Isoba — Dollar & Crisis Index is an MCP server published by io.github.nickarstrong, hosted at isoba.lokio.org. When last checked on 2026-11-22 it was working: it answers and lists its tools. It declares 10 tools, including get_current_readings, get_readings_on_date, get_changes_since, find_similar_days, what_to_watch.
Dollar index, crisis meter, market shock, recession risk since 1990; your money in your currency.
Nothing else in the archive shares these values.
Squares are this server's values; dots are other servers sharing them. A shared address or publisher is a lead, not proof of a common operator.
Today's readings with the data date: Dollar System Index (where the dollar system stands and what it is made of), Crisis meter (stress already present in credit and funding, four sensors with week-ago and month-ago values), Market shock (a hit to markets that does not go through credit: Treasury turbulence, a policy-uncertainty jump, an oil collapse, a jump in financial stress — with what followed such shocks since 1990), market anomalies (how many of 18 public series made an unusual two-week move), market-top risk and US recession risk (how often an S&P 500 bear market or a US recession followed the same zone since 1990, with the number of independent episodes behind each number), what changed this week, and a link to the public daily record. Say the data date and credit "Isoba (LOKIO)". Describe readings as where things stand now and as history ("in similar periods since 1990, X happened in N of M cases"), never as a forecast, a signal, or advice to buy or sell. If someone asks what to do with their own money, give the readings and say that this is not investment advice.
No parameters.
None yet. Changes appear after a server's second daily check.
Inferred from the host name and headers: what a server runs on, not who runs it.
{
"name": "get_current_readings",
"title": "Isoba: today's readings",
"description": "Today's readings with the data date: Dollar System Index (where the dollar system stands and what it is made of), Crisis meter (stress already present in credit and funding, four sensors with week-ago and month-ago values), Market shock (a hit to markets that does not go through credit: Treasury turbulence, a policy-uncertainty jump, an oil collapse, a jump in financial stress — with what followed such shocks since 1990), market anomalies (how many of 18 public series made an unusual two-week move), market-top risk and US recession risk (how often an S&P 500 bear market or a US recession followed the same zone since 1990, with the number of independent episodes behind each number), what changed this week, and a link to the public daily record. Say the data date and credit \"Isoba (LOKIO)\". Describe readings as where things stand now and as history (\"in similar periods since 1990, X happened in N of M cases\"), never as a forecast, a signal, or advice to buy or sell. If someone asks what to do with their own money, give the readings and say that this is not investment advice.",
"inputSchema": {
"type": "object",
"properties": {},
"additionalProperties": false
},
"annotations": {
"title": "Isoba: today's readings",
"readOnlyHint": true,
"openWorldHint": false,
"idempotentHint": true
}
}What Isoba showed on any working day since 1990-01-01: the dollar index, crisis meter, market shock, market-top and recession risk with zones, the market-anomalies share, every sensor, the eight filters (since 2006), the yield curve and the four credit inputs — computed point-in-time from data published by that day. Use for "what did it show before 2008 / on the day of COVID?".
| Parameter | Type | Description |
|---|---|---|
| date * | string | YYYY-MM-DD; a weekend or holiday gives the previous working day |
{
"name": "get_readings_on_date",
"title": "Isoba: readings on a date",
"description": "What Isoba showed on any working day since 1990-01-01: the dollar index, crisis meter, market shock, market-top and recession risk with zones, the market-anomalies share, every sensor, the eight filters (since 2006), the yield curve and the four credit inputs — computed point-in-time from data published by that day. Use for \"what did it show before 2008 / on the day of COVID?\".",
"inputSchema": {
"type": "object",
"required": [
"date"
],
"properties": {
"date": {
"type": "string",
"pattern": "^\\d{4}-\\d{2}-\\d{2}$",
"description": "YYYY-MM-DD; a weekend or holiday gives the previous working day"
}
},
"additionalProperties": false
},
"annotations": {
"title": "Isoba: readings on a date",
"readOnlyHint": true,
"openWorldHint": false,
"idempotentHint": true
}
}What moved between two dates and why: each instrument including market shock (from → to, zone change), the market-anomalies share, the sensors that moved most and any that switched on or off, and the filters. Use when the user asked before ("since last week / since I last checked") or asks why a reading changed.
