ivive.app
Human hepatic clearance from in-vitro CLint, with the error band measured on known drugs.
使うべきか
品質と安全性
A
ツール定義とプロトコルへの準拠に関する自動分析に基づいています。
コンテキストコスト
~2,172トークン数（ツール定義）
~3.6 KB一般的なレスポンスサイズ
注意への影響は中程度（128k コンテキストの 1.70%）
これは、サーバーのツールがモデルのコンテキストに読み込まれるたびに消費されるおおよそのトークン数です。数が多いほど、ほかのタスクに使える注意が減ります。
インストール
ワンクリックインストール
これを `claude_desktop_config.json` ファイルに追加してください:
{
"mcpServers": {
"ivive": {
"url": "https://api.ivive.app/mcp/"
}
}
}リモートエンドポイント
https://api.ivive.app/mcp/streamable-httpできること
ツール一覧
ツール（6）
🟢 読み取り専用🟡 書き込み🔴 削除⚪ 不明
🟢predict_inputs(smiles, assay_type, concentration)
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.
入力スキーマ
{
"type": "object",
"properties": {
"smiles": {
"maxLength": 2000,
"title": "Smiles",
"type": "string"
},
"assay_type": {
"default": "microsomes",
"enum": [
"microsomes",
"hepatocytes"
],
"title": "Assay Type",
"type": "string"
},
"concentration": {
"default": 1,
"description": "Incubation concentration: mg microsomal protein/mL, or 10⁶ hepatocytes/mL.",
"exclusiveMinimum": 0,
"maximum": 10,
"title": "Concentration",
"type": "number"
}
},
"required": [
"smiles"
],
"title": "PredictionRequest"
}⚪calc_clhep(clint, fu_mic, fu_p, rb, species, ...)
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.
入力スキーマ
{
"type": "object",
"properties": {
"clint": {
"description": "Intrinsic clearance (µL/min/mg microsomal protein). Use ge=0: zero clearance is physiologically valid.",
"minimum": 0,
"title": "Clint",
"type": "number"
},
"fu_mic": {
"description": "Unbound fraction in microsomes (0–1). Corrects for non-specific microsomal binding.",
"exclusiveMinimum": 0,
"maximum": 1,
"title": "Fu Mic",
"type": "number"
},
"fu_p": {
"description": "Unbound fraction in plasma (0–1). Plasma protein binding correction.",
"maximum": 1,
"minimum": 0,
"title": "Fu P",
"type": "number"
},
"rb": {
"default": 1,
"description": "Blood-to-plasma concentration ratio. fu_b = fu_p / Rb. Output is blood clearance.",
"exclusiveMinimum": 0,
"maximum": 50,
"title": "Rb",
"type": "number"
},
"species": {
"description": "Species for physiological parameters (Qh, MPPGL, liver weight).",
"enum": [
"human",
"rat",
"dog"
],
"title": "Species",
"type": "string"
},
"model": {
"default": "well-stirred",
"description": "IVIVE model. well-stirred (venous equilibrium) or parallel-tube (sinusoidal perfusion).",
"enum": [
"well-stirred",
"parallel-tube"
],
"title": "Model",
"type": "string"
},
"assay_type": {
"default": "microsomes",
"description": "Assay type for CLint scaling. microsomes: uses MPPGL (mg/g) × 1e-3; hepatocytes: uses HPGL (×10⁶ cells/g) × 1e-3.",
"enum": [
"microsomes",
"hepatocytes"
],
"title": "Assay Type",
"type": "string"
},
"correction_id": {
"anyOf": [
{
"format": "uuid",
"type": "string"
},
{
"type": "null"
}
],
"default": null,
"description": "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.",
"title": "Correction Id"
},
"clint_censored": {
"default": false,
"description": "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.",
"title": "Clint Censored",
"type": "boolean"
}
},
"required": [
"clint",
"fu_mic",
"fu_p",
"species"
],
"title": "CLhepRequest"
}🟢target_clint(target_clp, fu_mic, fu_p, rb, species, ...)
The in-vitro CLint an assay must read for a compound to reach a target plasma clearance.
入力スキーマ
{
"type": "object",
"properties": {
"target_clp": {
"description": "Plasma clearance to aim for (mL/min/kg). Must be below hepatic blood flow × Rb.",
"exclusiveMinimum": 0,
"title": "Target Clp",
"type": "number"
},
"fu_mic": {
"exclusiveMinimum": 0,
"maximum": 1,
"title": "Fu Mic",
"type": "number"
},
"fu_p": {
"exclusiveMinimum": 0,
"maximum": 1,
"title": "Fu P",
"type": "number"
},
"rb": {
"default": 1,
"exclusiveMinimum": 0,
"maximum": 50,
"title": "Rb",
"type": "number"
},
"species": {
"enum": [
"human",
"rat",
"dog"
],
"title": "Species",
"type": "string"
},
"model": {
"default": "well-stirred",
"enum": [
"well-stirred",
"parallel-tube"
],
"title": "Model",
"type": "string"
},
"assay_type": {
"default": "microsomes",
"enum": [
"microsomes",
"hepatocytes"
],
"title": "Assay Type",
"type": "string"
}
},
"required": [
"target_clp",
"fu_mic",
"fu_p",
"species"
],
"title": "TargetClintRequest"
}⚪input_sensitivity(clint, fu_mic, fu_p, rb, species, ...)
