nutri (vryahn/nutri) is an MCP server listed on the M8ven Trust Index. It scores 74 out of 100, grade C. It declares 11 tools. No publisher has claimed this listing.

Caution

74/100

nutri

Item: nutri
Rating: 74
Author: M8ven

Production nutrition-tracking PWA (React, Supabase) built and operated inside Claude Code: production RAG pipeline, hybrid semantic search (pgvector), self-built remote MCP server (OAuth 2.1 + PKCE, RLS-enforced), three-model AI fallback chain, and an LLM eval harness gating every release.

→ vryahn/nutri · listed on github_repo_search

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 push why connect →

Who stands behind it

vryahn

Source: github_repo_search

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 →

⚡ Connect GitHub for Live Monitored

Install from

GitHub

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

✅

11 tools verified — handlers match their declared behaviour

4 read-only tools verified — handlers contain no write/delete/exec

✅

No credential exfiltration, no sensitive file access, no obfuscation

Static analysis found nothing flowing your secrets to unexpected places.

🔐

You'll be asked for 9 credentials: FDC_KEY, GEMINI_KEY, GROQ_KEY, MISTRAL_KEY, VITE_FDC_KEY, VITE_GEMINI_KEY, VITE_GROQ_KEY, VITE_MISTRAL_KEY, VITE_SUPABASE_ANON_KEY

These are read from process.env at runtime. Make sure you trust where they’ll be sent.

// tools this server exposes11 tools

These names and descriptions are the publisher's own, read from the source code. We print them as written. Our assessment is the findings above, not this list.

search_catalog

Busca alimentos y recetas por nombre/marca (ilike). Valores por 100 g. is_mine indica si el ítem es propio (owner del food/receta); el catálogo base compartido (owner NULL) aparece con is_mine:false.

log_entry

Registra un consumo (cantidad SIEMPRE en gramos; el agua se registra con el food "Agua", grams = ml). Preferir food_id/recipe_id (de search_catalog); item (nombre) es fallback y puede enganchar un homónimo.

delete_entry

Borra un registro de consumo por id (RLS limita a los propios).

get_day

Totales del día (daily_totals) + registros individuales (entry_nutrients), con etiqueta y nombre. Default hoy.

get_targets

Objetivo resuelto para una fecha (día específico si existe, si no la fase dow vigente), con label/goal de la fase y `bounds` ({clave:{min,max}} explícitos por nutriente; vacío = arquetipo por defecto). Default hoy.

set_target_bounds

Fija límites explícitos mín/máx por nutriente en el objetivo que aplica a una fecha: su día específico si existe, si no TODA la fase vigente/programada (las fases pasadas se rechazan). Patch por clave: {min,max} reemplaza el bound de ese nutriente, null lo quita, las claves no enviadas se conservan;…

create_food

Crea un alimento en tu catálogo, TODO por 100 g. Guarda bajo responsabilidad del usuario; los avisos ⚠ (kcal vs macros, valores implausibles, componentes inconsistentes) se muestran también en la app y NO bloquean el guardado. Las claves de micros inválidas SÍ bloquean (error).

create_recipe

Crea una receta a partir de ingredientes existentes en el catálogo (food_id + gramos). cooked_weight_g es el peso final tras cocinar; si se omite o es 0 se usa la suma de gramos de los ingredientes. Devuelve los valores por 100 g calculados.

update_food

Edita un food. Si es propio, actualiza en sitio (portions-only no cambia la fuente; cualquier otro campo marca source:"ia_personal" y limpia reviewed_at). Si es del catálogo base o de otro dueño (no editable), crea tu propia copia (forked:true) sin tocar el original. Prohibido: borrar foods o editar…

log_measurement

Guarda mediciones corporales (bioimpedancia, circunferencias) del día en la tab Medidas. Claves EXACTAS de BODY_METRICS en domain.js (peso_kg, grasa_pct, musculo_kg, agua_pct, grasa_visceral, metabolismo_basal_kcal, …); claves libres se rechazan. Merge con lo ya guardado ese día: solo pisa las clave…

get_measurements

Mediciones corporales por rango de fechas (ambos extremos opcionales), orden descendente por día.

// known CVEs in dependencies1 low

Disclosed vulnerabilities in this server's declared npm dependencies (via OSV). Whether each is reachable depends on the installed versions.

lowvitest@4.1.10GHSA-82fw-gwwq-j7x9

Vitest: Path Traversal / Arbitrary File Read via @vitest/mocker Redirect Mock

Depend on this server? Get alerted when its CVEs change.Watch this server free →

// 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.

configEVAL_MODEL

🔐 secretFDC_KEYenables USDA FoodData Central match chips ([free key](https://fdc.nal.usda.gov/api-key-signup)); in production it stays server-side behind /api/ai, in dev the VITE_ one calls FDC directly

🔐 secretGEMINI_KEY

🔐 secretGROQ_KEY

🔐 secretMISTRAL_KEY

🔐 secretVITE_FDC_KEYenables USDA FoodData Central match chips ([free key](https://fdc.nal.usda.gov/api-key-signup)); in production it stays server-side behind /api/ai, in dev the VITE_ one calls FDC directly

🔐 secretVITE_GEMINI_KEYenables "Datos con IA", semantic search, and "ask your log" ([Google AI Studio](https://aistudio.google.com/apikey) free tier, no billing); without it those modules are hidden

🔐 secretVITE_GROQ_KEY

🔐 secretVITE_MISTRAL_KEYenables the Mistral tail of the AI fallback cascade; skipped if absent

🔐 secretVITE_SUPABASE_ANON_KEYanon/publishable key

configVITE_SUPABASE_URLSupabase project URL

Deployment configuration, supplied by whoever hosts the server. Users are not asked for these.

deployPORT

// quality suggestions

All four hints declared on every tool

10/11 tools missing one or more hints — search_catalog (missing: destructiveHint, idempotentHint); log_entry (missing: idempotentHint); get_day (missing: destructiveHint, idempotentHint), +7 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

4 tools perform destructive updates without destructiveHint — set_target_bounds overwrites at line 188 (supabase.from('targets').update({ bounds: merged })); create_recipe deletes at line 273 (supabase.from('recipes').delete()); update_food overwrites at line 321 (supabase.from('foods').update(updatePayload))

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.

License file

No license file

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

Tool test coverage

Only 1/11 tools referenced in tests (9%)

Write tests that reference each tool by name so every tool has at least one test.

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 4 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/vryahn/nutri?variant=verified)](https://m8ven.ai/mcp/vryahn/nutri)

Shows verification status without the grade. Want the grade badge instead? Remove ?variant=verified from the URL.

commit: 00c7262ec4cee355cdeda2e062105f40616556ad

code hash: 8f96e7ee88cb8156880d9a03d5decca7e527ebd1bc5cdc25534f2bde4a785d0f

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