regimen
Tells you whether a trading strategy's edge is distinguishable from luck.
我該用這個嗎
品質與安全性
A
根據工具定義與協定合規性的自動化分析。
上下文成本
~3,485Token（工具定義）
~9.0 KB典型回應大小
顯著的注意力影響（128k 上下文的 2.72%）
這是每次將伺服器的工具載入模型上下文時所消耗的約略 token 數量。數量越高，可用於其他工作的注意力就越少。
安裝
一鍵安裝
將以下內容加入你的 `claude_desktop_config.json` 檔案：
{
"mcpServers": {
"regimen": {
"url": "https://regimen-nu.vercel.app/mcp"
}
}
}遠端端點
https://regimen-nu.vercel.app/mcpstreamable-http它能做什麼
工具清單
工具（4）
🟢 唯讀🟡 寫入🔴 刪除⚪ 未知
🟢regimen_describe_factors
List the market-condition factors Regimen slices performance by, with units, the upstream operation each is read from, and how it is bucketed. Call this when you need to know which factor keys exist or how to explain a bucket to a user. Takes no arguments, reaches no network, never changes.
輸入結構描述
{
"type": "object",
"properties": {},
"$schema": "https://json-schema.org/draft/2020-12/schema"
}輸出結構描述
{
"type": "object",
"properties": {
"factors": {
"type": "array",
"items": {
"type": "object",
"properties": {
"key": {
"type": "string"
},
"label": {
"type": "string"
},
"unit": {
"type": "string"
},
"description": {
"type": "string"
},
"source": {
"type": "string"
},
"pointInTime": {
"type": "boolean"
}
},
"required": [
"key",
"label",
"unit",
"description",
"source",
"pointInTime"
],
"additionalProperties": false
}
},
"note": {
"type": "string"
}
},
"required": [
"factors",
"note"
],
"$schema": "https://json-schema.org/draft/2020-12/schema",
"additionalProperties": false
}🟢regimen_evaluate_track_record(selector, benchmarkSharpe, confidence, trialSharpes, detail)
Answer whether a trading strategy’s measured performance is distinguishable from luck. Returns the Probabilistic Sharpe Ratio (the probability the true Sharpe beats a benchmark, corrected for sample length, skew and fat tails), a bootstrap confidence interval, and the Minimum Track Record Length — how long the record would have to run before the claim could be made at all. Use this whenever someone quotes a Sharpe ratio, a win rate or a return and you need to know whether the number means anything. It will frequently say the evidence is too thin; that is the intended answer, not a failure.
輸入結構描述
{
"type": "object",
"properties": {
"selector": {
"type": "object",
"properties": {
"source": {
"type": "string",
"enum": [
"olaxbt-nexus",
"inline"
],
"description": "olaxbt-nexus analyses the strategy bound to this connection’s API key. inline analyses an equity curve you supply directly, from any venue or backtest."
},
"symbol": {
"description": "For olaxbt-nexus: the market the strategy trades, used for point-in-time reads. Default BTC/USDT.",
"type": "string",
"minLength": 3,
"maxLength": 32
},
"trackRecord": {
"description": "Required when source is inline.",
"type": "object",
"properties": {
"label": {
"default": "inline-track-record",
"description": "A name for this track record, echoed back in results. Do not put anything sensitive here.",
"type": "string",
"minLength": 1,
"maxLength": 80
},
"equity": {
"minItems": 2,
"maxItems": 10000,
"type": "array",
"items": {
"type": "object",
"properties": {
"t": {
"description": "Epoch milliseconds, epoch seconds, or an ISO 8601 timestamp. UTC is assumed.",
"type": [
"number",
"string"
]
},
"equity": {
"type": "number",
"exclusiveMinimum": 0,
"description": "Account equity at that instant, in any single consistent unit."
}
},
"required": [
"t",
"equity"
]
},
"description": "The equity curve, one point per period. Order does not matter; it is sorted by timestamp."
},
"trades": {
"maxItems": 20000,
"type": "array",
"items": {
"type": "object",
"properties": {
"symbol": {
"type": "string",
"minLength": 1,
"maxLength": 64
},
"pnl": {
"type": "number",
"description": "Realised profit or loss for the closed trade, in the equity unit."
