Noon Barbari Backtesting

Official11 toolsLive

by noonbarbari

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

xyz.noonbarbari/backtesting MCP Server

The xyz.noonbarbari/backtesting MCP server provides crypto backtesting capabilities, including real backtests, robustness verdicts, daily signals, and market data. It is designed to support analysis workflows where backtest results and related signals are derived from market inputs.

🛠️ Key Features

Real backtests
Robustness verdicts
Daily signals
Market data
11 tools available

🚀 Use Cases

Evaluating crypto trading strategies via real backtests
Assessing robustness through robustness verdicts
Generating or consuming daily signals from market data
Using market data as an input source for backtesting workflows

⚡ Developer Benefits

Structured tool set (11 tools)
Backtest outputs tied to robustness verdicts
Availability of daily signals and market data for iterative testing

⚠️ Limitations

Scope is limited to “crypto backtesting” and the explicitly listed outputs (robustness verdicts, daily signals, market data).

Captured live from the server via tools/list.

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.

Parameters

No parameters.

Raw schema

{
  "type": "object",
  "properties": {},
  "additionalProperties": false
}

get_coin_signals

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.

Parameters1

coin

string

optional

Lower-case ticker, e.g. btc, eth, sol. Omit for all coins.

Raw schema

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

get_buy_hold

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.

Parameters1

coin

string

required

Lower-case ticker, e.g. btc, eth, sol.

Raw schema

{
  "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.

Parameters

No parameters.

Raw schema

{
  "type": "object",
  "properties": {},
  "additionalProperties": false
}

compare_strategies

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').

Parameters2

strategy_a	string	required	First strategy name, e.g. super_trend
strategy_b	string	required	Second strategy name, e.g. ema_crossover

Raw schema

{
  "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

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.

Parameters1

query

string

required

Free-text query, e.g. 'why do backtests fail'

Raw schema

{
  "type": "object",
  "properties": {
    "query": {
      "type": "string",
      "description": "Free-text query, e.g. 'why do backtests fail'"
    }
  },
  "required": [
    "query"
  ],
  "additionalProperties": false
}

run_backtest

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.

Parameters3

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

Raw schema

{
  "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

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.

Parameters4

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

Raw schema

{
  "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

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.

Parameters6

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

Raw schema

{
  "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

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.

Parameters2

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

Raw schema

{
  "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

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.

Parameters1

query

string

required

A term or question, e.g. 'deflated sharpe' or 'what is RSI'.

Raw schema

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

Install

Tools (11)

list_strategiesget_coin_signalsget_buy_holdget_overfitting_indexcompare_strategiessearch_answersrun_backtestget_dca

Remote endpoint

Streamable HTTP

Hosted server - connect over the network, no local install.

url

https://noonbarbari.xyz/mcp

Add to VS Code Add to Cursor

claude_desktop_config.json

json

{
  "mcpServers": {
    "backtesting": {
      "command": "npx",
      "args": [
        "-y",
        "mcp-remote",
        "https://noonbarbari.xyz/mcp"
      ]
    }
  }
}

Desktop config is stdio-only; this bridges via mcp-remote. Native remote: Settings > Connectors.

xyz.noonbarbari/backtesting MCP Server

🛠️ Key Features

🚀 Use Cases

⚡ Developer Benefits

⚠️ Limitations

list_strategies

get_coin_signals

get_buy_hold

get_overfitting_index

compare_strategies

search_answers

run_backtest

get_dca

check_overfitting

query_dataset

search_glossary

Install

Remote endpoint

Related servers