com.healthai/clarity

Est-ce que com.healthai/clarity est sûr ?

Au dernier audit MCP Hub, le serveur MCP « com.healthai/clarity » est classé « Non encore testé ». Référencé dans l'annuaire. Seul le pentest comportemental fait foi, et il n'a pas encore été exécuté sur ce serveur. Le verdict est réévalué en continu ; consultez la fiche pour l'état à jour.

Méthode : MCP Hub analyse la description de chaque outil (couche 1) et, pour le verdict fort, exécute le serveur dans une micro-VM isolée avec leurres et réseau bloqué (couche 2). On publie des noms et des compteurs, jamais le contenu brut renvoyé par un outil.

Les 9 outils

• check_ingredient≈ 556 tokens

  Look up a cosmetic/food/supplement ingredient in Clarity's condition-aware database. Returns verdict, evidence tier (Gold/Silver/Bronze), and citation for a given condition lens. Pass `lenses` (array) instead of `lens` to check several conditions in ONE call (profile-shaped checking, e.g. a user who is pregnant AND has MCAS) — results then carry a per-lens breakdown under `lenses{}`. Every result includes human_url, a live Clarity page to hand the user as the source link.

  Paramètres, retour & exemple (3)

  Paramètres

  • lens · string · optionnel · breastfeeding | lactation | pregnancy | histamine | mcas | rosacea | hs | allergy
    Single condition lens
  • name · string · requis
    Ingredient name, e.g. 'niacinamide' or 'aged cheddar cheese'
  • lenses · array · optionnel
    Multiple condition lenses in one call (anonymous max 3, keyed max 4); wins over `lens` when provided

  Exemple d'appel

  {"name": "check_ingredient", "arguments": {"name": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"error": "texte", "human_url": "texte", "disclaimer": "texte", "source_notice": "texte"}}

• check_interaction≈ 495 tokens

  Check Clarity's curated ingredient-to-ingredient interaction database. Give one ingredient to list everything it interacts with (e.g. 'iron'), or two ingredients to check a specific pair (e.g. 'calcium' + 'iron'). Returns interaction_type, severity (Beneficial/Moderate/High), mechanism, clinical_note, source, and whether it affects lactation/infant/absorption. Queries both directions of the pair. Absence of a result is NOT proof of safety — the set is curated and growing. Descriptive with sources, not medical advice.

  Paramètres, retour & exemple (2)

  Paramètres

  • ingredient_a · string · requis
    The ingredient to check, e.g. 'iron' or 'calcium'
  • ingredient_b · string · optionnel
    Optional second ingredient to check a specific pair. Omit to list all interactions for ingredient_a.

  Exemple d'appel

  {"name": "check_interaction", "arguments": {"ingredient_a": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"error": "texte", "human_url": "texte", "disclaimer": "texte", "source_notice": "texte"}}

• check_recall≈ 488 tokens

  Check whether a consumer product or brand has an FDA/consumer recall on file — supplements, food, cosmetics (NOT medical devices). Query by `brand` (primary), optionally narrow by `product_name`. Returns recall_flag, whether any active Class I (most serious) recall exists, and each matching record with classification, reason, date, status, and a source_url to verify. Recall data has no barcode, so matches are brand/name text matches — confirm via source_url. For medical-DEVICE recalls, use the radar MCP (com.healthai/radar).

  Paramètres, retour & exemple (2)

  Paramètres

  • brand · string · requis
    Brand or manufacturer name, e.g. 'Nature Made' or 'Similac'
  • product_name · string · optionnel
    Optional product name to narrow within the brand, e.g. 'infant formula'

  Exemple d'appel

  {"name": "check_recall", "arguments": {"brand": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"error": "texte", "human_url": "texte", "disclaimer": "texte", "source_notice": "texte"}}

• check_stack≈ 580 tokens

  Audit a supplement/ingredient STACK in one call: per-item condition-lens verdicts (evidence-graded, cited where citations exist) PLUS every curated ingredient-to-ingredient interaction found WITHIN the stack (type, severity, mechanism, source). Use when a user takes multiple supplements together. Supports multi-lens via `lenses`. Absence of an interaction is NOT proof of safety — the curated set is growing. Every result includes human_url for the user.

  Paramètres, retour & exemple (3)

  Paramètres

  • lens · string · optionnel · breastfeeding | lactation | pregnancy | histamine | mcas | rosacea | hs | allergy
    Single condition lens
  • lenses · array · optionnel
    Multiple condition lenses in one call (anonymous max 2, keyed max 3); wins over `lens` when provided
  • ingredients · array · requis
    2-6 ingredient/supplement names anonymously (2-10 with a key), e.g. ['iron','calcium','quercetin']

  Exemple d'appel

  {"name": "check_stack", "arguments": {"ingredients": []}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"error": "texte", "human_url": "texte", "disclaimer": "texte", "source_notice": "texte"}}

• find_alternatives≈ 603 tokens

  Find 2-3 safer swaps for a flagged product: same-category products that rate good/excellent on Clarity's general food/skincare quality score AND contain no ingredient flagged for the given condition lens. Seed by barcode (preferred — e.g. right after scan_barcode flags something) or product_name. Each alternative carries its score, ingredient-recognition coverage, and human_url. The score is a GENERAL quality score, not a condition verdict — verify a chosen alternative with scan_barcode or check_stack. Food and skincare only (supplement swaps are declined honestly for now).