},
"exitedAt": {
"type": [
"number",
"string"
]
},
"entryPrice": {
"type": "number"
},
"exitPrice": {
"type": "number"
},
"holdingBars": {
"type": "integer",
"minimum": 0,
"maximum": 9007199254740991
},
"exitReason": {
"type": "string",
"maxLength": 120
}
},
"required": [
"pnl"
]
}
},
"reportedSharpe": {
"description": "Optional. The Sharpe ratio you believe this track record has, so Regimen can contrast it with its own.",
"type": "number"
}
},
"required": [
"equity"
]
}
},
"required": [
"source"
],
"description": "Which track record to analyse."
},
"benchmarkSharpe": {
"default": 0,
"description": "Per-period Sharpe the record must beat. 0 asks only whether there is any edge at all.",
"type": "number"
},
"confidence": {
"default": 0.95,
"type": "number",
"exclusiveMinimum": 0.5,
"exclusiveMaximum": 1
},
"trialSharpes": {
"description": "Per-period Sharpe ratios of other configurations tried for this strategy. Supplying them enables the Deflated Sharpe Ratio, which discounts the headline for how many variants were tested before this one was reported.",
"maxItems": 500,
"type": "array",
"items": {
"type": "number"
}
},
"detail": {
"default": "concise",
"description": "concise returns the verdict, the headline statistics and the reasoning — enough to answer a user. full adds every bucket, every dropped point and the complete provenance list, and is much larger.",
"type": "string",
"enum": [
"concise",
"full"
]
}
},
"required": [
"selector"
],
"$schema": "https://json-schema.org/draft/2020-12/schema"
}輸出結構描述
{
"type": "object",
"properties": {
"label": {
"type": "string"
},
"sourceId": {
"type": "string"
},
"verdict": {
"type": "string",
"description": "One of insufficient_evidence, indistinguishable_from_luck, weak, supported, strong."
},
"headline": {
"type": "string"
},
"usableReturns": {
"type": "number"
},
"sharpePerPeriod": {
"type": [
"number",
"null"
]
},
"sharpeAnnualised": {
"type": [
"number",
"null"
]
},
"probabilisticSharpe": {
"type": [
"number",
"null"
]
},
"minimumTrackRecordLength": {
"type": [
"number",
"null"
]
},
"periodsShortOfSignificance": {
"type": [
"number",
"null"
]
},
"sharpeConfidenceInterval": {
"anyOf": [
{
"type": "object",
"properties": {
"lower": {
"type": "number"
},
"upper": {
"type": "number"
},
"level": {
"type": "number"
}
},
"required": [
"lower",
"upper",
"level"
],
"additionalProperties": false
},
{
"type": "null"
}
]
},
"deflatedSharpe": {
"type": [
"number",
"null"
]
},
"reasoning": {
"type": "array",
"items": {
"type": "string"
}
},
"divergencesFromReported": {
"type": "array",
"items": {
"type": "object",
"properties": {
"field": {
"type": "string"
},
"reported": {
"type": "number"
},
"recomputed": {
"type": "number"
},
"material": {
"type": "boolean"
}
},
"required": [
"field",
"reported",
"recomputed",
"material"
],
"additionalProperties": false
}
},
"notes": {
"type": "array",
"items": {
"type": "string"
}
},
"full": {
"anyOf": [
{},
{
"type": "null"
}
],
"description": "The complete report when detail is \"full\", otherwise null."
}
},
"required": [
"label",
"sourceId",
"verdict",
"headline",
"usableReturns",
"sharpePerPeriod",
"sharpeAnnualised",
"probabilisticSharpe",
"minimumTrackRecordLength",
"periodsShortOfSignificance",
"sharpeConfidenceInterval",
"deflatedSharpe",
"reasoning",
"divergencesFromReported",
"notes",
"full"
],
"$schema": "https://json-schema.org/draft/2020-12/schema",
"additionalProperties": false
}🟢regimen_regime_map(selector, minSample, maxDates, detail)
Break a strategy’s returns down by the market conditions that held on each date — volatility, funding, open interest, positioning, sentiment, trend state — and report performance per bucket. Each factor also gets a permutation test: the observed best-to-worst spread is compared against spreads produced by randomly reshuffling the regime labels, so a flattering subset cannot pass itself off as a regime effect. Use this after regimen_evaluate_track_record when you need to know WHERE an edge comes from, or whether it is a bet on conditions that could end.
輸入結構描述
{
"type": "object",
"properties": {
"selector": {
"type": "object",
"properties": {
"source": {
"type": "string",
"enum": [
"olaxbt-nexus",
"inline"
],
"description": "olaxbt-nexus analyses the strategy bound to this connection’s API key. inline analyses an equity curve you supply directly, from any venue or backtest."