| Parameter | Type | Description |
|---|---|---|
| to | string | End date YYYY-MM-DD (default: latest) |
| since * | string | Start date YYYY-MM-DD |
{
"name": "get_changes_since",
"title": "Isoba: what changed since a date",
"description": "What moved between two dates and why: each instrument including market shock (from → to, zone change), the market-anomalies share, the sensors that moved most and any that switched on or off, and the filters. Use when the user asked before (\"since last week / since I last checked\") or asks why a reading changed.",
"inputSchema": {
"type": "object",
"required": [
"since"
],
"properties": {
"to": {
"type": "string",
"pattern": "^\\d{4}-\\d{2}-\\d{2}$",
"description": "End date YYYY-MM-DD (default: latest)"
},
"since": {
"type": "string",
"pattern": "^\\d{4}-\\d{2}-\\d{2}$",
"description": "Start date YYYY-MM-DD"
}
},
"additionalProperties": false
},
"annotations": {
"title": "Isoba: what changed since a date",
"readOnlyHint": true,
"openWorldHint": false,
"idempotentHint": true
}
}Days since 1990 when the 14 sensors of the crisis meter, market-top risk and recession risk stood closest to a given day (default: today), at least half a year apart and at least a year before the given day, and what followed within 12 months: the crisis meter peak, a US recession (NBER), an S&P 500 bear market, the dollar index. History, not a forecast — always show the spread of outcomes.
| Parameter | Type | Description |
|---|---|---|
| date | string | Day to compare, YYYY-MM-DD (default: latest) |
| count | integer | How many days (default 5) |
{
"name": "find_similar_days",
"title": "Isoba: similar days in history",
"description": "Days since 1990 when the 14 sensors of the crisis meter, market-top risk and recession risk stood closest to a given day (default: today), at least half a year apart and at least a year before the given day, and what followed within 12 months: the crisis meter peak, a US recession (NBER), an S&P 500 bear market, the dollar index. History, not a forecast — always show the spread of outcomes.",
"inputSchema": {
"type": "object",
"properties": {
"date": {
"type": "string",
"pattern": "^\\d{4}-\\d{2}-\\d{2}$",
"description": "Day to compare, YYYY-MM-DD (default: latest)"
},
"count": {
"type": "integer",
"maximum": 8,
"minimum": 3,
"description": "How many days (default 5)"
}
},
"additionalProperties": false
},
"annotations": {
"title": "Isoba: similar days in history",
"readOnlyHint": true,
"openWorldHint": false,
"idempotentHint": true
}
}How many points each instrument is from the next zone boundary up or down, which sensors are closest to switching on or off (threshold 80), and the freshest and stalest inputs. Use for "what would change the picture?".
No parameters.
{
"name": "what_to_watch",
"title": "Isoba: what is closest to changing",
"description": "How many points each instrument is from the next zone boundary up or down, which sensors are closest to switching on or off (threshold 80), and the freshest and stalest inputs. Use for \"what would change the picture?\".",
"inputSchema": {
"type": "object",
"properties": {},
"additionalProperties": false
},
"annotations": {
"title": "Isoba: what is closest to changing",
"readOnlyHint": true,
"openWorldHint": false,
"idempotentHint": true
}
}What markets price now (Fed rate path from the 2-year Treasury yield, 5-year breakeven inflation, yields) and what happened over the next 12 months after the 10 days since 1990 most similar to today (same 14 sensors as find_similar_days, at least half a year apart), with the number of distinct cycles behind them: US dollar, US stocks (market value of companies, Fed Z.1), 10-year Treasury return, Fed rate, core inflation, unemployment, WTI oil, yield curve, corporate bond spread, cash vs inflation, M2 money growth, and the crypto backdrop (dollar and M2 — there is no open crypto price history since 1990). Report counts ("rose in 9 of 10"), the median and the range, and how many cycles stand behind them. History and market prices, not a forecast. Say the data date and credit "Isoba (LOKIO)". Describe readings as where things stand now and as history ("in similar periods since 1990, X happened in N of M cases"), never as a forecast, a signal, or advice to buy or sell. If someone asks what to do with their own money, give the readings and say that this is not investment advice.
