D
Caution
52/100
15 days ago

foundation

MCP server for a personal long-term memory base, providing 140 tools to search and write via PostgreSQL and Qdrant, with integrations for Obsidian, session histories, meetings, tasks, and smart home.

Caution. Specific findings reduced this grade. They are listed on the page. Grades reflect the full trust pyramid: code, verification depth, and reputation. New projects cap at C until adoption is earned.

How we verified

Code 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

nekoPhysics

Source: Glama

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

M8ven verifies MCPs across every public registry — install directly from whichever one you prefer.

// key findings
No credential exfiltration, no sensitive file access, no obfuscation
Static analysis found nothing flowing your secrets to unexpected places.
🔐
You'll be asked for 4 credentials: DB_PASSWORD, DISCORD_BOT_TOKEN, HF_TOKEN, SCAN_RECEIVER_TOKEN
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.
configOBSIDIAN_RAG_BASE_URL
configFOUNDATION_ALLOWED_EMAILSOAuth (streamable-http モード) の許可メールアドレス一覧 必須 (http モード時)
configGPU_SCHEDULER_URLgpu-scheduler の HTTP エンドポイント http://gpu-scheduler:9400
configRRF_SEMANTIC_W
configRRF_KEYWORD_W
configRRF_KEYWORD_RESCUE
configFOUNDATION_RERANK_RANK1_GUARD
configFOUNDATION_RERANK_GUARD_FLOOR
configRRF_KEYWORD_RESERVE
configFOUNDATION_DELIVER_DEVICE
configMEETING_SERVER_URL
configFOUNDATION_DIR
configFOUNDATION_MCP_PORT
configMORNING_DIGEST_RULES
configFOUNDATION_ATTACHMENTS_HOST
configFOUNDATION_ATTACHMENTS_PORT
configLOG_LEVELログレベル INFO
configGPU_SCHEDULER_PORT
configCUDA_DEVICE
configQDRANT_HOST/ QDRANT_PORT Qdrant 接続先 localhost / 6333
configQDRANT_PORTQDRANT_HOST / Qdrant 接続先 localhost / 6333
configOLLAMA_URLローカル LLM (Ollama) エンドポイント http://localhost:11434
configLLAMA_SERVER_DEFER_PRIORITY_MIN
configLLAMA_SERVER_USER_ACTIVE_CACHE_TTL_SEC
configVRAM_KEEP_ALIVE_EMBED_QUERY_S
configEMBED_BATCH_CHUNK_SIZE
configWHISPER_INITIAL_PROMPT
configGPU_TASK_TIMEOUT_DEFAULT
configGPU_TASK_TIMEOUT_LONG
configLLAMA_SERVER_IDLE_SEC
configLLAMA_SERVER_IDLE_POLL_SEC
configMEETING_APP_PORT
configDB_HOST
configDB_PORT
configDB_NAME
configDB_USER
🔐 secretDB_PASSWORD
configFOUNDATION_ATTACHMENTS_FETCH_MAX_BYTES
configOPENAI_COMPAT_URL外部 OpenAI 互換エンドポイント (既定 0.0.0.0:8317、 で変更可) を
configRESEARCH_MODEL
🔐 secretDISCORD_BOT_TOKEN
configCHAT_MODEL
configCHAT_PROXY_URL
configCHAT_BOT_NAME
configCHAT_HISTORY_LIMIT
configDISCORD_CHAT_CHANNEL_ID
configGPU_SCHEDULER_OWNS_EMBEDDER埋め込みモデルの直接ロードを gpu-scheduler だけに限定するガード gpu-scheduler コンテナのみ 1
configCREDENTIALS_DIRECTORY
configLLM_LOG_ENABLED
configLLM_LOG_FILE
configLLM_LOG_VERBOSE
configLLAMA_SERVER_START_TIMEOUT_SEC
configFOUNDATION_CONFIG_YAML
configMEETING_V2_CHUNK_SIZE_CHARS
configMEETING_V2_CHUNK_OVERLAP_CHARS
configMEETING_V2_CHUNK_THRESHOLD_CHARS
configMEETING_V2_DEDUP
configMEETING_V2_DEDUP_THRESHOLD
configMEETING_V2_CRITIQUE
configMEETING_V2_AUTO_RETRY_THRESHOLD
config_MEETING_V2_RETRY_INFLIGHT
configMEETING_CRITIQUE_MODEL
configMEETING_CRITIQUE_EFFORT
configMEETING_EXTRACT_V2
configWHISPER_MODEL
configWHISPER_LANGUAGE
configWHISPER_NUM_BEAMS
configWHISPER_VAD_SEGMENT
configWHISPER_VAD_THRESHOLD
configWHISPER_VAD_MIN_SILENCE_MS
configWHISPER_VAD_SPEECH_PAD_MS
configWHISPER_VAD_MAX_SPEECH_S
🔐 secretHF_TOKENHuggingFace の認証トークン (ゲート付きモデル利用時) 任意
configLLM_CONFIG
configMEETING_SPEAKER_LLM_INFER
configVAULT_OUTPUT_DIRコンテナ内での Vault 出力先マウントポイント /output
configOCR_MAX_FILES
configRERANK_OOM_RETRIES
configRERANK_OOM_RETRY_WAIT_S
configRERANK_MAX_PASSAGE_CHARS
configRERANK_BATCH_SIZE
configSCAN_RECEIVER_HOST
configSCAN_RECEIVER_PORT
configSCAN_RECEIVER_DATA
configXDG_RUNTIME_DIR
🔐 secretSCAN_RECEIVER_TOKEN
configINGEST_LLM_PRIORITY
configXDG_STATE_HOME
configMORNING_DIGEST_ALWAYS_SAVE
configFOUNDATION_ORCH_MAX_CONCURRENT
configFOUNDATION_ORCH_CWD_ROOTS
configFOUNDATION_ORCH_TMUX_SESSION
configMORNING_DIGEST_FACTS_DATE
Deployment configuration, supplied by whoever hosts the server. Users are not asked for these.
deployDATABASE_URL
// quality suggestions

