Helious market intelligence
US Treasury auction tails, the live curve regime, scored macro releases, and why rates moved.
我該用這個嗎
品質與安全性
根據工具定義與協定合規性的自動化分析。
上下文成本
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": {
"market-intelligence": {
"url": "https://helious.io/mcp"
}
}
}遠端端點
https://helious.io/mcpstreamable-http它能做什麼
工具清單
工具(24)
🟢get_rates_and_curve
US Treasury yields, the 2s10s and other spreads, and the curve regime (bull or bear, steepener or flattener) with the time it flipped. Prices are live on Pro and Ultimate, one hour behind on Starter, and answer with upgrade steps on the free tiers.
輸入結構描述
{
"type": "object",
"properties": {},
"required": []
}🟢get_curve_history(since, limit)
Past curve regime changes: every flip with its time, what it flipped from, and how the session closed.
輸入結構描述
{
"type": "object",
"properties": {
"since": {
"type": "string",
"description": "Oldest date to include, like 2026-06-01. How far back you can go depends on your plan."
},
"limit": {
"type": "integer",
"description": "Most rows to return."
}
},
"required": []
}🟢get_fx_board(since, limit)
FX momentum scorecard: seven major currencies scored against the basket. Newest reading plus past boards. Market data: answers with numbers on Pro and Ultimate.
輸入結構描述
{
"type": "object",
"properties": {
"since": {
"type": "string",
"description": "Oldest date to include, like 2026-06-01. How far back you can go depends on your plan."
},
"limit": {
"type": "integer",
"description": "Most rows to return."
}
},
"required": []
}🟢get_vol_board(since, limit)
Implied volatility board: VIX and the other vol gauges with their one-year percentile. Newest reading plus past boards. Market data: answers with numbers on Pro and Ultimate.
輸入結構描述
{
"type": "object",
"properties": {
"since": {
"type": "string",
"description": "Oldest date to include, like 2026-06-01. How far back you can go depends on your plan."
},
"limit": {
"type": "integer",
"description": "Most rows to return."
}
},
"required": []
}🟢get_inflation(measures, history, window)
Every US inflation measure on one axis: headline and core CPI and PCE, supercore, the trimmed means, the median, the sticky and flexible splits, the CPI components, and what markets expect next. Each one comes back with its year-over-year reading plus 1, 3 and 6-month annualised, so you never have to annualise anything yourself. Also says which parts of the basket are driving the headline rate. `measures` filters by key, `history` adds the monthly series. Published statistics, so it answers on every tier.
輸入結構描述
{
"type": "object",
"properties": {
"measures": {
"type": "string",
"description": "Comma-separated keys to return, such as core_cpi,core_pce. Omit for all of them."
},
"history": {
"type": "boolean",
"description": "Add the full monthly series per measure."
},
"window": {
"type": "integer",
"description": "Months of history to include when history is true."
}
},
"required": []
}🟢get_jobs(measures, history, window)
Every US employment measure on one axis: total nonfarm payrolls split into private and government, the ten private sectors, federal, state and local government, ADP's own private count by sector, initial and continuing jobless claims, and JOLTS openings, hires, quits and layoffs including openings by sector. Each comes back with its monthly change plus 3, 6 and 12-month windows, in THOUSANDS of jobs. Also says which sectors drove the headline, and those parts sum to it exactly. Percentages such as the unemployment and quits rates ride in `standing`. `measures` filters by key, `history` adds the monthly series. Published statistics, so it answers on every tier.
輸入結構描述
{
"type": "object",
"properties": {
"measures": {
"type": "string",
"description": "Comma-separated keys to return, such as payrolls,edhealth,openings. Omit for all."
},
"history": {
"type": "boolean",
"description": "Add the full monthly series per measure."
},
"window": {
"type": "integer",
"description": "Months of history to include when history is true."
}
},
"required": []
}🟢get_rate_path(lane, history)
What the market is paying for US interest rates up to four years out. Two strips, kept apart because they are DIFFERENT RATES: `sr3` is sixteen quarterly 3-month SOFR futures grouped into the whites, reds, greens and blues a rates desk quotes, and `ff` is forty-eight monthly 30-day fed funds contracts. Every contract carries its implied rate now and the rate the SAME contract carried six and twelve months ago, so the gap is the market changing its mind rather than a different instrument. Rates are percent. These are traded prices and not forecasts. Do not compare the two lanes contract by contract: SOFR is secured and the fed funds effective rate is not, and an SR3 month spans the quarter between two IMM dates while a fed funds month is a calendar month.