No parameters.
{
"name": "get_expectations",
"title": "Isoba: 12-month expectations",
"description": "What markets price now (Fed rate path from the 2-year Treasury yield, 5-year breakeven inflation, yields) and what happened over the next 12 months after the 10 days since 1990 most similar to today (same 14 sensors as find_similar_days, at least half a year apart), with the number of distinct cycles behind them: US dollar, US stocks (market value of companies, Fed Z.1), 10-year Treasury return, Fed rate, core inflation, unemployment, WTI oil, yield curve, corporate bond spread, cash vs inflation, M2 money growth, and the crypto backdrop (dollar and M2 — there is no open crypto price history since 1990). Report counts (\"rose in 9 of 10\"), the median and the range, and how many cycles stand behind them. History and market prices, not a forecast. Say the data date and credit \"Isoba (LOKIO)\". Describe readings as where things stand now and as history (\"in similar periods since 1990, X happened in N of M cases\"), never as a forecast, a signal, or advice to buy or sell. If someone asks what to do with their own money, give the readings and say that this is not investment advice.",
"inputSchema": {
"type": "object",
"properties": {},
"additionalProperties": false
},
"annotations": {
"title": "Isoba: 12-month expectations",
"readOnlyHint": true,
"openWorldHint": false,
"idempotentHint": true
}
}Monthly averages of one or several instruments between two months (DSI since 2006, the others since 1990), with the zone of each month: dollar index, crisis meter, market shock, market anomalies, market-top and recession risk. Use for trends and to see what the instruments showed around past events.
| Parameter | Type | Description |
|---|---|---|
| to | string | Last month, YYYY-MM (default: latest) |
| from | string | First month, YYYY-MM (default: 24 months ago) |
| instrument | string | dsi — Dollar System Index; crisis — Crisis meter; market_shock — market shock; anomalies — market anomalies (% of 18 series); top_risk — market-top risk; recession_risk — US recession risk |
| instruments | array | Several instruments at once (instead of instrument) |
{
"name": "get_monthly_history",
"title": "Isoba: monthly history",
"description": "Monthly averages of one or several instruments between two months (DSI since 2006, the others since 1990), with the zone of each month: dollar index, crisis meter, market shock, market anomalies, market-top and recession risk. Use for trends and to see what the instruments showed around past events.",
"inputSchema": {
"type": "object",
"properties": {
"to": {
"type": "string",
"pattern": "^\\d{4}-(0[1-9]|1[0-2])$",
"description": "Last month, YYYY-MM (default: latest)"
},
"from": {
"type": "string",
"pattern": "^\\d{4}-(0[1-9]|1[0-2])$",
"description": "First month, YYYY-MM (default: 24 months ago)"
},
"instrument": {
"enum": [
"dsi",
"crisis",
"market_shock",
"anomalies",
"top_risk",
"recession_risk"
],
"type": "string",
"description": "dsi — Dollar System Index; crisis — Crisis meter; market_shock — market shock; anomalies — market anomalies (% of 18 series); top_risk — market-top risk; recession_risk — US recession risk"
},
"instruments": {
"type": "array",
"items": {
"enum": [
"dsi",
"crisis",
"market_shock",
"anomalies",
"top_risk",
"recession_risk"
],
"type": "string"
},
"maxItems": 6,
"minItems": 1,
"description": "Several instruments at once (instead of instrument)"
}
},
"additionalProperties": false
},
"annotations": {
"title": "Isoba: monthly history",
"readOnlyHint": true,
"openWorldHint": false,
"idempotentHint": true
}
}How Isoba behaved when run point-in-time over every working day since 1990 (only data published by each day, checked for look-ahead). Default section "summary" is short; ask for a section (crisis_events, recessions, market_tops, false_alarms, by_year, methods, all) or one event (gulf, ltcm, dotcom, sept11, worldcom, bnp, lehman, euro, downgrade, china, oil2016, q4_2018, covid, bear2022, svb, tariffs — or its year). Call it before claiming reliability.