How far plasma CL moves as each input is varied over a range, e.g. a predicted fu,p over its 50% range.
入力スキーマ
{
"type": "object",
"properties": {
"clint": {
"description": "Intrinsic clearance (µL/min/mg microsomal protein). Use ge=0: zero clearance is physiologically valid.",
"minimum": 0,
"title": "Clint",
"type": "number"
},
"fu_mic": {
"description": "Unbound fraction in microsomes (0–1). Corrects for non-specific microsomal binding.",
"exclusiveMinimum": 0,
"maximum": 1,
"title": "Fu Mic",
"type": "number"
},
"fu_p": {
"description": "Unbound fraction in plasma (0–1). Plasma protein binding correction.",
"maximum": 1,
"minimum": 0,
"title": "Fu P",
"type": "number"
},
"rb": {
"default": 1,
"description": "Blood-to-plasma concentration ratio. fu_b = fu_p / Rb. Output is blood clearance.",
"exclusiveMinimum": 0,
"maximum": 50,
"title": "Rb",
"type": "number"
},
"species": {
"description": "Species for physiological parameters (Qh, MPPGL, liver weight).",
"enum": [
"human",
"rat",
"dog"
],
"title": "Species",
"type": "string"
},
"model": {
"default": "well-stirred",
"description": "IVIVE model. well-stirred (venous equilibrium) or parallel-tube (sinusoidal perfusion).",
"enum": [
"well-stirred",
"parallel-tube"
],
"title": "Model",
"type": "string"
},
"assay_type": {
"default": "microsomes",
"description": "Assay type for CLint scaling. microsomes: uses MPPGL (mg/g) × 1e-3; hepatocytes: uses HPGL (×10⁶ cells/g) × 1e-3.",
"enum": [
"microsomes",
"hepatocytes"
],
"title": "Assay Type",
"type": "string"
},
"correction_id": {
"anyOf": [
{
"format": "uuid",
"type": "string"
},
{
"type": "null"
}
],
"default": null,
"description": "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.",
"title": "Correction Id"
},
"clint_censored": {
"default": false,
"description": "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.",
"title": "Clint Censored",
"type": "boolean"
},
"clint_range": {
"anyOf": [
{
"$ref": "#/$defs/InputRange"
},
{
"type": "null"
}
],
"default": null
},
"fu_mic_range": {
"anyOf": [
{
"$ref": "#/$defs/InputRange"
},
{
"type": "null"
}
],
"default": null
},
"fu_p_range": {
"anyOf": [
{
"$ref": "#/$defs/InputRange"
},
{
"type": "null"
}
],
"default": null,
"description": "A predicted fu,p carries its 50% range; pass it to see what it costs."
}
},
"required": [
"clint",
"fu_mic",
"fu_p",
"species"
],
"$defs": {
"InputRange": {
"properties": {
"low": {
"exclusiveMinimum": 0,
"title": "Low",
"type": "number"
},
"high": {
"exclusiveMinimum": 0,
"title": "High",
"type": "number"
}
},
"required": [
"low",
"high"
],
"title": "InputRange",
"type": "object"
}
},
"description": "The same inputs as a calculation, plus the range to vary each over.",
"title": "SensitivityRequest"
}⚪similar_drugs(smiles, n)
Most similar reference drugs to a SMILES, with observed and IVIVE-predicted clearance: how IVIVE fared on this kind of structure.
入力スキーマ
{
"type": "object",
"properties": {
"smiles": {
"maxLength": 2000,
"title": "Smiles",
"type": "string"
},
"n": {
"default": 3,
"maximum": 10,
"minimum": 1,
"title": "N",
"type": "integer"
}
},
"required": [
"smiles"
],
"title": "SimilarityRequest"
}⚪scale_to_human(animals, fu_p_human)
Predict human plasma CL from observed animal in-vivo CL (rat, dog, monkey), every applicable method with its measured error. Observed animal CL only, never predicted.
入力スキーマ
{
"type": "object",
"properties": {
"animals": {
"items": {
"$ref": "#/$defs/SpeciesPoint"
},
"minItems": 1,
"title": "Animals",
"type": "array"
},
"fu_p_human": {
"anyOf": [
{
"exclusiveMinimum": 0,
"maximum": 1,
"type": "number"
},
{
"type": "null"
}
],
"default": null,
"description": "Human unbound fraction, needed by the fu-corrected methods",
"title": "Fu P Human"
}
},
"required": [
"animals"
],
"$defs": {
"SpeciesPoint": {
"description": "One animal's measured in-vivo plasma clearance, and optionally its binding.",
"properties": {
"species": {
"description": "One of ['dog', 'monkey', 'rat']",
"title": "Species",
"type": "string"
},
"cl": {
"description": "Observed plasma CL, mL/min/kg",
"exclusiveMinimum": 0,
"maximum": 1000,
"title": "Cl",
"type": "number"
},
"fu_p": {
"anyOf": [
{
"exclusiveMinimum": 0,
"maximum": 1,
"type": "number"
},
{
"type": "null"
}
],
"default": null,
"description": "Unbound fraction in plasma for this species",
"title": "Fu P"
}
},
"required": [
"species",
"cl"
],
"title": "SpeciesPoint",
"type": "object"
}
},
"title": "ScalingRequest"
}コミュニティ
エビデンス
最近の観測
検証済みバージョンは記録されていませんツール 6 件