  Paramètres, retour & exemple (4)

  Paramètres

  • lens · string · optionnel · breastfeeding | lactation | pregnancy | histamine | mcas | rosacea | hs | allergy
    Condition lens for the ingredient screen
  • count · integer · optionnel
    How many alternatives to return (anonymous 1-2; keyed 1-3)
  • barcode · string · optionnel
    UPC/EAN of the product to swap away from (6-14 digits)
  • product_name · string · optionnel
    Product name to seed from when no barcode is available

  Exemple d'appel

  {"name": "find_alternatives", "arguments": {"lens": "breastfeeding", "count": 1, "barcode": "texte", "product_name": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"error": "texte", "human_url": "texte", "disclaimer": "texte", "source_notice": "texte"}}

• scan_barcode≈ 570 tokens

  Look up a product by barcode (Open Food Facts / Open Beauty Facts), match its ingredients against Clarity's database, return which ingredients are flagged for the given condition lens, AND flag any active FDA recall for the product (recall_flag + recalls[], sourced from FDA — verify via source_url). Anonymous calls are read-only: a local-mirror miss may query the public source but does not refresh Clarity's mirror or harvest tokens. An authenticated caller may opt into each bounded side effect with persist_mirror:true and harvest_crosswalk:true.

  Paramètres, retour & exemple (4)

  Paramètres

  • lens · string · optionnel · breastfeeding | lactation | pregnancy | histamine | mcas | rosacea | hs | allergy
    Condition lens
  • barcode · string · requis
    UPC/EAN barcode, 6-14 digits
  • persist_mirror · boolean · optionnel
    Authenticated callers only: explicitly allow one bounded live-result mirror refresh.
  • harvest_crosswalk · boolean · optionnel
    Authenticated callers only: explicitly allow bounded unmatched-token coverage logging.

  Exemple d'appel

  {"name": "scan_barcode", "arguments": {"barcode": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"error": "texte", "human_url": "texte", "disclaimer": "texte", "source_notice": "texte"}}

• score_product≈ 509 tokens

  Get Clarity's product quality score by barcode. Returns category-specific scores (food: nutrition/additive/processing/organic; skincare: irritation/allergen/endocrine/condition; supplement: transparency/safety/label_quality/complexity — dose transparency penalizes proprietary blends, safety flags high-risk botanicals) — these are DISTINCT and never merged — plus per-lens fit with match coverage. Always includes data_quality/coverage so a score is never given without its confidence.

  Paramètres, retour & exemple (3)

  Paramètres

  • lens · string · optionnel · breastfeeding | lactation | pregnancy | histamine | mcas | rosacea | hs | allergy
    Condition lens for per-lens fit
  • barcode · string · requis
    UPC/EAN barcode, 6-14 digits
  • category · string · optionnel · food | skincare | supplement
    Product category (omit for auto)

  Exemple d'appel

  {"name": "score_product", "arguments": {"barcode": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"error": "texte", "human_url": "texte", "disclaimer": "texte", "source_notice": "texte"}}

• strain_lookup≈ 359 tokens

  Look up a cannabis or mushroom species/strain in Clarity's database. Returns verdict, evidence tier, PMID citation, and safety flags.

  Paramètres, retour & exemple (1)

  Paramètres

  • species · string · requis
    Species or strain name, e.g. 'Cannabis sativa' or 'Lion's Mane'

  Exemple d'appel

  {"name": "strain_lookup", "arguments": {"species": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"error": "texte", "human_url": "texte", "disclaimer": "texte", "source_notice": "texte"}}

• validate_claim≈ 571 tokens

  Fact-check a free-text health/safety claim against Clarity's human-curated, evidence-graded database. Given a statement (e.g. 'fenugreek is safe while breastfeeding') and a condition lens, returns whether Clarity's curated position supports / contradicts / does-not-cover it, plus any verified citation on file. Anonymous calls never write the review queue. An authenticated caller may explicitly opt into a bounded, redacted review signal with review_consent:true. Do not include personal information. Descriptive — not medical advice.

  Paramètres, retour & exemple (3)

  Paramètres

  • lens · string · optionnel · breastfeeding | lactation | pregnancy | histamine | mcas | rosacea | hs | allergy
    Condition lens the claim is about
  • statement · string · requis
    The health/safety claim to validate, e.g. 'niacinamide is safe during pregnancy'. Do not include personal information.
  • review_consent · boolean · optionnel
    Authenticated callers only: explicitly consent to a bounded, redacted uncovered-claim review signal. Ignored for anonymous calls.

  Exemple d'appel

  {"name": "validate_claim", "arguments": {"statement": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"error": "texte", "human_url": "texte", "disclaimer": "texte", "source_notice": "texte"}}

C'est votre serveur ?

Revendiquez-le sur l'espace créateur (preuve GitHub, domaine ou npm) pour afficher le badge « propriétaire vérifié » et lancer un pentest comportemental à la demande afin d'obtenir le badge « Vérifié ».

Créer un compte / revendiquer →

Source

https://mcp.healthai.com