xyz.noonbarbari/backtesting

Est-ce que xyz.noonbarbari/backtesting est sûr ?

Au dernier audit MCP Hub, le serveur MCP « xyz.noonbarbari/backtesting » 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 11 outils

• check_overfitting≈ 309 tokens

  Compute the Deflated Sharpe Ratio (Bailey & Lopez de Prado 2014) for YOUR OWN backtest: given its annualised Sharpe, length, and how many strategy variants you tried before selecting it, returns the probability the result is real skill rather than selection luck, the luck bar it must clear, and a plain verdict. Works on any backtest, not just ours.

  Paramètres, retour & exemple (6)

  Paramètres

  • skew · number · optionnel
    Skewness of the return series (default 0).
  • sharpe · number · requis
    Annualised Sharpe ratio of the selected backtest.
  • kurtosis · number · optionnel
    Non-excess kurtosis of returns (Gaussian = 3, the default).
  • n_trials · number · requis
    How many strategy/parameter variants were tried before picking this one.
  • timeframe · string · optionnel · 1h | 4h | 1d | 1w
    Bar timeframe of the returns (default 1d).
  • length_days · number · requis
    Length of the backtest in calendar days.

  Exemple d'appel

  {"name": "check_overfitting", "arguments": {"sharpe": 1, "n_trials": 1, "length_days": 1}}

  Exemple de retour

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

• compare_strategies≈ 172 tokens

  Head-to-head comparison of two strategy templates from real monthly engine runs across ~50 coins: per-coin win count, median out-of-sample Sharpe, survival counts, median return and drawdown. Use strategy names from list_strategies (e.g. 'super_trend', 'ema_crossover').

  Paramètres, retour & exemple (2)

  Paramètres

  • strategy_a · string · requis
    First strategy name, e.g. super_trend
  • strategy_b · string · requis
    Second strategy name, e.g. ema_crossover

  Exemple d'appel

  {"name": "compare_strategies", "arguments": {"strategy_a": "texte", "strategy_b": "texte"}}

  Exemple de retour

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

• get_buy_hold≈ 122 tokens

  What a $1,000 buy of a coin on Jan 1 of each available year would be worth today — ROI, peak value and date, and the maximum drawdown endured along the way. Real Binance data, refreshed daily.

  Paramètres, retour & exemple (1)

  Paramètres

  • coin · string · requis
    Lower-case ticker, e.g. btc, eth, sol.

  Exemple d'appel

  {"name": "get_buy_hold", "arguments": {"coin": "texte"}}

  Exemple de retour

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

• get_coin_signals≈ 151 tokens

  Today's daily-bar indicator readings for crypto coins, computed by a real backtesting engine from Binance closes: price, RSI-14, MACD state, SMA 50/200 posture, SuperTrend, Bollinger position, ATR volatility, 52-week range. Pass a coin ticker (e.g. 'btc') for one coin, or omit for the whole 50-coin board.

  Paramètres, retour & exemple (1)

  Paramètres

  • coin · string · optionnel
    Lower-case ticker, e.g. btc, eth, sol. Omit for all coins.

  Exemple d'appel

  {"name": "get_coin_signals", "arguments": {"coin": "texte"}}

  Exemple de retour

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

• get_dca≈ 236 tokens

  Dollar-cost-averaging outcome for a coin: what buying a fixed dollar amount on a schedule (weekly or monthly) since a start date would be worth today — total invested, units, average cost, current value and ROI — plus the lump-sum comparison and the worst drawdown endured. Real Binance closes, refreshed daily.

  Paramètres, retour & exemple (4)

  Paramètres

  • coin · string · requis
    Lower-case ticker, e.g. btc, eth, sol.
  • amount · number · optionnel
    USD invested per purchase (default 100).
  • frequency · string · optionnel · weekly | monthly
    Purchase cadence (default weekly).
  • start_date · string · optionnel
    ISO date to start buying from, e.g. 2021-01-01 (optional; default = full history).

  Exemple d'appel

  {"name": "get_dca", "arguments": {"coin": "texte"}}

  Exemple de retour

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

• get_overfitting_index≈ 117 tokens

  The Crypto Overfitting Index: the monthly share (%) of default-parameter strategy configurations (10 templates × 50 coins) whose out-of-sample Sharpe turned negative — how much of what backtests promise fails on unseen data. Returns the current reading and full history.

  Paramètres, retour & exemple (0)

  Exemple d'appel

  {"name": "get_overfitting_index", "arguments": {}}

  Exemple de retour

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

• list_strategies≈ 93 tokens

  List the strategy templates available for backtesting and comparison (name, title, one-line description). Use the returned `name` value as the strategy identifier in other tools.

  Paramètres, retour & exemple (0)

  Exemple d'appel

  {"name": "list_strategies", "arguments": {}}

  Exemple de retour

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

• query_dataset≈ 190 tokens

  Query our open 11,440-run curve-fitting study (10 strategy templates x 20 coins, 70/30 in-sample/out-of-sample split). Returns the headline overfitting stats and the tuned picks matching an optional template and/or coin filter — each with in-sample vs out-of-sample Sharpe, the Sharpe haircut, and the in-sample-to-out-of-sample parameter rank correlation.

  Paramètres, retour & exemple (2)

  Paramètres

  • coin · string · optionnel
    Ticker, e.g. btc (optional). Omit for all coins.
  • template · string · optionnel
    Strategy name, e.g. super_trend (optional). Omit for all templates.

  Exemple d'appel

  {"name": "query_dataset", "arguments": {"coin": "texte", "template": "texte"}}

  Exemple de retour

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

• run_backtest≈ 204 tokens

  Run a real backtest of a strategy template on BTC/USDT from a start date (public what-if engine; may take up to a minute on a cache miss; rate-limited). Returns net return, max drawdown, trade count, a robustness score with an overfitting verdict, and a shareable result URL.

  Paramètres, retour & exemple (3)

  Paramètres

  • strategy · string · requis
    Strategy name from list_strategies, e.g. super_trend
  • start_date · string · requis
    ISO date, e.g. 2022-01-01 (2020-01-01 or later)
  • starting_cash · number · optionnel
    Starting balance in USD (default 10000, max 1000000)

  Exemple d'appel

  {"name": "run_backtest", "arguments": {"strategy": "texte", "start_date": "texte"}}

  Exemple de retour

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

• search_answers≈ 133 tokens

  Search Noon Barbari's Q&A knowledge base of direct, data-grounded answers about backtesting, overfitting, validation, indicators, risk management and crypto markets. Returns the top matching questions with their full answers.

  Paramètres, retour & exemple (1)

  Paramètres

  • query · string · requis
    Free-text query, e.g. 'why do backtests fail'

  Exemple d'appel

  {"name": "search_answers", "arguments": {"query": "texte"}}

  Exemple de retour

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

• search_glossary≈ 149 tokens

  Search Noon Barbari's trading glossary for a plain-language definition of an indicator, metric or concept (RSI, MACD, Sharpe ratio, drawdown, walk-forward, overfitting, and 60+ more). Returns the top matching terms with a short definition, the full explanation, and a link.

  Paramètres, retour & exemple (1)

  Paramètres

  • query · string · requis
    A term or question, e.g. 'deflated sharpe' or 'what is RSI'.

  Exemple d'appel

  {"name": "search_glossary", "arguments": {"query": "texte"}}

  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://noonbarbari.xyz/mcp