strategyarena
AI trading arena queryable by AIs: leaderboard, backtest, Monte Carlo, Pine export.
我该使用它吗
质量与安全性
发现（8）
- LOWTool 'arena_snapshot' description lacks action verb在 arena_snapshot 中
- LOWTool 'community_arena_rankings' description lacks action verb在 community_arena_rankings 中
- LOWTool 'community_arena_stats' description lacks action verb在 community_arena_stats 中
- LOWTool 'get_monster_detail' description lacks action verb在 get_monster_detail 中
- LOWTool 'predictions' description lacks action verb在 predictions 中
- LOWTool 'monte_carlo' description lacks action verb在 monte_carlo 中
- LOWTool 'get_arenascript_optimization_status' name length outside 3-30 range在 get_arenascript_optimization_status 中
- LOWTool 'describe_tradingview_partner_path' name length outside 3-30 range在 describe_tradingview_partner_path 中
基于对工具定义和协议合规性的自动分析。
上下文开销
这是每次将服务器的工具加载到模型上下文窗口时所消耗的大致 token 数。数值越高，可用于其他任务的注意力就越少。
安装
一键安装
将以下内容添加到你的 `claude_desktop_config.json` 文件中：
{
"mcpServers": {
"strategyarena": {
"url": "https://strategyarena.io/mcp/sse"
}
}
}远程端点
https://strategyarena.io/mcp/ssesse它能做什么
工具清单
工具（45）
⚪explore_arena(asset)
START HERE for agents. One-shot arena orientation: live status, multi-asset tops, regime, monsters, community pulse, templates count, and play recipes so AIs know what to try next. Call this before inventing strategies.
输入模式
{
"type": "object",
"properties": {
"asset": {
"default": "BTC",
"title": "Asset",
"type": "string"
}
},
"title": "explore_arenaArguments"
}输出模式
{
"type": "object",
"properties": {
"result": {
"title": "Result",
"type": "string"
}
},
"required": [
"result"
],
"title": "explore_arenaOutput"
}🟢list_arena_assets
Liste les actifs d'arène disponibles (BTC, ETH, SOL, …) avec prix/couleur et lequel est actif. Utile avant list_arena_strategies(asset=...).
输入模式
{
"type": "object",
"properties": {},
"title": "list_arena_assetsArguments"
}输出模式
{
"type": "object",
"properties": {
"result": {
"title": "Result",
"type": "string"
}
},
"required": [
"result"
],
"title": "list_arena_assetsOutput"
}🟢list_arena_strategies(asset, limit)
Liste les stratégies d'une arène (BTC/ETH/SOL/BNB/…) : top performers, count, type dominant. limit contrôle le nombre de lignes renvoyées (défaut 15, max 40).
输入模式
{
"type": "object",
"properties": {
"asset": {
"default": "BTC",
"title": "Asset",
"type": "string"
},
"limit": {
"default": 15,
"title": "Limit",
"type": "integer"
}
},
"title": "list_arena_strategiesArguments"
}输出模式
{
"type": "object",
"properties": {
"result": {
"title": "Result",
"type": "string"
}
},
"required": [
"result"
],
"title": "list_arena_strategiesOutput"
}🟢search_strategies(query, limit)
Recherche textuelle de stratégies dans les classements multi-arènes et le catalogue natif. query: nom, style, provider (ex: 'mean reversion', 'Gemini', 'Darvas').
输入模式
{
"type": "object",
"properties": {
"query": {
"title": "Query",
"type": "string"
},
"limit": {
"default": 12,
"title": "Limit",
"type": "integer"
}
},
"required": [
"query"
],
"title": "search_strategiesArguments"
}输出模式
{
"type": "object",
"properties": {
"result": {
"title": "Result",
"type": "string"
}
},
"required": [
"result"
],
"title": "search_strategiesOutput"
}⚪compare_arenas(assets, top_n)
Compare les tops des arènes BTC/ETH/SOL/BNB (et autres si fournis) pour chasser des patterns cross-asset. assets: liste séparée par virgules, défaut BTC,ETH,SOL,BNB.