},
"symbol": {
"description": "For olaxbt-nexus: the market the strategy trades, used for point-in-time reads. Default BTC/USDT.",
"type": "string",
"minLength": 3,
"maxLength": 32
},
"trackRecord": {
"description": "Required when source is inline.",
"type": "object",
"properties": {
"label": {
"default": "inline-track-record",
"description": "A name for this track record, echoed back in results. Do not put anything sensitive here.",
"type": "string",
"minLength": 1,
"maxLength": 80
},
"equity": {
"minItems": 2,
"maxItems": 10000,
"type": "array",
"items": {
"type": "object",
"properties": {
"t": {
"description": "Epoch milliseconds, epoch seconds, or an ISO 8601 timestamp. UTC is assumed.",
"type": [
"number",
"string"
]
},
"equity": {
"type": "number",
"exclusiveMinimum": 0,
"description": "Account equity at that instant, in any single consistent unit."
}
},
"required": [
"t",
"equity"
]
},
"description": "The equity curve, one point per period. Order does not matter; it is sorted by timestamp."
},
"trades": {
"maxItems": 20000,
"type": "array",
"items": {
"type": "object",
"properties": {
"symbol": {
"type": "string",
"minLength": 1,
"maxLength": 64
},
"pnl": {
"type": "number",
"description": "Realised profit or loss for the closed trade, in the equity unit."
},
"exitedAt": {
"type": [
"number",
"string"
]
},
"entryPrice": {
"type": "number"
},
"exitPrice": {
"type": "number"
},
"holdingBars": {
"type": "integer",
"minimum": 0,
"maximum": 9007199254740991
},
"exitReason": {
"type": "string",
"maxLength": 120
}
},
"required": [
"pnl"
]
}
},
"reportedSharpe": {
"description": "Optional. The Sharpe ratio you believe this track record has, so Regimen can contrast it with its own.",
"type": "number"
}
},
"required": [
"equity"
]
}
},
"required": [
"source"
],
"description": "Which track record to analyse."
},
"minSample": {
"default": 15,
"description": "Buckets below this many observations are returned but flagged unusable.",
"type": "integer",
"minimum": 5,
"maximum": 500
},
"maxDates": {
"default": 45,
"description": "How many of the most recent dates to read conditions for, bounded by the upstream rate limit.",
"type": "integer",
"minimum": 5,
"maximum": 45
},
"detail": {
"default": "concise",
"description": "concise returns the verdict, the headline statistics and the reasoning — enough to answer a user. full adds every bucket, every dropped point and the complete provenance list, and is much larger.",
"type": "string",
"enum": [
"concise",
"full"
]
}
},
"required": [
"selector"
],
"$schema": "https://json-schema.org/draft/2020-12/schema"
}輸出結構描述
{
"type": "object",
"properties": {
"label": {
"type": "string"
},
"datesCovered": {
"type": "number"
},
"minSample": {
"type": "number"
},
"factors": {
"type": "array",
"items": {
"type": "object",
"properties": {
"key": {
"type": "string"
},
"bucketingMethod": {
"type": "string"
},
"sufficientBuckets": {
"type": "number"
},
"best": {
"anyOf": [
{
"type": "object",
"properties": {
"label": {
"type": "string"
},
"sharpe": {
"type": "number"
}
},
"required": [
"label",
"sharpe"
],
"additionalProperties": false
},
{
"type": "null"
}
]
},
"worst": {
"anyOf": [
{
"type": "object",
"properties": {
"label": {
"type": "string"
},
"sharpe": {
"type": "number"
}
},
"required": [
"label",
"sharpe"
],
"additionalProperties": false
},
{
"type": "null"
}
]
},
"spread": {
"type": [
"number",
"null"
]
},
"permutationPValue": {
"type": [
"number",
"null"
]
},
"interpretation": {
"type": [
"string",
"null"
]
},
"warnings": {
"type": "array",
"items": {
"type": "string"
}
}
},
"required": [
"key",
"bucketingMethod",
"sufficientBuckets",
"best",
"worst",
"spread",
"permutationPValue",
"interpretation",
"warnings"
],
"additionalProperties": false
}
},
"warnings": {
"type": "array",
"items": {
"type": "string"
}
},
"full": {
"anyOf": [
{},
{
"type": "null"
}
]
}
},
"required": [
"label",
"datesCovered",
"minSample",
"factors",
"warnings",
"full"
],
"$schema": "https://json-schema.org/draft/2020-12/schema",
"additionalProperties": false
}🟢regimen_self_attack(selector, simulations)
Run Regimen’s own analysis against controls whose answer is known in advance: the strategy’s returns with the edge mathematically removed, and a simulated population of strategies with no edge at all. Returns whether the engine correctly found nothing in them, and where the real strategy’s confidence sits among pure-luck strategies of the same length and volatility. Use this when a user is entitled to ask why they should believe the verdict, or before quoting a result as evidence.
