com.healthai/radar

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

Au dernier audit MCP Hub, le serveur MCP « com.healthai/radar » 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 14 outils

• cohort_postmarket_stats≈ 280 tokens

  Postmarket presence rates across the snapshotted AI/ML device cohort (optionally by panel): share with any recall in 24 months, with a rising MAUDE trend, with any drift signal, with a warning-letter match — every rate with its denominator inline, never pooled across devices.

  Paramètres, retour & exemple (1)

  Paramètres

  • panel · string · optionnel
    Advisory panel, e.g. Radiology; omit for all

  Exemple d'appel

  {"name": "cohort_postmarket_stats", "arguments": {"panel": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"data": "texte", "status": "ok", "message": "texte", "untrusted_data_notice": "texte"}}

• device_evidence_lookup≈ 305 tokens

  Look up the structured premarket evidence FDA accepted for a specific AI/ML-enabled device by 510(k) number (e.g. K252148). Returns parsed summary fields — validation study design, sample sizes, endpoints, reported performance, predicate chain, PCCP — each with a verbatim source quote and page. Null means the summary did not state it.

  Paramètres, retour & exemple (1)

  Paramètres

  • k_number · string · requis
    510(k) or De Novo number, e.g. K252148 or DEN180001

  Exemple d'appel

  {"name": "device_evidence_lookup", "arguments": {"k_number": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"data": "texte", "status": "ok", "message": "texte", "untrusted_data_notice": "texte"}}

• device_postmarket_lookup≈ 327 tokens

  Post-clearance intelligence for one AI/ML device by 510(k) number: its product code's recalls, MAUDE adverse-event level and trend, warning-letter and 483 matches for the applicant, plus per-device drift signals (adverse-event inflection, re-clearances of the same device line, software-recall patterns, predicate-cohort recall activity). Descriptive observables with sources — never a safety judgment.

  Paramètres, retour & exemple (1)

  Paramètres

  • k_number · string · requis
    510(k) or De Novo number, e.g. K252148 or DEN180001

  Exemple d'appel

  {"name": "device_postmarket_lookup", "arguments": {"k_number": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"data": "texte", "status": "ok", "message": "texte", "untrusted_data_notice": "texte"}}

• device_risk_lookup≈ 299 tokens

  Review a medical-device category's public FDA signals by three-letter product code (e.g. FRN = infusion pump). Returns recalls, MAUDE adverse-event trend, warning-letter matches, a normalized category signal, its driver contributions, and interpretation limits. It does not predict enforcement against a firm.

  Paramètres, retour & exemple (1)

  Paramètres

  • product_code · string · requis
    FDA product code, e.g. FRN

  Exemple d'appel

  {"name": "device_risk_lookup", "arguments": {"product_code": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"data": "texte", "status": "ok", "message": "texte", "untrusted_data_notice": "texte"}}

• evidence_cohort_stats≈ 324 tokens

  Reporting-rate stats across the parsed AI/ML corpus (optionally by panel). Each rate is a presence figure with its denominator — 'reported in X of Y audited devices' — never a pooled performance value. Excludes not-yet-parsed devices from every denominator and discloses the parse queue separately. Predicate age (median years between a clearance and its cited predicates) is included when decision-date coverage clears a 60% floor, and withheld otherwise.

  Paramètres, retour & exemple (1)

  Paramètres

  • panel · string · optionnel
    Advisory panel, e.g. Radiology; omit for all

  Exemple d'appel

  {"name": "evidence_cohort_stats", "arguments": {"panel": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"data": "texte", "status": "ok", "message": "texte", "untrusted_data_notice": "texte"}}

• evidence_search≈ 607 tokens

  Find AI/ML device clearances by filter — product code, panel, applicant, and whether the submission reported clinical data, any sensitivity metric, or a PCCP. Answers 'what evidence did FDA accept for devices like mine'. Returns bounded discovery summaries; call device_evidence_lookup with a result's K-number for the full source-quoted FDA record. Presence flags are descriptive: 'reports a sensitivity metric' is not 'reports a comparable sensitivity' — analysis units differ across devices.