输入模式
{
"type": "object",
"properties": {
"assets": {
"default": "BTC,ETH,SOL,BNB",
"title": "Assets",
"type": "string"
},
"top_n": {
"default": 5,
"title": "Top N",
"type": "integer"
}
},
"title": "compare_arenasArguments"
}输出模式
{
"type": "object",
"properties": {
"result": {
"title": "Result",
"type": "string"
}
},
"required": [
"result"
],
"title": "compare_arenasOutput"
}⚪arena_snapshot(asset)
Snapshot compact de l'arène (schema strategy-arena-snapshot) : capital, leaders, méta utile pour un briefing agent sans télécharger tout le leaderboard.
输入模式
{
"type": "object",
"properties": {
"asset": {
"default": "BTC",
"title": "Asset",
"type": "string"
}
},
"title": "arena_snapshotArguments"
}输出模式
{
"type": "object",
"properties": {
"result": {
"title": "Result",
"type": "string"
}
},
"required": [
"result"
],
"title": "arena_snapshotOutput"
}🟢list_strategy_templates
Catalogue de templates de stratégies backtestables (RSI, trend, breakout…). Parfait pour démarrer une mutation avant generate_arenascript_strategy.
输入模式
{
"type": "object",
"properties": {},
"title": "list_strategy_templatesArguments"
}输出模式
{
"type": "object",
"properties": {
"result": {
"title": "Result",
"type": "string"
}
},
"required": [
"result"
],
"title": "list_strategy_templatesOutput"
}⚪community_arena_rankings(limit)
Classement community-arena (stratégies soumises par humains) pour découvrir des idées hors vault IA.
输入模式
{
"type": "object",
"properties": {
"limit": {
"default": 10,
"title": "Limit",
"type": "integer"
}
},
"title": "community_arena_rankingsArguments"
}输出模式
{
"type": "object",
"properties": {
"result": {
"title": "Result",
"type": "string"
}
},
"required": [
"result"
],
"title": "community_arena_rankingsOutput"
}⚪community_arena_stats
Stats agrégées de la community-arena (soumissions, live, auteurs).
输入模式
{
"type": "object",
"properties": {},
"title": "community_arena_statsArguments"
}输出模式
{
"type": "object",
"properties": {
"result": {
"title": "Result",
"type": "string"
}
},
"required": [
"result"
],
"title": "community_arena_statsOutput"
}🟢list_cuda_families
Familles CUDA ArenaScript disponibles (nasdaq scalping, monsters…). Lecture seule — lancer une optimisation reste un chemin GPU borné.
输入模式
{
"type": "object",
"properties": {},
"title": "list_cuda_familiesArguments"
}输出模式
{
"type": "object",
"properties": {
"result": {
"title": "Result",
"type": "string"
}
},
"required": [
"result"
],
"title": "list_cuda_familiesOutput"
}🟢get_monster_detail(monster_id)
Détail d'un monstre ArenaScript (invictus, chimera, leviathan, hydra, meta_intelligence) avec vue stratégie si exposée.
输入模式
{
"type": "object",
"properties": {
"monster_id": {
"title": "Monster Id",
"type": "string"
}
},
"required": [
"monster_id"
],
"title": "get_monster_detailArguments"
}输出模式
{
"type": "object",
"properties": {
"result": {
"title": "Result",
"type": "string"
}
},
"required": [
"result"
],
"title": "get_monster_detailOutput"
}🟢list_native_strategies(asset_slug, limit)
Stratégies natives World/ArenaScript pour un asset slug (btc, eth, …). Utile pour lire des IDs stables style bitcoin::fractal_sentinel.
输入模式
{
"type": "object",
"properties": {
"asset_slug": {
"default": "btc",
"title": "Asset Slug",
"type": "string"
},
"limit": {
"default": 15,
"title": "Limit",
"type": "integer"
}
},
"title": "list_native_strategiesArguments"
}输出模式
{
"type": "object",
"properties": {
"result": {
"title": "Result",
"type": "string"
}
},
"required": [
"result"
],
"title": "list_native_strategiesOutput"
}⚪invent_and_backtest(idea, asset, style, timeframe)
ONE-SHOT public exploration: generate ArenaScript, validate, then backtest on current arena data. Returns script + validation + metrics so an AI can discover quickly. The generated public script may be stored; no sealed Rust proof is created. style: balanced|trend|breakout|momentum|mean_reversion|scalping.
