AOPX
Selects between supported SEARCH providers for ECONOMY or CRITICAL mode.
使うべきか
品質と安全性
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
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": {
"aopx": {
"url": "https://api.aopx.fr/mcp/"
}
}
}リモートエンドポイント
https://api.aopx.fr/mcp/streamable-httpできること
ツール一覧
ツール（4）
🟢recommend_provider(mode, client_id, max_cost_eur, max_latency_ms)
Use when a software agent needs an AOPX recommendation for the SEARCH category instead of hard-coding a single supported provider. Supported modes are ECONOMY and CRITICAL. Returns a primary provider and, when applicable, a fallback provider plus a recommendation_id. AOPX does not execute the search and does not handle payment; the caller executes the provider path externally. After a real execution, call report_outcome with the same recommendation_id. max_cost_eur and max_latency_ms are accepted and recorded by the current v0 interface but are not enforced as hard routing constraints.
入力スキーマ
{
"type": "object",
"properties": {
"mode": {
"enum": [
"ECONOMY",
"BALANCED",
"CRITICAL"
],
"title": "Mode",
"type": "string"
},
"client_id": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"default": null,
"title": "Client Id"
},
"max_cost_eur": {
"anyOf": [
{
"type": "number"
},
{
"type": "null"
}
],
"default": null,
"title": "Max Cost Eur"
},
"max_latency_ms": {
"anyOf": [
{
"type": "integer"
},
{
"type": "null"
}
],
"default": null,
"title": "Max Latency Ms"
}
},
"required": [
"mode"
],
"title": "recommend_providerArguments"
}出力スキーマ
{
"type": "object",
"additionalProperties": true,
"title": "recommend_providerDictOutput"
}⚪report_outcome(recommendation_id, attempts)
Use only after a real external execution of a provider path returned by recommend_provider. Records the caller-reported production outcome for that recommendation_id. The recommendation must exist, only one outcome is accepted per recommendation, and provider attempts must match the recommended primary/fallback path. Reported outcomes are production evidence supplied by the caller; they are not described as independently verified outcomes.
入力スキーマ
{
"type": "object",
"properties": {
"recommendation_id": {
"title": "Recommendation Id",
"type": "string"
},
"attempts": {
"items": {
"$ref": "#/$defs/ProviderAttempt"
},
"title": "Attempts",
"type": "array"
}
},
"required": [
"recommendation_id",
"attempts"
],
"$defs": {
"ProviderAttempt": {
"properties": {
"provider_id": {
"title": "Provider Id",
"type": "string"
},
"success": {
"title": "Success",
"type": "boolean"
},
"quality_score": {
"anyOf": [
{
"maximum": 1,
"minimum": 0,
"type": "number"
},
{
"type": "null"
}
],
"default": null,
"title": "Quality Score"
},
"cost_eur": {
"anyOf": [
{
"minimum": 0,
"type": "number"
},
{
"type": "null"
}
],
"default": null,
"title": "Cost Eur"
},
"latency_ms": {
"anyOf": [
{
"minimum": 0,
"type": "integer"
},
{
"type": "null"
}
],
"default": null,
"title": "Latency Ms"
},
"error_type": {
"anyOf": [
{
"maxLength": 200,
"type": "string"
},
{
"type": "null"
}
],
"default": null,
"title": "Error Type"
}
},
"required": [
"provider_id",
"success"
],
"title": "ProviderAttempt",
"type": "object"
}
},
"title": "report_outcomeArguments"
}出力スキーマ
{
"type": "object",
"additionalProperties": true,
"title": "report_outcomeDictOutput"
}🟢public_stats
Read aggregate public statistics from the AOPX production pilot, including consultation and reported-outcome activity. Use this for public telemetry, not for provider recommendation. LAB benchmarks, tests, shadow runs and replay events are excluded from these production statistics.
入力スキーマ
{
"type": "object",
"properties": {},
"title": "public_statsArguments"
}出力スキーマ
{
"type": "object",
"additionalProperties": true,
"title": "public_statsDictOutput"
}🟢public_outcomes(limit)
Read recent caller-reported production outcomes from the AOPX public evidence surface. Use this to inspect what was reported after real recommendations were executed, not to request a new recommendation. Provider identities are exposed only through public aliases. LAB benchmarks, tests, shadow runs and replays are not returned here, and reported outcomes are not described as independently verified.
入力スキーマ
{
"type": "object",
"properties": {
"limit": {
"default": 100,
"title": "Limit",
"type": "integer"
}
},
"title": "public_outcomesArguments"
}出力スキーマ
{
"type": "object",
"additionalProperties": true,
"title": "public_outcomesDictOutput"
}コミュニティ
エビデンス