輸入結構描述
{
"type": "object",
"properties": {
"lane": {
"type": "string",
"description": "sr3 for the quarterly SOFR strip, ff for the monthly fed funds strip. Omit for both."
},
"history": {
"type": "boolean",
"description": "Add each contract's own daily settlement run."
}
},
"required": []
}🟢get_correlations(since, limit)
Cross-asset correlation matrix (stocks, bonds, dollar, gold, oil) over 30 to 120 day windows. Newest reading plus past boards. Market data: answers with numbers on Pro and Ultimate.
輸入結構描述
{
"type": "object",
"properties": {
"since": {
"type": "string",
"description": "Oldest date to include, like 2026-06-01. How far back you can go depends on your plan."
},
"limit": {
"type": "integer",
"description": "Most rows to return."
}
},
"required": []
}🟢get_hormuz_transits(days)
Ships through the Strait of Hormuz per day, split tanker and cargo, measured by Helious from live ship tracking.
輸入結構描述
{
"type": "object",
"properties": {
"days": {
"type": "integer",
"description": "How many days back."
}
},
"required": []
}🟢get_yield_closes(since, limit)
Official 17:00 New York Treasury yield closes per session, as Helious recorded them. Opens on Starter and above.
輸入結構描述
{
"type": "object",
"properties": {
"since": {
"type": "string",
"description": "Oldest date to include, like 2026-06-01. How far back you can go depends on your plan."
},
"limit": {
"type": "integer",
"description": "Most rows to return."
}
},
"required": []
}🟢get_economic_calendar(days_back, days_ahead, country, limit)
Economic releases with forecasts, prior values and the actual once it prints, plus Fed speakers and auction times. Defaults to yesterday through the next 7 days; widen days_back and days_ahead to see more, or filter to one country like US, EU, GB or JP.
輸入結構描述
{
"type": "object",
"properties": {
"days_back": {
"type": "integer",
"description": "How many days of already-printed events to include. Default 1, up to 90."
},
"days_ahead": {
"type": "integer",
"description": "How many days ahead to include. Default 7, up to 365."
},
"country": {
"type": "string",
"description": "Two-letter country or bloc, like US, EU, GB, JP. Empty means everywhere."
},
"limit": {
"type": "integer",
"description": "Most events to return. Default 100."
}
},
"required": []
}🟢list_series
Every US economic data series Helious tracks (CPI, payrolls, GDP and so on) with its slug for get_series.
輸入結構描述
{
"type": "object",
"properties": {},
"required": []
}🟢get_series(slug)
One economic data series: the latest print, the forecast, the surprise in standard deviations, and the history.
輸入結構描述
{
"type": "object",
"properties": {
"slug": {
"type": "string",
"description": "Series slug from list_series, like cpi or nonfarm-payrolls."
}
},
"required": []
}🟢get_auctions(limit, tenor)
US Treasury auction results, measured by Helious at the close: the high yield, the tail against the when-issued yield, bid-to-cover against the tenor's twelve-auction average, who bought (indirect, direct, dealer), and the desk's strong, in line or weak verdict. Pass tenor to ask about one part of the curve, like 10-year-note or 30-year-bond, which is what you want for 'how did the last 10-year auction go'. The tail is the number that answers whether an auction was good or bad, and Helious is the only free source that publishes it.
輸入結構描述
{
"type": "object",
"properties": {
"limit": {
"type": "integer",
"description": "Most auctions to return."
},
"tenor": {
"type": "string",
"description": "One tenor, like 10-year-note, 30-year-bond or 26-week-bill. Plain forms work too: '10y', '30 year'. Or a whole class: bills, notes, bonds, tips, frn. Or a curve SEGMENT, which is usually what 'the front end / belly / long end of the curve' means: front (bills plus the 2- and 3-year notes), belly (the 5-, 7- and 10-year), long (the 20- and 30-year). Reopenings of a tenor are included."
}
},
"required": []
}🟢get_feed(q, categories, limit)
The posts Helious publishes: scored releases, auction results, board updates, the daily brief and live squawk lines. Posts carry helious_read, the desk's plain-English line on why it matters. Depth follows your plan (1 day keyless, 7 days free, 12-24 months paid, 10 years Ultimate). Optional q filters by word; categories narrows to chosen lanes. Delayed 60 minutes without a paid key.
輸入結構描述
{
"type": "object",
"properties": {
"q": {
"type": "string",
"description": "Filter word."
