strategy_grid_lookup

Backtest lookup: what one exact version of a strategy actually did. Buy-the-dip and the moving-average cross, every combination of their knobs, computed over nine years of real prices with the exchange's fees charged both ways — sixteen coins, three of which died. Give the coin and the numbers and you get the return, the trades, the worst drawdown, and what buying and holding did over the same window. Read from a file you can download.

Parameters9

coin	string	required	BTC, ETH, SOL, DOGE, PEPE, SRM… ticker or full pair. Ask with an unknown one and the answer lists the sixteen we hold.
family	string	optional	dip (buy when it falls) or cross (moving average crossover). Defaults to dip.
drop	number	optional	dip only: how far below its recent high to buy, in %.
target	number	optional	dip only: take profit, in %.
stop	number	optional	dip only: stop loss, in %.
hours	number	optional	dip only: give up after this many hours.
fast	number	optional	cross only: fast average.
slow	number	optional	cross only: slow average.
candles	string	optional	cross only: 1d or 4h.

Raw schema

{
  "type": "object",
  "properties": {
    "coin": {
      "type": "string",
      "description": "BTC, ETH, SOL, DOGE, PEPE, SRM… ticker or full pair. Ask with an unknown one and the answer lists the sixteen we hold."
    },
    "family": {
      "type": "string",
      "description": "dip (buy when it falls) or cross (moving average crossover). Defaults to dip."
    },
    "drop": {
      "type": "number",
      "description": "dip only: how far below its recent high to buy, in %."
    },
    "target": {
      "type": "number",
      "description": "dip only: take profit, in %."
    },
    "stop": {
      "type": "number",
      "description": "dip only: stop loss, in %."
    },
    "hours": {
      "type": "number",
      "description": "dip only: give up after this many hours."
    },
    "fast": {
      "type": "number",
      "description": "cross only: fast average."
    },
    "slow": {
      "type": "number",
      "description": "cross only: slow average."
    },
    "candles": {
      "type": "string",
      "description": "cross only: 1d or 4h."
    }
  },
  "required": [
    "coin"
  ],
  "description": "Which exact version of the strategy you want looked up."
}

overfitting_odds

Overfitting check: how many attempts plain chance needs to produce the track record you were shown. Give the wins, the losses and how many versions were tried: you get the exact binomial odds of one try reaching it, the odds once somebody shows you the best of N, and how many tries would make it an even bet. Arithmetic only — no market data, no model, no opinion. A 62% win rate over 100 trades is one thing on the first try, nothing on the fiftieth.

Parameters5

wins	number	required	Winning trades.
losses	number	optional	Losing trades. Give this or trades.
trades	number	required	Total trades.
tries	number	optional	How many versions were tried before this one was shown to you. Defaults to 1, which is almost never true.
baseline	number	optional	Probability a single trade wins by chance. Defaults to 0.5.

Raw schema

{
  "type": "object",
  "properties": {
    "wins": {
      "type": "number",
      "description": "Winning trades."
    },
    "losses": {
      "type": "number",
      "description": "Losing trades. Give this or trades."
    },
    "trades": {
      "type": "number",
      "description": "Total trades."
    },
    "tries": {
      "type": "number",
      "description": "How many versions were tried before this one was shown to you. Defaults to 1, which is almost never true."
    },
    "baseline": {
      "type": "number",
      "description": "Probability a single trade wins by chance. Defaults to 0.5."
    }
  },
  "required": [
    "wins",
    "trades"
  ],
  "description": "The track record you were shown, and how much searching went into finding it."
}

leverage_survival

What a leveraged trade actually did, opened on every single day of the history instead of the one day that worked. Give coin, side, leverage and holding period: you get the share of those days that ended liquidated, the median outcome, the best day, and what the same coin did with no leverage at all. Real perpetual tape, with the funding that was actually paid charged daily and eating into margin. Coins that blew up included.

Parameters4

coin	string	required	Ticker or full pair. An unknown one comes back with the list we hold and the ones we do not.
side	string	optional	long or short. Defaults to long.
leverage	number	required	2, 3, 5, 10, 20, 25, 50 or 100.
days	number	required	How long it is held: 1, 7, 30 or 90.

Raw schema

{
  "type": "object",
  "properties": {
    "coin": {
      "type": "string",
      "description": "Ticker or full pair. An unknown one comes back with the list we hold and the ones we do not."
    },
    "side": {
      "type": "string",
      "description": "long or short. Defaults to long."
    },
    "leverage": {
      "type": "number",
      "description": "2, 3, 5, 10, 20, 25, 50 or 100."
    },
    "days": {
      "type": "number",
      "description": "How long it is held: 1, 7, 30 or 90."
    }
  },
  "required": [
    "coin",
    "leverage",
    "days"
  ],
  "description": "The leveraged trade you want opened on every day there has been."
}

drawdown_check

Drawdown check: what it cost to collect the return you were shown. The coin is bought at the close of every day of its history and held for the period you name: you get the drawdown from the entry before the period was out, the share of starts that fell 30% and 50%, the days spent under water, how it ended — and, among the starts that ended in profit, the drawdown they sat through first. Spot tape, no fees, coins that died included.

