Sardine: Kalshi crypto settlement history
How often Kalshi BTC/ETH/XRP contracts settled YES, counted not forecast, with a public record
使うべきか
品質と安全性
ツール定義とプロトコルへの準拠に関する自動分析に基づいています。
コンテキストコスト
これは、サーバーのツールがモデルのコンテキストに読み込まれるたびに消費されるおおよそのトークン数です。数が多いほど、ほかのタスクに使える注意が減ります。
インストール
ワンクリックインストール
これを `claude_desktop_config.json` ファイルに追加してください:
{
"mcpServers": {
"sardine": {
"command": "uvx",
"args": [
"sardine-mcp"
]
}
}
}実行可能なパッケージ
0.1.1stdioリモートエンドポイント
https://sardine.info/mcpstreamable-httpできること
ツール一覧
ツール（9）
🟢list_markets
List the Kalshi series Sardine covers, and whether each is currently served. Each entry gives the Sardine key (e.g. "BTC-15M"), the Kalshi series ticker, the window length, and the latest calibration check: the largest gap, in probability points, between what Sardine published and what then settled.
入力スキーマ
{
"type": "object",
"properties": {},
"title": "list_marketsArguments"
}出力スキーマ
{
"type": "object",
"additionalProperties": true,
"title": "list_marketsDictOutput"
}🟢get_settlement_rate(asset, window_minutes, strike, minutes_left, side, ...)
How often has a contract like this one settled in favour of `side`? Uses the asset's live spot price. Give the contract's strike (target price), the minutes left until it settles, and optionally Kalshi's ask in dollars (0.01-0.99) to get Kalshi's fee and all-in price on the same line. Returns the historical settlement rate, its 95% interval, the number of past windows counted, the 1-minute realised vol and z behind the lookup, and with `kalshi_ask`: the fee, the all-in price and the gap after fee (`gap_after_fee`, `gap_cents`, signed: positive means history is above the price). A small `windows_counted` means a weak answer.
入力スキーマ
{
"type": "object",
"properties": {
"asset": {
"enum": [
"BTC",
"ETH",
"XRP"
],
"title": "Asset",
"type": "string"
},
"window_minutes": {
"enum": [
15,
60
],
"title": "Window Minutes",
"type": "integer"
},
"strike": {
"title": "Strike",
"type": "number"
},
"minutes_left": {
"title": "Minutes Left",
"type": "number"
},
"side": {
"default": "YES",
"enum": [
"YES",
"NO"
],
"title": "Side",
"type": "string"
},
"kalshi_ask": {
"anyOf": [
{
"type": "number"
},
{
"type": "null"
}
],
"default": null,
"title": "Kalshi Ask"
}
},
"required": [
"asset",
"window_minutes",
"strike",
"minutes_left"
],
"title": "get_settlement_rateArguments"
}出力スキーマ
{
"type": "object",
"additionalProperties": true,
"title": "get_settlement_rateDictOutput"
}🟢get_live_board(market, limit)
Open Kalshi contracts right now, each with Sardine's historical count. No prices. Optionally filter to one market. Each row has the contract, the minutes left, the historical settlement rate with its interval and sample size, and a one-sentence summary of the count. Kalshi's prices are deliberately NOT included (pending Kalshi's Redistribution licence): read them from Kalshi's own API, then pass kalshi_ask to get_settlement_rate for the fee and the gap.
入力スキーマ
{
"type": "object",
"properties": {
"market": {
"anyOf": [
{
"enum": [
"BTC-15M",
"ETH-15M",
"BTC-1H"
],
"type": "string"
},
{
"type": "null"
}
],
"default": null,
"title": "Market"
},
"limit": {
"default": 10,
"title": "Limit",
"type": "integer"
}
},
"title": "get_live_boardArguments"
}出力スキーマ
{
"type": "object",
"additionalProperties": true,
"title": "get_live_boardDictOutput"
}🟢get_rate_table(asset, window_minutes)
The full lookup table behind every Sardine number for one series. Each row is a (distance-from-strike, time-left) bucket: distance in volatility units, seconds left, the share that settled YES, its 95% interval, and the number of independent windows counted.
入力スキーマ
{
"type": "object",
"properties": {
"asset": {
"default": "BTC",
"enum": [
"BTC",
"ETH",
"XRP"
],
"title": "Asset",
"type": "string"
},
"window_minutes": {
"default": 15,
"enum": [
15,
60
],
"title": "Window Minutes",
"type": "integer"
}
},
"title": "get_rate_tableArguments"
}出力スキーマ
{
"type": "object",
"additionalProperties": true,
"title": "get_rate_tableDictOutput"
}🟢get_track_record
How accurate Sardine's published numbers have been, scored against settlements. For each series and probability bucket: what Sardine said, what actually settled, and the miss in points. Use this before relying on any number.
入力スキーマ
{
"type": "object",
"properties": {},
"title": "get_track_recordArguments"
}出力スキーマ
{
"type": "object",
"additionalProperties": true,
"title": "get_track_recordDictOutput"
}🟢list_datasets
Downloadable CSV history files, with row counts, date ranges and URLs. Files open directly in Excel, pandas or any CSV reader. Credit "Sardine (sardine.info)" when you use them.