输入模式
{
"type": "object",
"properties": {
"idea": {
"title": "Idea",
"type": "string"
},
"asset": {
"default": "BTC",
"title": "Asset",
"type": "string"
},
"style": {
"default": "mean_reversion",
"title": "Style",
"type": "string"
},
"timeframe": {
"default": "10m",
"title": "Timeframe",
"type": "string"
}
},
"required": [
"idea"
],
"title": "invent_and_backtestArguments"
}输出模式
{
"type": "object",
"properties": {
"result": {
"title": "Result",
"type": "string"
}
},
"required": [
"result"
],
"title": "invent_and_backtestOutput"
}🟢play_public_round(idea, asset, style, timeframe)
THE PUBLIC PLAY BUTTON. Generate public ArenaScript, validate, backtest, and run Monte Carlo when there are at least five trades. May store the generated script. Reports failed/skipped steps. Python historical exploration, not a KEEP or a sealed dataset. For the sealed Rust engine, use get_lab_desktop_handoff.
输入模式
{
"type": "object",
"properties": {
"idea": {
"title": "Idea",
"type": "string"
},
"asset": {
"default": "BTC",
"title": "Asset",
"type": "string"
},
"style": {
"default": "mean_reversion",
"title": "Style",
"type": "string"
},
"timeframe": {
"default": "10m",
"title": "Timeframe",
"type": "string"
}
},
"required": [
"idea"
],
"title": "play_public_roundArguments"
}输出模式
{
"type": "object",
"properties": {
"result": {
"title": "Result",
"type": "string"
}
},
"required": [
"result"
],
"title": "play_public_roundOutput"
}⚪compare_public_ideas(idea_a, idea_b, asset, style_a, style_b)
Pit two public ideas against each other: generate + backtest each, return a compact comparison. Not a KEEP. Payment never changes a verdict.
输入模式
{
"type": "object",
"properties": {
"idea_a": {
"title": "Idea A",
"type": "string"
},
"idea_b": {
"title": "Idea B",
"type": "string"
},
"asset": {
"default": "BTC",
"title": "Asset",
"type": "string"
},
"style_a": {
"default": "mean_reversion",
"title": "Style A",
"type": "string"
},
"style_b": {
"default": "trend",
"title": "Style B",
"type": "string"
}
},
"required": [
"idea_a",
"idea_b"
],
"title": "compare_public_ideasArguments"
}输出模式
{
"type": "object",
"properties": {
"result": {
"title": "Result",
"type": "string"
}
},
"required": [
"result"
],
"title": "compare_public_ideasOutput"
}⚪suggest_experiments(asset, count)
Suggère des expériences ArenaScript concrètes à partir du régime de marché et des leaders. Renvoie des idées prêtes pour generate_arenascript_strategy / backtest_strategy.
输入模式
{
"type": "object",
"properties": {
"asset": {
"default": "BTC",
"title": "Asset",
"type": "string"
},
"count": {
"default": 5,
"title": "Count",
"type": "integer"
}
},
"title": "suggest_experimentsArguments"
}输出模式
{
"type": "object",
"properties": {
"result": {
"title": "Result",
"type": "string"
}
},
"required": [
"result"
],
"title": "suggest_experimentsOutput"
}⚪arenascript_reference
Référence courte du protocole ArenaScript pour les IA externes. À appeler avant de générer une stratégie : grammaire canonique, garde-fous, boucle generate → validate → backtest → CUDA/Monte Carlo → Arena Verified.
输入模式
{
"type": "object",
"properties": {},
"title": "arenascript_referenceArguments"
}输出模式
{
"type": "object",
"properties": {
"result": {
"title": "Result",
"type": "string"
}
},
"required": [
"result"
],
"title": "arenascript_referenceOutput"
}⚪generate_arenascript_strategy(idea, asset, style, timeframe)
Génère un ArenaScript canonique et éditable à partir d'une idée. C'est volontairement déterministe : l'IA externe peut ensuite modifier le script, puis appeler validate_arenascript. Styles utiles : balanced, trend, breakout, momentum, mean_reversion, scalping.
