes to verified publishers, along with an alert whenever a new one lands. Verified publishers can also review each finding and dispute it in one click. Publisher corrections have sharpened several of our checks this month, because the maintainer knows the codebase better than any scanner.
// improvement guidance — verified publishers only
We have 1 concrete improvement we can share with the publisher of this MCP. Each comes with specific guidance to raise the trust score.
// embed badge in your README
[](https://m8ven.ai/mcp/mnemosyne-oss/mnemosyne)Shows your grade and updates automatically. Prefer no grade? Append
?variant=verified to the badge URL.commit: 14ef54ea7e13e16589a3122c5a827bb39a93e42e
code hash: 15bcf8de299747601d0555868bd0d849e0a876110b0b0c6a9b9f42f0e78e132c
Check MCPs from inside your assistant
Tool Check · MCPVetting this one by hand? Tool Check is an MCP that scores other MCPs. Add it once and ask Claude, ChatGPT, or any MCP client to grade a server, surface CVEs, check the publisher, and suggest safer alternatives — before you install.
https://m8ven.ai/api/mcp/tool-checkcheck_toolsearch_toolscompare_toolsrecommend_alternativescheck_publisherreport_concern
How to add it →Free · no account needed · works in any MCP client