  Paramètres, retour & exemple (8)

  Paramètres

  • limit · integer · optionnel
  • panel · string · optionnel
    Advisory panel, e.g. Radiology
  • cursor · string · optionnel
    Opaque continuation cursor returned by a prior page.
  • has_pccp · boolean · optionnel
    Included a Predetermined Change Control Plan
  • applicant · string · optionnel
    Substring match on applicant/company name
  • product_code · string · optionnel
    FDA product code, e.g. QAS
  • has_clinical_data · boolean · optionnel
  • reports_any_sensitivity_metric · boolean · optionnel
    Reported any sensitivity metric (canonical — includes per-finding sensitivities, not just the top-level slot). Not a claim of cross-device comparability.

  Exemple d'appel

  {"name": "evidence_search", "arguments": {"limit": 1, "panel": "texte", "cursor": "texte", "has_pccp": true, "applicant": "texte", "product_code": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"data": "texte", "status": "ok", "message": "texte", "untrusted_data_notice": "texte"}}

• firm_compliance_history≈ 504 tokens

  Build a recent, source-bounded FDA public-record timeline for a device firm: matched recalls, warning letters, and Form 483 citations where exact FEI numbers are available. Product codes are discovered from Constat's AI/ML-device corpus or may be supplied explicitly. Returns attribution and coverage limits with the records; it is not a finding of noncompliance or a prediction of FDA action.

  Paramètres, retour & exemple (5)

  Paramètres

  • limit · integer · optionnel
    Maximum records per source and events in the timeline (default 20).
  • since · string · optionnel
    Earliest event date, YYYY-MM-DD. Defaults to five years ago.
  • firm_name · string · requis
    FDA applicant or company name, e.g. 'Medtronic'
  • fei_numbers · array · optionnel
    Optional exact FDA FEI numbers; improves Form 483 attribution.
  • product_codes · array · optionnel
    Optional FDA product-code scope. When omitted, Constat discovers codes from applicant matches in its device corpus.

  Exemple d'appel

  {"name": "firm_compliance_history", "arguments": {"firm_name": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"data": "texte", "status": "ok", "message": "texte", "untrusted_data_notice": "texte"}}

• postmarket_search≈ 604 tokens

  Find AI/ML devices by postmarket criteria — product code, panel, applicant, whether any drift signal exists, minimum recalls in 24 months, or a rising MAUDE trend. Returns per-device postmarket summaries with drift-signal counts.

  Paramètres, retour & exemple (9)

  Paramètres

  • limit · integer · optionnel
  • panel · string · optionnel
    Advisory panel, e.g. Radiology
  • cursor · string · optionnel
    Opaque continuation cursor returned by a prior page.
  • applicant · string · optionnel
    Substring match on applicant/company name
  • product_code · string · optionnel
    FDA product code, e.g. QIH
  • maude_trend_up · boolean · optionnel
    Code-level MAUDE trend above its own 3-year baseline
  • has_drift_signal · boolean · optionnel
  • min_recalls_24mo · integer · optionnel
    Product-code recalls in trailing 24 months
  • signal_specificity · string · optionnel · device | product_code
    Restrict the drift-signal filter to one tier: 'device' = attributable to this device (own line re-cleared, own applicant's recall, predicate neighbors) — the high-signal tier; 'product_code' = observed in its category

  Exemple d'appel

  {"name": "postmarket_search", "arguments": {"limit": 1, "panel": "texte", "cursor": "texte", "applicant": "texte", "product_code": "texte", "maude_trend_up": true}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"data": "texte", "status": "ok", "message": "texte", "untrusted_data_notice": "texte"}}

• predicate_chain≈ 346 tokens

  Trace the predicate ancestry of a 510(k) device, with each cited predicate's age (how many years old the predicate was when the child cleared). Reveals how AI/ML devices chain to older predicates.

  Paramètres, retour & exemple (2)

  Paramètres

  • depth · integer · optionnel
    Max ancestry depth (default 4)
  • k_number · string · requis
    510(k) or De Novo number, e.g. K252148 or DEN180001

  Exemple d'appel

  {"name": "predicate_chain", "arguments": {"k_number": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"data": "texte", "status": "ok", "message": "texte", "untrusted_data_notice": "texte"}}

• reimbursement_lookup≈ 388 tokens

  Trace the clearance-to-payment pathway for an AI/ML device by FDA clearance number (K/DEN, e.g. DEN170073) OR bare CPT code (e.g. 75580). Returns every payment mechanism (NTAP add-on, Category I/III CPT + CMS rate, HCPCS, MAC LCD) with amounts, effective dates, and source links, plus any commercial/MAC payer coverage policies that reference the clearance or its codes. Answers 'who got paid, how much, through which mechanism, on what basis.' CPT codes are bare factual identifiers only — no procedure descriptors; follow the CMS source link for the official descriptor.