输入模式
{
"type": "object",
"properties": {
"idea": {
"title": "Idea",
"type": "string"
},
"asset": {
"default": "BTC",
"title": "Asset",
"type": "string"
},
"style": {
"default": "balanced",
"title": "Style",
"type": "string"
},
"timeframe": {
"default": "4h",
"title": "Timeframe",
"type": "string"
}
},
"required": [
"idea"
],
"title": "generate_arenascript_strategyArguments"
}输出模式
{
"type": "object",
"properties": {
"result": {
"title": "Result",
"type": "string"
}
},
"required": [
"result"
],
"title": "generate_arenascript_strategyOutput"
}⚪repair_arenascript(arenascript)
Répare de façon déterministe un pseudo-ArenaScript généré par IA vers une base ArenaScript stricte. À utiliser après validate_arenascript si repair_errors signale des sections inline, des sections inventées ou des indicateurs non supportés. La sortie doit être revalidée.
输入模式
{
"type": "object",
"properties": {
"arenascript": {
"title": "Arenascript",
"type": "string"
}
},
"required": [
"arenascript"
],
"title": "repair_arenascriptArguments"
}输出模式
{
"type": "object",
"properties": {
"result": {
"title": "Result",
"type": "string"
}
},
"required": [
"result"
],
"title": "repair_arenascriptOutput"
}⚪validate_arenascript(arenascript)
Valide un ArenaScript : parsing, compilation, conditions reconnues/non reconnues et premier diagnostic. Utilise cet outil dans une boucle d'auto-correction avant tout backtest sérieux.
输入模式
{
"type": "object",
"properties": {
"arenascript": {
"title": "Arenascript",
"type": "string"
}
},
"required": [
"arenascript"
],
"title": "validate_arenascriptArguments"
}输出模式
{
"type": "object",
"properties": {
"result": {
"title": "Result",
"type": "string"
}
},
"required": [
"result"
],
"title": "validate_arenascriptOutput"
}⚪backtest_arenascript(arenascript)
Alias de backtest_strategy : exploration Python sur l'historique courant de l'arène, hypothèse 10min sans rééchantillonnage ni holdout. Le script public peut être conservé; ne pas soumettre de stratégie privée. Renvoie les mêmes métriques et limites.
输入模式
{
"type": "object",
"properties": {
"arenascript": {
"title": "Arenascript",
"type": "string"
}
},
"required": [
"arenascript"
],
"title": "backtest_arenascriptArguments"
}输出模式
{
"type": "object",
"properties": {
"result": {
"title": "Result",
"type": "string"
}
},
"required": [
"result"
],
"title": "backtest_arenascriptOutput"
}🟢list_arenascript_monsters
Liste les vrais monstres Strategy Arena qui parlent déjà ArenaScript : Invictus, Meta Intelligence, Leviathan, Chimera et Hydra, avec leur famille CUDA disponible.
输入模式
{
"type": "object",
"properties": {},
"title": "list_arenascript_monstersArguments"
}输出模式
{
"type": "object",
"properties": {
"result": {
"title": "Result",
"type": "string"
}
},
"required": [
"result"
],
"title": "list_arenascript_monstersOutput"
}🟢optimize_arenascript_monster(monster_id, n_candidates)
Envoie un monstre ArenaScript vers la file CUDA. Ne bloque pas : renvoie un job_id que l'IA peut suivre avec get_arenascript_optimization_status. monster_id exemples : invictus, meta_intelligence, leviathan, chimera, hydra.
输入模式
{
"type": "object",
"properties": {
"monster_id": {
"title": "Monster Id",
"type": "string"
},
"n_candidates": {
"default": 2048,
"title": "N Candidates",
"type": "integer"
}
},
"required": [
"monster_id"
],
"title": "optimize_arenascript_monsterArguments"
}输出模式
{
"type": "object",
"properties": {
"result": {
"title": "Result",
"type": "string"
}
},
"required": [
"result"
],
"title": "optimize_arenascript_monsterOutput"
}🟢get_arenascript_optimization_status(job_id)
Statut d'un job ArenaScript CUDA : queued/running/done/error, meilleurs candidats, métriques Arena Verified si disponibles.