Parameters2

coin	string	required	Ticker or full pair. An unknown one comes back with the list we hold and the ones left out.
days	number	required	How long it is held: 30, 90, 365 or 730.

Raw schema

{
  "type": "object",
  "properties": {
    "coin": {
      "type": "string",
      "description": "Ticker or full pair. An unknown one comes back with the list we hold and the ones left out."
    },
    "days": {
      "type": "number",
      "description": "How long it is held: 30, 90, 365 or 730."
    }
  },
  "required": [
    "coin",
    "days"
  ],
  "description": "The hold you want opened on every day there has been."
}

diversification_check

Diversification check: how many independent bets a basket of coins really is. Give the coins (and optionally the window: 90, 365 or 730 days): you get the average correlation between the pairs on real daily returns, the number of independent bets it works out to, each coin's correlation with bitcoin — and what the equal-weight basket did on the days bitcoin closed 3% or more down: how often it fell too, by how much, and its worst such day. Dead coins included.

Parameters2

coins	array	required	Tickers or full pairs, e.g. ["BTC", "ETH", "SOL"]. A comma-separated string also works. One we do not hold comes back with the list.
days	number	required	Window ending on the last day of the data: 90, 365 or 730. Defaults to 365.

Raw schema

{
  "type": "object",
  "properties": {
    "coins": {
      "type": "array",
      "items": {
        "type": "string"
      },
      "description": "Tickers or full pairs, e.g. [\"BTC\", \"ETH\", \"SOL\"]. A comma-separated string also works. One we do not hold comes back with the list."
    },
    "days": {
      "type": "number",
      "description": "Window ending on the last day of the data: 90, 365 or 730. Defaults to 365."
    }
  },
  "required": [
    "coins",
    "days"
  ],
  "description": "The basket you want measured."
}

averaging_in_check

Whether spreading the entry would have helped, measured. One amount into a coin over a window (90, 365 or 730 days): all of it on day one, or equal instalments weekly or monthly. Both start the same day, move the same money and are valued on the same day, started on every day of the history. You get how often spreading ended ahead, the middle result of each, and the worst start day of each — which is what spreading actually buys and the half nobody shows. Spot tape, no fees, dead coins included.

Parameters3

coin	string	required	Ticker or full pair. An unknown one comes back with the list we hold and the ones left out.
days	number	required	The window, in days: 90, 365 or 730.
instalments	string	required	How often a slice goes in: weekly or monthly. Defaults to weekly.

Raw schema

{
  "type": "object",
  "properties": {
    "coin": {
      "type": "string",
      "description": "Ticker or full pair. An unknown one comes back with the list we hold and the ones left out."
    },
    "days": {
      "type": "number",
      "description": "The window, in days: 90, 365 or 730."
    },
    "instalments": {
      "type": "string",
      "description": "How often a slice goes in: weekly or monthly. Defaults to weekly."
    }
  },
  "required": [
    "coin",
    "days",
    "instalments"
  ],
  "description": "The coin and the window you want compared."
}

stop_loss_check

Whether a stop-loss would have helped, measured. The same buy of a coin, held 30, 90, 365 or 730 days, with a stop 5, 10, 15, 20 or 30% below the entry and without one, started on every day of the history. The stop fires on the day's low, not its close, and fees are charged to both. You get how often it fired, how often it sold a buy that would have ended in profit, and the worst case of each. Spot tape, dead coins included.

Parameters3

coin	string	required	Ticker or full pair. An unknown one comes back with the list we hold and the ones left out.
days	number	required	Holding period in days: 30, 90, 365 or 730.
stop	number	required	How far below the entry, in percent: 5, 10, 15, 20 or 30. 0.05 is read as 5.

Raw schema

{
  "type": "object",
  "properties": {
    "coin": {
      "type": "string",
      "description": "Ticker or full pair. An unknown one comes back with the list we hold and the ones left out."
    },
    "days": {
      "type": "number",
      "description": "Holding period in days: 30, 90, 365 or 730."
    },
    "stop": {
      "type": "number",
      "description": "How far below the entry, in percent: 5, 10, 15, 20 or 30. 0.05 is read as 5."
    }
  },
  "required": [
    "coin",
    "days",
    "stop"
  ],
  "description": "The coin, how long you meant to hold, and the stop."
}

copy_trading_check

Whether copying the top traders works, measured. Accounts in the top 10% or 1% of Hyperliquid one month, by return or by dollar profit: how many were in the top again the next month, next to chance, how many fell to the bottom instead, and how many made money the month you would have copied them for, next to every active account. 4,000 accounts sampled at random, not today's leaders; about 30 month pairs.

Parameters2

ranked_by	string	required	return (default) or profit.
top_pct	number	required	10 (default) or 1. 0.1 is read as 10.

