app.ivive/ivive

Est-ce que app.ivive/ivive est sûr ?

Au dernier audit MCP Hub, le serveur MCP « app.ivive/ivive » 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 6 outils

• calc_clhep≈ 622 tokens

  Hepatic and plasma clearance from in-vitro CLint, fu,mic and fu,p (IVIVE), with the observed-CL band and applicability warnings. If fu,p or fu,mic came from predict_inputs, tell the user the result rests on predicted inputs.

  Paramètres, retour & exemple (9)

  Paramètres

  • rb · number · optionnel
    Blood-to-plasma concentration ratio. fu_b = fu_p / Rb. Output is blood clearance.
  • fu_p · number · requis
    Unbound fraction in plasma (0–1). Plasma protein binding correction.
  • clint · number · requis
    Intrinsic clearance (µL/min/mg microsomal protein). Use ge=0: zero clearance is physiologically valid.
  • model · string · optionnel · well-stirred | parallel-tube
    IVIVE model. well-stirred (venous equilibrium) or parallel-tube (sinusoidal perfusion).
  • fu_mic · number · requis
    Unbound fraction in microsomes (0–1). Corrects for non-specific microsomal binding.
  • species · string · requis · human | rat | dog
    Species for physiological parameters (Qh, MPPGL, liver weight).
  • assay_type · string · optionnel · microsomes | hepatocytes
    Assay type for CLint scaling. microsomes: uses MPPGL (mg/g) × 1e-3; hepatocytes: uses HPGL (×10⁶ cells/g) × 1e-3.
  • correction_id · ? · optionnel
    Saved lab correction (/api/correction-equations) to apply. Must match species and assay_type. Corrects predicted plasma CL and replaces the reference band with one from the lab's compounds.
  • clint_censored · boolean · optionnel
    Set when the assay reported CLint below its limit of quantification and `clint` is that limit rather than a measurement. CLint then lies in [0, clint), so every clearance output is an upper bound: `upper_bound` is true, no observed-CL band is returned, and the clint_below_loq flag fires.

  Exemple d'appel

  {"name": "calc_clhep", "arguments": {"fu_p": 1, "clint": 1, "fu_mic": 1, "species": "human"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• input_sensitivity≈ 772 tokens

  How far plasma CL moves as each input is varied over a range, e.g. a predicted fu,p over its 50% range.

  Paramètres, retour & exemple (12)

  Paramètres

  • rb · number · optionnel
    Blood-to-plasma concentration ratio. fu_b = fu_p / Rb. Output is blood clearance.
  • fu_p · number · requis
    Unbound fraction in plasma (0–1). Plasma protein binding correction.
  • clint · number · requis
    Intrinsic clearance (µL/min/mg microsomal protein). Use ge=0: zero clearance is physiologically valid.
  • model · string · optionnel · well-stirred | parallel-tube
    IVIVE model. well-stirred (venous equilibrium) or parallel-tube (sinusoidal perfusion).
  • fu_mic · number · requis
    Unbound fraction in microsomes (0–1). Corrects for non-specific microsomal binding.
  • species · string · requis · human | rat | dog
    Species for physiological parameters (Qh, MPPGL, liver weight).
  • assay_type · string · optionnel · microsomes | hepatocytes
    Assay type for CLint scaling. microsomes: uses MPPGL (mg/g) × 1e-3; hepatocytes: uses HPGL (×10⁶ cells/g) × 1e-3.
  • fu_p_range · ? · optionnel
    A predicted fu,p carries its 50% range; pass it to see what it costs.
  • clint_range · ? · optionnel
  • fu_mic_range · ? · optionnel
  • correction_id · ? · optionnel
    Saved lab correction (/api/correction-equations) to apply. Must match species and assay_type. Corrects predicted plasma CL and replaces the reference band with one from the lab's compounds.
  • clint_censored · boolean · optionnel
    Set when the assay reported CLint below its limit of quantification and `clint` is that limit rather than a measurement. CLint then lies in [0, clint), so every clearance output is an upper bound: `upper_bound` is true, no observed-CL band is returned, and the clint_below_loq flag fires.

  Exemple d'appel

  {"name": "input_sensitivity", "arguments": {"fu_p": 1, "clint": 1, "fu_mic": 1, "species": "human"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• predict_inputs≈ 187 tokens

  Predict fu,p and fu,inc from a SMILES, with structure-only human CL and Vss as second opinions. Predictions, not measurements; check the applicability verdict.

  Paramètres, retour & exemple (3)

  Paramètres

  • smiles · string · requis
    Structure as SMILES.
  • assay_type · string · optionnel · microsomes | hepatocytes
  • concentration · number · optionnel
    Incubation concentration: mg microsomal protein/mL, or 10⁶ hepatocytes/mL.

  Exemple d'appel

  {"name": "predict_inputs", "arguments": {"smiles": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• scale_to_human≈ 320 tokens

  Predict human plasma CL from observed animal in-vivo CL (rat, dog, monkey), every applicable method with its measured error. Observed animal CL only, never predicted.

  Paramètres, retour & exemple (2)

  Paramètres

  • animals · array · requis
  • fu_p_human · ? · optionnel
    Human unbound fraction, needed by the fu-corrected methods

  Exemple d'appel

  {"name": "scale_to_human", "arguments": {"animals": []}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• similar_drugs≈ 185 tokens

  Nearest reference drugs to a SMILES (Tanimoto, Morgan radius 2), each with measured human plasma CL and the CL IVIVE predicted from its measured inputs. Use it to judge how far to trust calc_clhep for this chemotype: if IVIVE missed on the neighbours, expect it to miss here. Returns neighbours only, not a prediction for the query.

  Paramètres, retour & exemple (2)

  Paramètres

  • n · integer · optionnel
    How many reference drugs to return, nearest first.
  • smiles · string · requis
    Structure as SMILES.

  Exemple d'appel

  {"name": "similar_drugs", "arguments": {"smiles": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• target_clint≈ 432 tokens

  The in-vitro CLint an assay must read for a compound to reach a target plasma clearance (mL/min/kg): calc_clhep run backwards, e.g. to set a CLint cut-off for a screening cascade. Needs fu,mic and fu,p; refuses a target at or above the liver blood flow ceiling and returns that ceiling. Uncorrected IVIVE, so no error band.

  Paramètres, retour & exemple (7)

  Paramètres

  • rb · number · optionnel
    Blood-to-plasma concentration ratio; raises the plasma CL ceiling (Qh × Rb).
  • fu_p · number · requis
    Unbound fraction in plasma (0–1).
  • model · string · optionnel · well-stirred | parallel-tube
    IVIVE liver model to invert.
  • fu_mic · number · requis
    Unbound fraction in the incubation (0–1) the CLint would be measured at.
  • species · string · requis · human | rat | dog
    Species whose liver blood flow and scaling factors apply.
  • assay_type · string · optionnel · microsomes | hepatocytes
    Assay the CLint is for; sets its units (µL/min/mg protein or µL/min/10⁶ cells).
  • target_clp · number · requis
    Plasma clearance to aim for (mL/min/kg). Must be below hepatic blood flow × Rb.

  Exemple d'appel

  {"name": "target_clint", "arguments": {"fu_p": 1, "fu_mic": 1, "species": "human", "target_clp": 1}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

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://api.ivive.app/mcp/