入力スキーマ
{
"type": "object",
"properties": {},
"title": "list_datasetsArguments"
}出力スキーマ
{
"type": "object",
"additionalProperties": true,
"title": "list_datasetsDictOutput"
}🟢backtest_rule(market, side, min_minutes_left, max_minutes_left, min_price_cents, ...)
Would this rule have made money? Replays recorded Kalshi quotes, second by second. Describe a rule for Kalshi's 15-minute crypto up/down contracts: which side to buy, when (minutes left), at what prices (cents), and optionally only when Sardine's history beats Kalshi's ask plus fee by `min_gap_cents` (side BEST picks whichever side has the larger gap). Sardine replays its per-second recordings of Kalshi's order book: one trade per window, a limit order at the ask landing after `latency_seconds`, filled only up to the size resting there, Kalshi's real fee, and Kalshi's official settlement. Returns profit per contract after fees with a 95% interval, win rate, fill behaviour, a zero-latency comparison (exposes stale-quote illusions), a first-half/second-half stability check, breakdowns by minutes left and price, and warnings. Results only; no raw data. Dates are UTC YYYY-MM-DD. Present results as what happened historically, never as a forecast.
入力スキーマ
{
"type": "object",
"properties": {
"market": {
"default": "BTC-15M",
"enum": [
"BTC-15M",
"ETH-15M",
"XRP-15M"
],
"title": "Market",
"type": "string"
},
"side": {
"default": "YES",
"enum": [
"YES",
"NO",
"BEST"
],
"title": "Side",
"type": "string"
},
"min_minutes_left": {
"default": 2,
"title": "Min Minutes Left",
"type": "number"
},
"max_minutes_left": {
"default": 14,
"title": "Max Minutes Left",
"type": "number"
},
"min_price_cents": {
"default": 1,
"title": "Min Price Cents",
"type": "number"
},
"max_price_cents": {
"default": 99,
"title": "Max Price Cents",
"type": "number"
},
"min_gap_cents": {
"anyOf": [
{
"type": "number"
},
{
"type": "null"
}
],
"default": null,
"title": "Min Gap Cents"
},
"max_gap_cents": {
"anyOf": [
{
"type": "number"
},
{
"type": "null"
}
],
"default": 25,
"title": "Max Gap Cents"
},
"contracts": {
"default": 100,
"title": "Contracts",
"type": "integer"
},
"latency_seconds": {
"default": 2,
"title": "Latency Seconds",
"type": "integer"
},
"start_date": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"default": null,
"title": "Start Date"
},
"end_date": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"default": null,
"title": "End Date"
}
},
"title": "backtest_ruleArguments"
}出力スキーマ
{
"type": "object",
"additionalProperties": true,
"title": "backtest_ruleDictOutput"
}🟢backtest_signals(market, signals, latency_seconds, start_date, end_date)
Replay YOUR OWN signals on recorded per-second Kalshi quotes, after fees. `signals` is a list of {"ts": <UTC epoch seconds>, "side": "YES"|"NO", "contracts": <int>} (at most 5,000). Each one is treated like a trigger: the ask seen at that second for that side, a limit order landing after `latency_seconds`, filled only up to the size resting there, Kalshi's fee, Kalshi's official settlement. One trade per 15-minute window: the first signal in a window is used and later ones are counted as ignored. Returns aggregates only (profit per contract with interval, win rate, zero-latency comparison, stability, breakdowns, warnings), plus `signals_used` and `signals_outside_data`. Needs a free key when served remotely. Present results as what happened, never as a forecast.
入力スキーマ
{
"type": "object",
"properties": {
"market": {
"enum": [
"BTC-15M",
"ETH-15M",
"XRP-15M"
],
"title": "Market",
"type": "string"
},
"signals": {
"items": {
"additionalProperties": true,
"type": "object"
},
"title": "Signals",
"type": "array"
},
"latency_seconds": {
"default": 2,
"title": "Latency Seconds",
"type": "integer"
},
"start_date": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"default": null,
"title": "Start Date"
},
"end_date": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"default": null,
"title": "End Date"
}
},
"required": [
"market",
"signals"
],
"title": "backtest_signalsArguments"
}出力スキーマ
{
"type": "object",
"additionalProperties": true,
"title": "backtest_signalsDictOutput"
}🟢get_z(asset, window_minutes, strike, minutes_left)
Where a contract sits in the table's coordinates right now: spot, sigma_1m, z and the bucket. For a builder running the table offline against Kalshi's feed: the formula is returned with the numbers. No settlement rate here; use get_rate_table for the cells and get_settlement_rate for the count.
入力スキーマ
{
"type": "object",
"properties": {
"asset": {
"enum": [
"BTC",
"ETH",
"XRP"
],
"title": "Asset",
"type": "string"
},
"window_minutes": {
"enum": [
15,
60
],
"title": "Window Minutes",
"type": "integer"
},
"strike": {
"title": "Strike",
"type": "number"
},
"minutes_left": {
"title": "Minutes Left",
"type": "number"
}
},
"required": [
"asset",
"window_minutes",
"strike",
"minutes_left"
],
"title": "get_zArguments"
}出力スキーマ
{
"type": "object",
"additionalProperties": true,
"title": "get_zDictOutput"
}コミュニティ
エビデンス