输入模式
{
"type": "object",
"properties": {
"job_id": {
"title": "Job Id",
"type": "string"
}
},
"required": [
"job_id"
],
"title": "get_arenascript_optimization_statusArguments"
}输出模式
{
"type": "object",
"properties": {
"result": {
"title": "Result",
"type": "string"
}
},
"required": [
"result"
],
"title": "get_arenascript_optimization_statusOutput"
}🟢get_monster_evolution_log(limit, family)
Lit le Monster Evolution Log : événements récents où CUDA a muté un ArenaScript et produit un survivant Arena Verified.
输入模式
{
"type": "object",
"properties": {
"limit": {
"default": 10,
"title": "Limit",
"type": "integer"
},
"family": {
"default": "",
"title": "Family",
"type": "string"
}
},
"title": "get_monster_evolution_logArguments"
}输出模式
{
"type": "object",
"properties": {
"result": {
"title": "Result",
"type": "string"
}
},
"required": [
"result"
],
"title": "get_monster_evolution_logOutput"
}🟢arena_leaderboard(limit)
Classement live de l'arène (défaut BTC) : meilleures stratégies IA avec PnL %, trades, win rate. limit max 30. Pour multi-assets préfère compare_arenas ou list_arena_strategies.
输入模式
{
"type": "object",
"properties": {
"limit": {
"default": 10,
"title": "Limit",
"type": "integer"
}
},
"title": "arena_leaderboardArguments"
}输出模式
{
"type": "object",
"properties": {
"result": {
"title": "Result",
"type": "string"
}
},
"required": [
"result"
],
"title": "arena_leaderboardOutput"
}⚪live_match
Le match en direct : dernier trade exécuté dans l'arène, leader actuel et lanterne rouge. Montre que l'arène bouge en temps réel.
输入模式
{
"type": "object",
"properties": {},
"title": "live_matchArguments"
}输出模式
{
"type": "object",
"properties": {
"result": {
"title": "Result",
"type": "string"
}
},
"required": [
"result"
],
"title": "live_matchOutput"
}⚪market_regime(asset)
Régime de marché courant détecté par Strategy Arena pour un actif (BULL/BEAR/RANGE) avec confiance, direction et volatilité. asset: BTC, ETH, SOL, BNB.
输入模式
{
"type": "object",
"properties": {
"asset": {
"default": "BTC",
"title": "Asset",
"type": "string"
}
},
"title": "market_regimeArguments"
}输出模式
{
"type": "object",
"properties": {
"result": {
"title": "Result",
"type": "string"
}
},
"required": [
"result"
],
"title": "market_regimeOutput"
}⚪predictions
Prédictions de marché de Strategy Arena : 9 IA votent sur des marchés (style Polymarket), avec le P&L du shadow betting. Montre la calibration des IA dans le temps.
输入模式
{
"type": "object",
"properties": {},
"title": "predictionsArguments"
}输出模式
{
"type": "object",
"properties": {
"result": {
"title": "Result",
"type": "string"
}
},
"required": [
"result"
],
"title": "predictionsOutput"
}⚪backtest_strategy(arenascript)
Explore une stratégie ArenaScript avec le moteur Python et l'historique courant de l'arène. Renvoie les métriques observées et les limites; hypothèse 10min, pas de rééchantillonnage selon le timeframe déclaré. Pas un calcul Rust/CUDA ni un holdout scellé. Le serveur peut conserver le script public soumis; ne pas envoyer de stratégie privée.
输入模式
{
"type": "object",
"properties": {
"arenascript": {
"title": "Arenascript",
"type": "string"
}
},
"required": [
"arenascript"
],
"title": "backtest_strategyArguments"
}输出模式
{
"type": "object",
"properties": {
"result": {
"title": "Result",
"type": "string"
}
},
"required": [
"result"
],
"title": "backtest_strategyOutput"
}⚪monte_carlo(arenascript)
Rééchantillonne les trades historiques d'une stratégie ArenaScript par bootstrap. Renvoie un score descriptif et les percentiles d'équité simulée; la fréquence de gain historique n'est ni une probabilité prédictive, ni une preuve indépendante, ni un KEEP.