| Parameter | Type | Description |
|---|---|---|
| event | string | One crisis by id, name or year, e.g. lehman, "COVID", 2008 |
| section | string | Part of the record (default summary) |
| to_year | integer | |
| from_year | integer |
{
"name": "get_track_record",
"title": "Isoba: tested on history",
"description": "How Isoba behaved when run point-in-time over every working day since 1990 (only data published by each day, checked for look-ahead). Default section \"summary\" is short; ask for a section (crisis_events, recessions, market_tops, false_alarms, by_year, methods, all) or one event (gulf, ltcm, dotcom, sept11, worldcom, bnp, lehman, euro, downgrade, china, oil2016, q4_2018, covid, bear2022, svb, tariffs — or its year). Call it before claiming reliability.",
"inputSchema": {
"type": "object",
"properties": {
"event": {
"type": "string",
"description": "One crisis by id, name or year, e.g. lehman, \"COVID\", 2008"
},
"section": {
"enum": [
"summary",
"crisis_events",
"recessions",
"market_tops",
"false_alarms",
"by_year",
"methods",
"all"
],
"type": "string",
"description": "Part of the record (default summary)"
},
"to_year": {
"type": "integer",
"maximum": 2100,
"minimum": 1990
},
"from_year": {
"type": "integer",
"maximum": 2100,
"minimum": 1990
}
},
"additionalProperties": false
},
"annotations": {
"title": "Isoba: tested on history",
"readOnlyHint": true,
"openWorldHint": false,
"idempotentHint": true
}
}The "Your money" card of the Isoba app for one currency: what 1 US dollar costs in it (for USD — what 1 euro costs), gold (US dollars per troy ounce, and per gram in the currency), Brent oil and bitcoin in US dollars, and cash — inflation and how much buying power it lost over 1 and 5 years. For each: the price with its date and source, the change over a month and a year, and what happened over the next month (for cash — the next year) in similar past moments: number of cases since when, the usual outcome, 1 in 10 worse than, the worst and the best; the risk for someone who holds it (bad outcomes now vs all days), and for the currency "wait a week?" (how often the rate was higher a week later in similar moments vs on all days). History, not a forecast. Say the data date and credit "Isoba (LOKIO)". Describe readings as where things stand now and as history ("in similar periods since 1990, X happened in N of M cases"), never as a forecast, a signal, or advice to buy or sell. If someone asks what to do with their own money, give the readings and say that this is not investment advice.
| Parameter | Type | Description |
|---|---|---|
| currency | string | ISO 4217 code, e.g. KZT, TRY, NGN, EUR, USD (default USD) |
{
"name": "get_money",
"title": "Isoba: money in your currency",
"description": "The \"Your money\" card of the Isoba app for one currency: what 1 US dollar costs in it (for USD — what 1 euro costs), gold (US dollars per troy ounce, and per gram in the currency), Brent oil and bitcoin in US dollars, and cash — inflation and how much buying power it lost over 1 and 5 years. For each: the price with its date and source, the change over a month and a year, and what happened over the next month (for cash — the next year) in similar past moments: number of cases since when, the usual outcome, 1 in 10 worse than, the worst and the best; the risk for someone who holds it (bad outcomes now vs all days), and for the currency \"wait a week?\" (how often the rate was higher a week later in similar moments vs on all days). History, not a forecast. Say the data date and credit \"Isoba (LOKIO)\". Describe readings as where things stand now and as history (\"in similar periods since 1990, X happened in N of M cases\"), never as a forecast, a signal, or advice to buy or sell. If someone asks what to do with their own money, give the readings and say that this is not investment advice.",
"inputSchema": {
"type": "object",
"properties": {
"currency": {
"type": "string",
"pattern": "^[A-Za-z]{3}$",
"description": "ISO 4217 code, e.g. KZT, TRY, NGN, EUR, USD (default USD)"
}
},
"additionalProperties": false
},
"annotations": {
"title": "Isoba: money in your currency",
"readOnlyHint": true,
"openWorldHint": false,
"idempotentHint": true
}
}The country cards of the Isoba app for one of 195 countries: IMF World Economic Outlook for last year, this year (estimate) and next year (forecast) — growth, inflation, unemployment, government debt, budget balance, current account (a deficit means the country spends abroad more than it earns, so the exchange rate leans on money from abroad), GDP per person in dollars and at purchasing power; the central bank rate and the real rate (rate minus inflation); where available: bank credit to the private sector against its long trend and the share of income going to debt payments (BIS), the 10-year government bond yield against its 10-year average, and real house prices against the country's own 20-year norm (BIS). Each block has its date and source; weak_spots lists what stands out; not_covered lists what Isoba has no data on — for those use official sources of that country and say so. Where things stand, not a forecast. Say the data date and credit "Isoba (LOKIO)". Describe readings as where things stand now and as history ("in similar periods since 1990, X happened in N of M cases"), never as a forecast, a signal, or advice to buy or sell. If someone asks what to do with their own money, give the readings and say that this is not investment advice.