},
"categories": {
"type": "string",
"description": "Comma-separated lanes, like release,auction. Empty means all."
},
"limit": {
"type": "integer",
"description": "Most items to return."
}
},
"required": []
}🟢get_document_digests(kind, limit)
The desk's read of FULL central bank documents, not headlines: FOMC minutes and Fed/ECB speeches read end to end. Each digest carries a summary, what is genuinely new versus what the market already knew, key findings with their market consequence, a hawkish/dovish committee lean, and quotes verified word for word against the source document. Minutes carry no bond or equity direction on purpose: they describe a meeting about three weeks earlier, so the desk states the lean and declines the market call. Delayed 60 minutes without a paid key.
輸入結構描述
{
"type": "object",
"properties": {
"kind": {
"type": "string",
"description": "minutes, speech, or all (default)."
},
"limit": {
"type": "integer",
"description": "Most digests to return."
}
},
"required": []
}🟢get_fed_roster
Who is on the FOMC: governors and presidents, who votes this year, their lean, and their upcoming speeches.
輸入結構描述
{
"type": "object",
"properties": {},
"required": []
}🟢get_squawk_sessions(hours)
Live events Helious transcribed in the last week (Fed pressers, briefings), one entry per event.
輸入結構描述
{
"type": "object",
"properties": {
"hours": {
"type": "integer",
"description": "How many hours back, up to 168."
}
},
"required": []
}🟢get_access_info
What your current tier can do, the full plan ladder, and the exact steps to tell your user when you need more: make a free account, get a key, or subscribe.
輸入結構描述
{
"type": "object",
"properties": {},
"required": []
}🟢get_treasury_curve
The whole US Treasury curve in one call, 3M bill to 30Y bond with daily closes: live points on Pro and Ultimate, one hour behind on Starter, upgrade steps instead of numbers on the free tiers.
輸入結構描述
{
"type": "object",
"properties": {},
"required": []
}🟢get_nasdaq100(symbol, limit)
The NASDAQ-100 ranked best to worst on the session: price, change and sector for every stock. Pass symbol to ask about ONE company instead, like AAPL or NVDA, and you get its price, its move on the session and where it ranks on the board today. Equities are market data: live on Pro and Ultimate, upgrade steps instead of numbers below.
輸入結構描述
{
"type": "object",
"properties": {
"symbol": {
"type": "string",
"description": "One or more NASDAQ-100 tickers, comma separated, like AAPL or AAPL,MSFT. Empty returns the whole ranked board."
},
"limit": {
"type": "integer",
"description": "Most stocks to return."
}
},
"required": []
}🟢get_rate_odds
The odds of a Federal Reserve rate cut or hike at each remaining FOMC meeting, priced from fed funds futures. THIS IS THE TOOL for 'what are the odds of a cut in September', 'is the Fed cutting', 'what is priced in for the next meeting' or 'how many cuts this year'. Gives the probability per meeting, the implied effective rate after each one, and the total move priced across the whole path. Computed by Helious from settlement prices against the effective fed funds rate, not the target midpoint.
輸入結構描述
{
"type": "object",
"properties": {},
"required": []
}🟢get_market_context
START HERE for any 'why is the market doing this' question. One call gives the whole cross-asset board (equities, the Treasury curve, FX, volatility, commodities), every scored economic release behind it, and the Helious desk's read on what is actually driving the session: whether it is event-driven, flow-driven or quiet, the evidence that read rests on, and the regime yields and stocks have actually been trading in. Use this before the individual board tools: it saves five calls, and it characterises the session rather than leaving you to guess a cause. Market data: answers with numbers on Pro and Ultimate.
輸入結構描述
{
"type": "object",
"properties": {},
"required": []
}🟢get_earnings(symbol, limit)
US mega-cap earnings: when a company reports, whether that date is confirmed or still an estimate, whether it prints before the open or after the close, the consensus EPS, and once it lands the reported EPS with the beat or miss. Pass symbol for one name, like AAPL. This is the tool for any question about a company's earnings date or EPS.
輸入結構描述
{
"type": "object",
"properties": {
"symbol": {
"type": "string",
"description": "One or more tickers, comma separated, like AAPL or AAPL,MSFT. Empty returns every name tracked."
},
"limit": {
"type": "integer",
"description": "Most rows to return."
}
},
"required": []
}建議的提示詞
get_rates_and_curveget_rates_and_curvelist_serieslist_serieslist_seriesget_rates_and_curve社群
證據