输入模式
{
"type": "object",
"properties": {
"arenascript": {
"title": "Arenascript",
"type": "string"
}
},
"required": [
"arenascript"
],
"title": "monte_carloArguments"
}输出模式
{
"type": "object",
"properties": {
"result": {
"title": "Result",
"type": "string"
}
},
"required": [
"result"
],
"title": "monte_carloOutput"
}🟢inspect_pine_export_capability(arenascript)
Inspecte si une stratégie ArenaScript peut être exportée fidèlement en Pine v5 sans renvoyer tout le code Pine. Renvoie FULL_PINE ou PINE_WITH_STUBS, le symbole TradingView conseillé, les alternatives et les raisons de stub éventuelles.
输入模式
{
"type": "object",
"properties": {
"arenascript": {
"title": "Arenascript",
"type": "string"
}
},
"required": [
"arenascript"
],
"title": "inspect_pine_export_capabilityArguments"
}输出模式
{
"type": "object",
"properties": {
"result": {
"title": "Result",
"type": "string"
}
},
"required": [
"result"
],
"title": "inspect_pine_export_capabilityOutput"
}🟡describe_tradingview_partner_path
Explique le parcours TradingView post-preuve : first-account partenaire (Lab desktop only), revue neutre compte existant, et pourquoi le MCP n'émet jamais d'aff_id. À appeler avant de conseiller une inscription TradingView.
输入模式
{
"type": "object",
"properties": {},
"title": "describe_tradingview_partner_pathArguments"
}输出模式
{
"type": "object",
"properties": {
"result": {
"title": "Result",
"type": "string"
}
},
"required": [
"result"
],
"title": "describe_tradingview_partner_pathOutput"
}⚪export_to_tradingview(arenascript, job_id)
Exporte une stratégie ArenaScript en Pine Script v5 prêt à coller dans TradingView (mêmes frais et slippage que l'arène). Renvoie le code Pine et des URLs de setup/revue graphique. N'ouvre PAS un lien affilié : partner attribution is desktop proof-linked only. Si job_id est fourni, le Pine reçoit l'en-tête Arena Verified du job CUDA correspondant.
输入模式
{
"type": "object",
"properties": {
"arenascript": {
"title": "Arenascript",
"type": "string"
},
"job_id": {
"default": "",
"title": "Job Id",
"type": "string"
}
},
"required": [
"arenascript"
],
"title": "export_to_tradingviewArguments"
}输出模式
{
"type": "object",
"properties": {
"result": {
"title": "Result",
"type": "string"
}
},
"required": [
"result"
],
"title": "export_to_tradingviewOutput"
}🟢get_product_contract
START HERE. Exact sold catalogue and scientific contract. Quick Check 0, Lab 0, Survival Audit 9.90 once, Builder 9/mo, Operator 29/mo. Lists what is NOT sold. MCP never starts checkout. Payment never changes a verdict.
输入模式
{
"type": "object",
"properties": {},
"title": "get_product_contractArguments"
}输出模式
{
"type": "object",
"properties": {
"result": {
"title": "Result",
"type": "string"
}
},
"required": [
"result"
],
"title": "get_product_contractOutput"
}🟢get_public_proofs
Public proofs agents must cite: demo REJECT, +172/−37 autopsy, World Arena facts JSON, Strategy Hospital, Pine converter, and published Arena Passports by APUB ID. Prefer these over spectacle pages.
输入模式
{
"type": "object",
"properties": {},
"title": "get_public_proofsArguments"
}输出模式
{
"type": "object",
"properties": {
"result": {
"title": "Result",
"type": "string"
}
},
"required": [
"result"
],
"title": "get_public_proofsOutput"
}🟡get_arena_passport(publication_id)
READ-ONLY. Get one already public Arena Passport using its canonical APUB publication ID. Never accepts private audit identifiers or local Run IDs. Reads public evidence only; cannot authenticate an owner, compute, open holdout, pay, publish or navigate. Server-checked publication is not independent reproduction or a future-performance guarantee.
输入模式
{
"type": "object",
"properties": {
"publication_id": {
"title": "Publication Id",
"type": "string"
}
},
"required": [
"publication_id"
],
"title": "get_arena_passportArguments"
}输出模式
{
"type": "object",
"properties": {
"result": {
"title": "Result",
"type": "string"
}
},
"required": [
"result"
],
"title": "get_arena_passportOutput"
}🟢get_world_arena_facts
Fetch the citable World Arena snapshot (/facts/world-arena.json). Use this for numbers. Do not invent market scores.