輸入結構描述
{
"type": "object",
"properties": {
"selector": {
"type": "object",
"properties": {
"source": {
"type": "string",
"enum": [
"olaxbt-nexus",
"inline"
],
"description": "olaxbt-nexus analyses the strategy bound to this connection’s API key. inline analyses an equity curve you supply directly, from any venue or backtest."
},
"symbol": {
"description": "For olaxbt-nexus: the market the strategy trades, used for point-in-time reads. Default BTC/USDT.",
"type": "string",
"minLength": 3,
"maxLength": 32
},
"trackRecord": {
"description": "Required when source is inline.",
"type": "object",
"properties": {
"label": {
"default": "inline-track-record",
"description": "A name for this track record, echoed back in results. Do not put anything sensitive here.",
"type": "string",
"minLength": 1,
"maxLength": 80
},
"equity": {
"minItems": 2,
"maxItems": 10000,
"type": "array",
"items": {
"type": "object",
"properties": {
"t": {
"description": "Epoch milliseconds, epoch seconds, or an ISO 8601 timestamp. UTC is assumed.",
"type": [
"number",
"string"
]
},
"equity": {
"type": "number",
"exclusiveMinimum": 0,
"description": "Account equity at that instant, in any single consistent unit."
}
},
"required": [
"t",
"equity"
]
},
"description": "The equity curve, one point per period. Order does not matter; it is sorted by timestamp."
},
"trades": {
"maxItems": 20000,
"type": "array",
"items": {
"type": "object",
"properties": {
"symbol": {
"type": "string",
"minLength": 1,
"maxLength": 64
},
"pnl": {
"type": "number",
"description": "Realised profit or loss for the closed trade, in the equity unit."
},
"exitedAt": {
"type": [
"number",
"string"
]
},
"entryPrice": {
"type": "number"
},
"exitPrice": {
"type": "number"
},
"holdingBars": {
"type": "integer",
"minimum": 0,
"maximum": 9007199254740991
},
"exitReason": {
"type": "string",
"maxLength": 120
}
},
"required": [
"pnl"
]
}
},
"reportedSharpe": {
"description": "Optional. The Sharpe ratio you believe this track record has, so Regimen can contrast it with its own.",
"type": "number"
}
},
"required": [
"equity"
]
}
},
"required": [
"source"
],
"description": "Which track record to analyse."
},
"simulations": {
"default": 1000,
"type": "integer",
"minimum": 100,
"maximum": 10000
}
},
"required": [
"selector"
],
"$schema": "https://json-schema.org/draft/2020-12/schema"
}輸出結構描述
{
"type": "object",
"properties": {
"label": {
"type": "string"
},
"verdict": {
"type": "string"
},
"controls": {
"type": "array",
"items": {
"type": "object",
"properties": {
"name": {
"type": "string"
},
"expected": {
"type": "string"
},
"observed": {
"type": [
"number",
"null"
]
},
"passed": {
"type": "boolean"
},
"detail": {
"type": "string"
}
},
"required": [
"name",
"expected",
"observed",
"passed",
"detail"
],
"additionalProperties": false
}
},
"nullDistribution": {
"anyOf": [
{
"type": "object",
"properties": {
"simulations": {
"type": "number"
},
"observedPsr": {
"type": [
"number",
"null"
]
},
"nullMedianPsr": {
"type": [
"number",
"null"
]
},
"nullP95Psr": {
"type": [
"number",
"null"
]
},
"empiricalPValue": {
"type": [
"number",
"null"
]
},
"interpretation": {
"type": "string"
}
},
"required": [
"simulations",
"observedPsr",
"nullMedianPsr",
"nullP95Psr",
"empiricalPValue",
"interpretation"
],
"additionalProperties": false
},
{
"type": "null"
}
]
},
"notes": {
"type": "array",
"items": {
"type": "string"
}
}
},
"required": [
"label",
"verdict",
"controls",
"nullDistribution",
"notes"
],
"$schema": "https://json-schema.org/draft/2020-12/schema",
"additionalProperties": false
}社群
證據
近期觀測
已驗證未記錄版本4 個工具
已驗證未記錄版本4 個工具