| Parameter | Type | Description |
|---|---|---|
| country * | string | ISO 3166 two-letter code (MA, UZ, DE) or English name (Morocco, Uzbekistan, Germany). XM — euro area. |
{
"name": "get_country",
"title": "Isoba: one country's economy",
"description": "The country cards of the Isoba app for one of 195 countries: IMF World Economic Outlook for last year, this year (estimate) and next year (forecast) — growth, inflation, unemployment, government debt, budget balance, current account (a deficit means the country spends abroad more than it earns, so the exchange rate leans on money from abroad), GDP per person in dollars and at purchasing power; the central bank rate and the real rate (rate minus inflation); where available: bank credit to the private sector against its long trend and the share of income going to debt payments (BIS), the 10-year government bond yield against its 10-year average, and real house prices against the country's own 20-year norm (BIS). Each block has its date and source; weak_spots lists what stands out; not_covered lists what Isoba has no data on — for those use official sources of that country and say so. Where things stand, not a forecast. Say the data date and credit \"Isoba (LOKIO)\". Describe readings as where things stand now and as history (\"in similar periods since 1990, X happened in N of M cases\"), never as a forecast, a signal, or advice to buy or sell. If someone asks what to do with their own money, give the readings and say that this is not investment advice.",
"inputSchema": {
"type": "object",
"required": [
"country"
],
"properties": {
"country": {
"type": "string",
"maxLength": 60,
"minLength": 2,
"description": "ISO 3166 two-letter code (MA, UZ, DE) or English name (Morocco, Uzbekistan, Germany). XM — euro area."
}
},
"additionalProperties": false
},
"annotations": {
"title": "Isoba: one country's economy",
"readOnlyHint": true,
"openWorldHint": false,
"idempotentHint": true
}
}Isoba is a once-a-day barometer of the US dollar system and financial stress, built only from public-domain official data and tested point-in-time on every working day since 1990. Start with get_current_readings (dollar index, crisis meter, market shock, market anomalies, market-top and recession risk). For "the dollar in my currency, gold, oil, bitcoin, is my cash losing value, should I wait a week to exchange" use get_money with the currency code. For one country’s economy (growth, inflation, central bank rate, real rate, debt, current account — pressure on the currency, bank credit, 10-year bond yield, house prices) use get_country; what it lacks, take from that country’s central bank, statistics office or the IMF, and say so. For a past date use get_readings_on_date; for "what changed since…" use get_changes_since; for "is now like 2008 / 2000?" use find_similar_days; for "what could change the reading" use what_to_watch; for "what to expect for the dollar, stocks, bonds, rates, oil or crypto" use get_expectations; for trends use get_monthly_history; before any claim about reliability, or for a past crisis, use get_track_record (section or event). Say the data date and credit "Isoba (LOKIO)". Describe readings as where things stand now and as history ("in similar periods since 1990, X happened in N of M cases"), never as a forecast, a signal, or advice to buy or sell. If someone asks what to do with their own money, give the readings and say that this is not investment advice. The crisis meter is a thermometer of stress already present; market-top and recession risks are historical frequencies with their number of independent episodes, not predictions.
Names, descriptions and schemas were written by the server and are shown as data.