Noon Barbari Backtesting

Crypto backtesting tools: real backtests with robustness verdicts, daily signals and market data.

我该使用它吗

质量与安全性

A
描述质量
100%
模式完整度
85%
命名质量
98%
投毒风险
100%
权限匹配度
100%
协议合规性
100%

基于对工具定义和协议合规性的自动分析。

上下文开销

~1,720token 数(工具定义)
~799 B典型响应大小
对注意力有中等影响(占 128k 上下文窗口的 1.34%)

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": {
    "backtesting": {
      "url": "https://noonbarbari.xyz/mcp"
    }
  }
}

远程端点

https://noonbarbari.xyz/mcpstreamable-http

它能做什么

工具清单

工具(11)

🟢 只读🟡 写入🔴 删除⚪ 未知
🟢list_strategies

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.

输入模式

{
  "type": "object",
  "properties": {},
  "additionalProperties": false
}
🟢get_coin_signals(coin)

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.

输入模式

{
  "type": "object",
  "properties": {
    "coin": {
      "type": "string",
      "description": "Lower-case ticker, e.g. btc, eth, sol. Omit for all coins."
    }
  },
  "additionalProperties": false
}
🟢get_buy_hold(coin)

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.

输入模式

{
  "type": "object",
  "properties": {
    "coin": {
      "type": "string",
      "description": "Lower-case ticker, e.g. btc, eth, sol."
    }
  },
  "required": [
    "coin"
  ],
  "additionalProperties": false
}
🟢get_overfitting_index

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.

输入模式

{
  "type": "object",
  "properties": {},
  "additionalProperties": false
}
🟢compare_strategies(strategy_a, strategy_b)

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').

输入模式

{
  "type": "object",
  "properties": {
    "strategy_a": {
      "type": "string",
      "description": "First strategy name, e.g. super_trend"
    },
    "strategy_b": {
      "type": "string",
      "description": "Second strategy name, e.g. ema_crossover"
    }
  },
  "required": [
    "strategy_a",
    "strategy_b"
  ],
  "additionalProperties": false
}
🟢search_answers(query)

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.

输入模式

{
  "type": "object",
  "properties": {
    "query": {
      "type": "string",
      "description": "Free-text query, e.g. 'why do backtests fail'"
    }
  },
  "required": [
    "query"
  ],
  "additionalProperties": false
}
⚪run_backtest(strategy, start_date, starting_cash)

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.

输入模式

{
  "type": "object",
  "properties": {
    "strategy": {
      "type": "string",
      "description": "Strategy name from list_strategies, e.g. super_trend"
    },
    "start_date": {
      "type": "string",
      "description": "ISO date, e.g. 2022-01-01 (2020-01-01 or later)"
    },
    "starting_cash": {
      "type": "number",
      "description": "Starting balance in USD (default 10000, max 1000000)"
    }
  },
  "required": [
    "strategy",
    "start_date"
  ],
  "additionalProperties": false
}
🟢get_dca(coin, amount, frequency, start_date)

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.

输入模式

{
  "type": "object",
  "properties": {
    "coin": {
      "type": "string",
      "description": "Lower-case ticker, e.g. btc, eth, sol."
    },
    "amount": {
      "type": "number",
      "description": "USD invested per purchase (default 100)."
    },
    "frequency": {
      "type": "string",
      "enum": [
        "weekly",
        "monthly"
      ],
      "description": "Purchase cadence (default weekly)."
    },
    "start_date": {
      "type": "string",
      "description": "ISO date to start buying from, e.g. 2021-01-01 (optional; default = full history)."
    }
  },
  "required": [
    "coin"
  ],
  "additionalProperties": false
}
🟢check_overfitting(sharpe, timeframe, length_days, n_trials, skew, ...)

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.

输入模式

{
  "type": "object",
  "properties": {
    "sharpe": {
      "type": "number",
      "description": "Annualised Sharpe ratio of the selected backtest."
    },
    "timeframe": {
      "type": "string",
      "enum": [
        "1h",
        "4h",
        "1d",
        "1w"
      ],
      "description": "Bar timeframe of the returns (default 1d)."
    },
    "length_days": {
      "type": "number",
      "description": "Length of the backtest in calendar days."
    },
    "n_trials": {
      "type": "number",
      "description": "How many strategy/parameter variants were tried before picking this one."
    },
    "skew": {
      "type": "number",
      "description": "Skewness of the return series (default 0)."
    },
    "kurtosis": {
      "type": "number",
      "description": "Non-excess kurtosis of returns (Gaussian = 3, the default)."
    }
  },
  "required": [
    "sharpe",
    "length_days",
    "n_trials"
  ],
  "additionalProperties": false
}
🟢query_dataset(template, coin)

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.

输入模式

{
  "type": "object",
  "properties": {
    "template": {
      "type": "string",
      "description": "Strategy name, e.g. super_trend (optional). Omit for all templates."
    },
    "coin": {
      "type": "string",
      "description": "Ticker, e.g. btc (optional). Omit for all coins."
    }
  },
  "additionalProperties": false
}
🟢search_glossary(query)

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.

输入模式

{
  "type": "object",
  "properties": {
    "query": {
      "type": "string",
      "description": "A term or question, e.g. 'deflated sharpe' or 'what is RSI'."
    }
  },
  "required": [
    "query"
  ],
  "additionalProperties": false
}

社区

评价此服务器

证据

最近观测

已验证未记录版本11 个工具
已验证未记录版本11 个工具
已验证未记录版本11 个工具