  Paramètres, retour & exemple (2)

  Paramètres

  • cpt_code · string · optionnel
    Bare CPT code, e.g. 75580 or 0932T
  • k_number · string · optionnel
    FDA clearance number, e.g. DEN170073 or K252148

  Exemple d'appel

  {"name": "reimbursement_lookup", "arguments": {"cpt_code": "texte", "k_number": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"data": "texte", "status": "ok", "message": "texte", "untrusted_data_notice": "texte"}}

• reimbursement_search≈ 547 tokens

  Find AI/ML device payment pathways by mechanism — e.g. 'devices that got NTAP', 'devices paid under a Category I CPT code', 'pathways with a known CMS dollar rate'. Filters: mechanism, CPT category, NTAP status, applicant. Returns pathways with amounts, effective dates, and sources. Use reimbursement_stats for the mechanism distribution (never a single pooled reimbursement rate).

  Paramètres, retour & exemple (7)

  Paramètres

  • limit · integer · optionnel
  • cursor · string · optionnel
    Opaque continuation cursor returned by a prior page.
  • applicant · string · optionnel
    Substring match on device maker / applicant name
  • mechanism · string · optionnel · ntap | cat_iii_apc | cat_i | hcpcs | lcd | none
    Payment mechanism
  • ntap_status · string · optionnel · active | expired | granted | none
  • cpt_category · string · optionnel · I | III | unknown
    CPT category
  • has_cms_rate · boolean · optionnel
    Only pathways with a known CMS dollar rate

  Exemple d'appel

  {"name": "reimbursement_search", "arguments": {"limit": 1, "cursor": "texte", "applicant": "texte", "mechanism": "ntap", "ntap_status": "active", "cpt_category": "I"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"data": "texte", "status": "ok", "message": "texte", "untrusted_data_notice": "texte"}}

• reimbursement_stats≈ 278 tokens

  Distribution of payment mechanisms across the AI/ML reimbursement corpus — pathway and distinct-device counts per mechanism (NTAP, Cat I, Cat III/APC, …) with the min/median/max dollar amounts for each. Deliberately never a single pooled 'reimbursement rate': NTAP add-on amounts and CMS rates are different measurements and are reported separately with their own spreads.

  Paramètres, retour & exemple (0)

  Exemple d'appel

  {"name": "reimbursement_stats", "arguments": {}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"data": "texte", "status": "ok", "message": "texte", "untrusted_data_notice": "texte"}}

• vehicle_risk_lookup≈ 304 tokens

  Look up NHTSA safety history for a vehicle by make, model, and model year. Returns recall campaigns and complaint statistics (crashes, fires, injuries, top components).

  Paramètres, retour & exemple (3)

  Paramètres

  • make · string · requis
    e.g. honda
  • year · string · requis
    model year, e.g. 2020
  • model · string · requis
    e.g. civic

  Exemple d'appel

  {"name": "vehicle_risk_lookup", "arguments": {"make": "texte", "year": "texte", "model": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"data": "texte", "status": "ok", "message": "texte", "untrusted_data_notice": "texte"}}

• watchlist_diff≈ 416 tokens

  Return machine-generated FDA public-record changes detected for monitored product codes since a caller-supplied date, plus each code's latest category snapshot and postmarket coverage. Defaults to Constat Radar's five-code watchlist and the last seven days. Analyst verdict text and internal review status are excluded; use next_since as the next polling cursor.

  Paramètres, retour & exemple (3)

  Paramètres

  • limit · integer · optionnel
    Maximum changes to return (default 10).
  • since · string · optionnel
    Return changes on or after this ISO date or UTC timestamp. Defaults to the last seven days; pass the prior response's next_since for exact polling.
  • product_codes · array · optionnel
    FDA product codes to poll. Omit for the default Radar watchlist.

  Exemple d'appel

  {"name": "watchlist_diff", "arguments": {"limit": 1, "since": "texte", "product_codes": []}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"data": "texte", "status": "ok", "message": "texte", "untrusted_data_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://constat.dev/api/mcp