Raw schema

{
  "type": "object",
  "properties": {
    "ranked_by": {
      "type": "string",
      "description": "return (default) or profit."
    },
    "top_pct": {
      "type": "number",
      "description": "10 (default) or 1. 0.1 is read as 10."
    }
  },
  "required": [
    "ranked_by",
    "top_pct"
  ],
  "description": "Which ranking and which top group. Both optional."
}

leaderboard_rank_check

How much company a return has. Send a return (+340%) and a window (day, week, month or all time) and get how many accounts on Hyperliquid's whole public leaderboard did the same or better, out of how many traded, its percentile, and the median account next to it. Every row of the exchange's own table, refreshed daily; the denominator is the accounts that traded, not the ones that sat idle.

Parameters2

return_pct	number	required	In percent: 340 means +340%.
window	string	required	day, week, month (default) or allTime.

Raw schema

{
  "type": "object",
  "properties": {
    "return_pct": {
      "type": "number",
      "description": "In percent: 340 means +340%."
    },
    "window": {
      "type": "string",
      "description": "day, week, month (default) or allTime."
    }
  },
  "required": [
    "return_pct",
    "window"
  ],
  "description": "The return you were shown, and over what window."
}

calendar_check

'Uptober'. 'Mondays dip'. 'Sell in May'. Any calendar claim on 34 coins, measured against chance. With seven days one has to come first, so the answer is a permutation test: the SAME returns dealt out at random hundreds of times, and how often chance alone produces a bucket that good. Plus how many times the bucket really happened - October is 279 days of bitcoin but nine Octobers - and the round-trip cost. Nine years of daily candles.

Parameters2

coin	string	required	Ticker or full pair. An unknown one comes back with the list we hold and the ones left out.
calendar	string	required	day_of_week, month_of_year or hour_of_day. The hourly one exists for the 16 coins we hold hourly candles for.

Raw schema

{
  "type": "object",
  "properties": {
    "coin": {
      "type": "string",
      "description": "Ticker or full pair. An unknown one comes back with the list we hold and the ones left out."
    },
    "calendar": {
      "type": "string",
      "description": "day_of_week, month_of_year or hour_of_day. The hourly one exists for the 16 coins we hold hourly candles for."
    }
  },
  "required": [
    "coin",
    "calendar"
  ],
  "description": "The coin and which calendar: weekday, month or hour."
}

best_days_check

The 'miss the ten best days and you get nothing' claim, measured on both sides. The same window of a coin lived four ways: all of it, without its N best days, without its N worst days, and without either, from every start day of the history. You also get how many of those best days landed within a week of a worst one, which is what decides whether the claim means anything. Backtest on spot daily candles, dead coins included.

Parameters3

coin	string	required	Ticker or full pair. An unknown one comes back with the list we hold and the ones left out.
days	number	required	Window in days: 90, 365 or 730.
best_days	number	required	How many days are missed: 1, 5, 10 or 20. Defaults to 10, the number in the claim.

Raw schema

{
  "type": "object",
  "properties": {
    "coin": {
      "type": "string",
      "description": "Ticker or full pair. An unknown one comes back with the list we hold and the ones left out."
    },
    "days": {
      "type": "number",
      "description": "Window in days: 90, 365 or 730."
    },
    "best_days": {
      "type": "number",
      "description": "How many days are missed: 1, 5, 10 or 20. Defaults to 10, the number in the claim."
    }
  },
  "required": [
    "coin",
    "days",
    "best_days"
  ],
  "description": "The coin, the window, and how many days you would miss."
}

coin_comparison

Two or three coins side by side, every check at once: for each, how often a buy fell 30% or more before the window was out and where the middle one ended, how often a leveraged month ended with nothing, whether spreading the entry won, how often a stop-loss sold a buy that ended in profit, and how much it moves with bitcoin. Nothing is ranked and no coin is called better. Spot and perpetual tapes, fees charged.

Parameters3

coins	string	required	Two or three tickers, comma-separated: BTC,ETH,SOL. Kept in the order sent.
days	number	required	90, 365 (default) or 730.
leverage	number	required	For the leverage row. Default 25.

Raw schema

{
  "type": "object",
  "properties": {
    "coins": {
      "type": "string",
      "description": "Two or three tickers, comma-separated: BTC,ETH,SOL. Kept in the order sent."
    },
    "days": {
      "type": "number",
      "description": "90, 365 (default) or 730."
    },
    "leverage": {
      "type": "number",
      "description": "For the leverage row. Default 25."
    }
  },
  "required": [
    "coins",
    "days",
    "leverage"
  ],
  "description": "The coins, and optionally the window and the leverage."
}

Regime

xyz.regimetoken/regime Model Context Protocol (MCP) Server

🛠️ Key Features

🚀 Use Cases

⚡ Developer Benefits

⚠️ Limitations

strategy_grid_lookup

overfitting_odds

leverage_survival

drawdown_check

diversification_check

averaging_in_check

stop_loss_check

copy_trading_check

leaderboard_rank_check

calendar_check

best_days_check

coin_comparison

Install

Remote endpoint

Related servers