Tool annotations

No tools have read-only/destructive annotations

Add readOnlyHint or destructiveHint annotations to every tool so hosts can warn users before invoking.

All four hints declared on every tool

141/141 tools missing one or more hints — semantic_search (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint); keyword_search (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint); hybrid_search (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint), +138 more. OpenAI's directory rejects tools where any of the four hints are missing or non-boolean.

For every tool, set all four hints (readOnlyHint, destructiveHint, idempotentHint, openWorldHint) to explicit true/false values that match the handler’s actual behaviour.

Destructive tools are labelled

3 tools perform destructive updates without destructiveHint — vault_upload_pdf deletes at line 4076 (saved.unlink(missing_ok=True)); vault_edit deletes at line 4551 (os.unlink(tmp_path)); vault_clean deletes at line 4635 (fpath.unlink())

Add destructiveHint:true to any tool whose handler calls .delete(), .upsert(), .update(), unlink, rm, DELETE, DROP, REPLACE INTO, or any operation that overwrites existing data.

Tool inputs are validated

124/140 tool handlers declare input schemas (89%)

Declare an inputSchema with zod/joi/yup on every tool definition.

Tool handlers catch errors

92/140 tool handlers wrap calls in try/catch (66%)

Wrap each tool handler body in try/catch and return a structured error response.

License file

No license file

Add a LICENSE file (MIT, Apache-2.0, etc.).

Tests exist

No test files found

Add tests that exercise each declared tool.

Shell command execution

3 child_process calls — runs shell commands

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 8 concrete improvements we can share with the publisher of this MCP. Each comes with specific guidance to raise the trust score.
// embed badge in your README
[![M8ven Verified](https://m8ven.ai/badge/mcp/nekophysics-foundation-core-lch12b?variant=verified)](https://m8ven.ai/mcp/nekophysics-foundation-core-lch12b)
Shows verification status without the grade. Want the grade badge instead? Remove ?variant=verified from the URL.
commit: 23b336ac154ad739a40eff6c94db37248a040f7b
code hash: 0f4c15ae41cde6c86b373ef5dd9f5c18c8091fe1d97e877b0862f4ca7fa90669
verified: 8/6/2026, 8:57:21 AM
view raw JSON →
Check MCPs from inside your assistant
Tool Check · MCP

Vetting 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-check
check_toolsearch_toolscompare_toolsrecommend_alternativescheck_publisherreport_concern
How to add it →Free · no account needed · works in any MCP client