alphalabs-intelligence
Live trading-pipeline intelligence for AI agents: signal scoring, calibration, recorded outcomes.
使うべきか
品質と安全性
検出事項（1）
- LOWTool 'alphalabs_explain_decision' description lacks action verbalphalabs_explain_decision 内
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": {
"alphalabs-intelligence": {
"url": "https://api.pak-labs.com/mcp"
}
}
}リモートエンドポイント
https://api.pak-labs.com/mcpstreamable-httpできること
ツール一覧
ツール（6）
🟢alphalabs_get_catalog
Free: list AlphaLabs Intelligence products, prices, and auth model.
入力スキーマ
{
"type": "object",
"properties": {},
"additionalProperties": false
}⚪alphalabs_calibration_report
Live paper-trading pipeline calibration telemetry: stage funnel, gate failures, near-misses. Derived analytics only — no positions, orders, or account data exist on this surface.
入力スキーマ
{
"type": "object",
"properties": {},
"additionalProperties": false
}🟢alphalabs_evaluate_signal(ticker, bias, confidence, catalyst, thesis, ...)
Score YOUR trade idea through the live AlphaLabs deterministic engine: composite score, tier, per-component sub-signals, floors. Price/volume confirmation is not evaluated (no vendor market data). Returns an evaluation_id for alphalabs_explain_decision.
入力スキーマ
{
"type": "object",
"properties": {
"ticker": {
"type": "string",
"description": "Symbol, e.g. NVDA"
},
"bias": {
"type": "string",
"enum": [
"bullish",
"bearish",
"neutral"
]
},
"confidence": {
"type": "number",
"minimum": 0,
"maximum": 1,
"description": "Your own conviction 0-1 (echoed, not scored)"
},
"catalyst": {
"type": "string",
"description": "What just happened (headline/event)"
},
"thesis": {
"type": "string",
"description": "Why it should move the stock"
},
"catalyst_type": {
"type": "string",
"description": "Optional label, e.g. 'Government Contract'"
},
"catalyst_score": {
"type": "number",
"minimum": 0,
"maximum": 100,
"description": "Optional 0-100 materiality if you scored it"
}
},
"required": [
"ticker",
"bias"
],
"additionalProperties": false
}⚪alphalabs_outcome_report
Recorded outcomes of the live pipeline's own decisions: hit rates, score-band tables, accepted-vs-rejected edge, gate near-miss regret. Aggregated engine telemetry — percent moves and counts only.
入力スキーマ
{
"type": "object",
"properties": {},
"additionalProperties": false
}⚪alphalabs_feature_attribution
Which engine inputs actually predict outcomes, measured on recorded live results: Spearman rankings, median-split deltas, dead inputs.
入力スキーマ
{
"type": "object",
"properties": {},
"additionalProperties": false
}🟢alphalabs_explain_decision(evaluation_id)
Glass-box breakdown of a prior evaluation by evaluation_id: every sub-signal, weight, floor, and the composite reasoning.
入力スキーマ
{
"type": "object",
"properties": {
"evaluation_id": {
"type": "string"
}
},
"required": [
"evaluation_id"
],
"additionalProperties": false
}コミュニティ
エビデンス