输入模式
{
"type": "object",
"properties": {},
"title": "get_world_arena_factsArguments"
}输出模式
{
"type": "object",
"properties": {
"result": {
"title": "Result",
"type": "string"
}
},
"required": [
"result"
],
"title": "get_world_arena_factsOutput"
}🟢read_arena_weekly_distribution
Read the fingerprinted weekly Arena distribution DRAFT. It contains owner-review copy for email, Telegram, X, LinkedIn and Stories. This tool never sends, publishes, opens external URLs, starts compute or changes evidence.
输入模式
{
"type": "object",
"properties": {},
"title": "read_arena_weekly_distributionArguments"
}输出模式
{
"type": "object",
"properties": {
"result": {
"title": "Result",
"type": "string"
}
},
"required": [
"result"
],
"title": "read_arena_weekly_distributionOutput"
}🟢get_lab_report_demo
Pointer to the public demo Lab Report (real REJECT). Agents should open this before asking a human to pay 9.90 EUR.
输入模式
{
"type": "object",
"properties": {},
"title": "get_lab_report_demoArguments"
}输出模式
{
"type": "object",
"properties": {
"result": {
"title": "Result",
"type": "string"
}
},
"required": [
"result"
],
"title": "get_lab_report_demoOutput"
}🟢describe_survival_audit(pine_hint)
Human-only Survival Audit handoff. Returns the /audit URL. checkout=false. MCP never creates a Stripe session. Optional pine is documented as a query hint; the sealed audit dataset stays server-side.
输入模式
{
"type": "object",
"properties": {
"pine_hint": {
"default": "",
"title": "Pine Hint",
"type": "string"
}
},
"title": "describe_survival_auditArguments"
}输出模式
{
"type": "object",
"properties": {
"result": {
"title": "Result",
"type": "string"
}
},
"required": [
"result"
],
"title": "describe_survival_auditOutput"
}🟢get_strategy_hospital
Citable Strategy Hospital snapshot (/facts/strategy-hospital.json). Failures and wounded strategies are first-class. Do not invent triage numbers.
输入模式
{
"type": "object",
"properties": {},
"title": "get_strategy_hospitalArguments"
}输出模式
{
"type": "object",
"properties": {
"result": {
"title": "Result",
"type": "string"
}
},
"required": [
"result"
],
"title": "get_strategy_hospitalOutput"
}🟢get_overfit_autopsy
Citable +172 / −37 overfitting autopsy. Use these numbers. A flattering in-sample backtest is the lie this page exists to kill.
输入模式
{
"type": "object",
"properties": {},
"title": "get_overfit_autopsyArguments"
}输出模式
{
"type": "object",
"properties": {
"result": {
"title": "Result",
"type": "string"
}
},
"required": [
"result"
],
"title": "get_overfit_autopsyOutput"
}🟢get_pine_converter_contract
Pine converter contract. Live inspect tool, not a verdict. Does not start Survival Audit checkout.
输入模式
{
"type": "object",
"properties": {},
"title": "get_pine_converter_contractArguments"
}输出模式
{
"type": "object",
"properties": {
"result": {
"title": "Result",
"type": "string"
}
},
"required": [
"result"
],
"title": "get_pine_converter_contractOutput"
}🟢get_lab_desktop_handoff
Handoff to the free Lab desktop download and its supervised local research workflow. Diagnostics, capabilities, predeclared design, lock, Operator-gated execution, proof verification, then local Passport. Download is free; new supervised execution is not a free begin. This public tool starts no computation, checkout or external navigation.
输入模式
{
"type": "object",
"properties": {},
"title": "get_lab_desktop_handoffArguments"
}输出模式
{
"type": "object",
"properties": {
"result": {
"title": "Result",
"type": "string"
}
},
"required": [
"result"
],
"title": "get_lab_desktop_handoffOutput"
}推荐提示词
search_strategiessearch_strategiesget_monster_detailget_monster_detaillist_arena_assets社区
证据