El Tablero: Argentina economic data
Argentine economic statistics from official sources (BCRA, INDEC): FX, inflation, rates, reserves.
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": {
"argentina-economic-data": {
"url": "https://eltablero.ar/api/mcp"
}
}
}遠端端點
https://eltablero.ar/api/mcpstreamable-http它能做什麼
工具清單
工具（5）
🟢search_series(query)
Find Argentine economic time series by keywords and get their keys. Call this first whenever you don't already know a series key, then pass the key to get_series (history) or get_projection (forecast). Covers BCRA (exchange rates, reserves, interest rates, monetary aggregates, UVA, CER), INDEC via datos.gob.ar (inflation, activity, wages, trade, employment, poverty) and derived series (real rate, FX gap). Matches every word, ignoring accents and case; series names are in Spanish, so Spanish keywords work best ("inflacion", "dolar", "reservas", "badlar", "salarios"). Returns up to 15 matches with key, name, category, source and page URL; an empty list means no match, not an error. Read-only, no side effects, no authentication. Rate limited to 60 calls per minute per IP. Data updates at most once per business day.
輸入結構描述
{
"type": "object",
"properties": {
"query": {
"type": "string",
"minLength": 1,
"maxLength": 120,
"description": "Keywords to match against series names and categories, e.g. \"inflacion mensual\" or \"tipo de cambio\"."
}
},
"required": [
"query"
],
"$schema": "https://json-schema.org/draft/2020-12/schema"
}輸出結構描述
{
"type": "object",
"properties": {
"attribution": {
"type": "string"
},
"query": {
"type": "string"
},
"results": {
"type": "array",
"items": {
"type": "object",
"properties": {
"key": {
"type": "string"
},
"name": {
"type": "string"
},
"category": {
"type": "string"
},
"source": {
"type": "string"
},
"url": {
"type": "string"
}
},
"required": [
"key",
"name",
"category",
"source",
"url"
],
"additionalProperties": false
}
},
"note": {
"type": "string"
}
},
"required": [
"attribution",
"query",
"results"
],
"$schema": "https://json-schema.org/draft/2020-12/schema",
"additionalProperties": false
}🟢get_series(key, range, from)
Return the historical values of one series with its metadata (name, unit, frequency, source, page URL, last date and value). Use it for past and current values; use get_projection for future ones. Needs a key from search_series; well-known keys: bcra:27 monthly inflation, bcra:28 annual inflation, bcra:4 retail USD rate, bcra:5 wholesale USD rate, bcra:1 reserves, bcra:7 BADLAR rate, bcra:44 TAMAR rate, bcra:31 UVA, bcra:30 CER. Without range or from it returns the last year for daily series and the last five years for the rest. At most 500 points, the most recent ones; a note says how many older points were left out. An unknown key returns an error that asks to search first. Read-only, no side effects, no authentication. Rate limited to 60 calls per minute per IP. Data updates at most once per business day.
輸入結構描述
{
"type": "object",
"properties": {
"key": {
"type": "string",
"minLength": 3,
"maxLength": 120,
"description": "Series key with its source prefix, as returned by search_series: \"bcra:27\", \"datos:143.3_NO_PR_2004_A_31\", \"derivada:brecha_blue\"."
},
"range": {
"description": "Time window ending at the last available value: 1m, 3m, 6m, 1y, 5y or max (full history). Ignored if from is given.",
"type": "string",
"enum": [
"1m",
"3m",
"6m",
"1y",
"5y",
"max"
]
},
"from": {
"description": "Start date as YYYY-MM or YYYY-MM-DD; rounded down to the first day of that month. Takes precedence over range.",
"type": "string",
"pattern": "^\\d{4}-\\d{2}(-\\d{2})?$"
}
},
"required": [
"key"
],
"$schema": "https://json-schema.org/draft/2020-12/schema"
}輸出結構描述
{
"type": "object",
"properties": {
"attribution": {
"type": "string"
},
"key": {
"type": "string"
},
"name": {
"type": "string"
},
"category": {
"type": "string"
},
"unit": {
"type": "string"
},
"frequency": {
"type": "string",
"description": "D daily, M monthly, T quarterly, S semiannual, A annual"
},
"source": {
"type": "string"
},
"url": {
"type": "string"
},
"last_date": {
"type": "string"
},
"last_value": {
"type": "number"
},
"points": {
"type": "array",
"items": {
"type": "array",
"prefixItems": [
{
"type": "string"
},
{
"type": "number"
}
],
"items": false,
"minItems": 2,
"maxItems": 2
},
"description": "[date YYYY-MM-DD, value], oldest first"
},
"note": {
"type": "string"
}
},
"required": [
"attribution",
"key",
"name",
"category",
"unit",
"frequency",
"source",
"url",
"last_date",
"last_value",
"points"
],
"$schema": "https://json-schema.org/draft/2020-12/schema",
"additionalProperties": false
}🟢get_projection(key, horizon)
Project a series forward: point values with 80% and 95% bands, the models combined (ETS, ARIMA, Theta, chosen by walk-forward backtest), backtest errors and, when the series has one, the BCRA market-expectations survey (REM) median for the same months. Use it for "what's next" questions about inflation, exchange rates, interest rates or reserves; use get_series for past values. It is a statistical reference, not a forecast or advice: say so when you quote it. Needs a key from search_series. Series with too little history return an error. Read-only, no side effects, no authentication. Rate limited to 60 calls per minute per IP. Data updates at most once per business day.
輸入結構描述
{
"type": "object",
"properties": {
"key": {
"type": "string",
"minLength": 3,
"maxLength": 120,
"description": "Series key as returned by search_series, e.g. \"bcra:27\"."
},
"horizon": {
"description": "How far ahead: calendar days for daily series (default 30, up to 183), periods for the rest (default 12 months, 8 quarters).",
"type": "integer",
"minimum": 1,
"maximum": 183
}
},
"required": [
"key"
],
"$schema": "https://json-schema.org/draft/2020-12/schema"
}輸出結構描述
{
"type": "object",
"properties": {
"attribution": {
"type": "string"
},
"key": {
"type": "string"
},
"name": {
"type": "string"
},
"unit": {
"type": "string"
},
"engine": {
"type": "string",
"enum": [
"lote",
"sitio"
],
"description": "lote: daily batch models; sitio: computed on request"
},
"method": {
"type": "string"
},
"members": {
"type": "array",
"items": {
"type": "object",
"properties": {
"method": {
"type": "string"
},
"weight": {
"type": "number"
}
},
"required": [
"method",
"weight"
],
"additionalProperties": false
}
},
"backtest": {
"type": "object",
"properties": {
"mae": {
"type": "number"
},
"rmse": {
"type": "number"
},
"mape": {
"type": [
"number",
"null"
]
},
"coverage95": {
"type": "number"
},
"n": {
"type": "number"
}
},
"required": [
"mae",
"rmse",
"mape",
"coverage95",
"n"
],
"additionalProperties": false
},
"benchmark": {
"type": "object",
"properties": {
"method": {
"type": "string"
},
"rmse": {
"type": "number"
}
},
"required": [
"method",
"rmse"
],
"additionalProperties": false
},
"bands": {
"type": "object",
"properties": {
"method": {
"type": "string"
},
"origins": {
"type": "number"
}
},
"required": [
"method",
"origins"
],
"additionalProperties": false
},
"horizon": {
"type": "array",
"items": {
"type": "object",
"properties": {
"date": {
"type": "string"
},
"value": {
"type": "number"
},
"band_80": {
"type": "array",
"prefixItems": [
{
"type": "number"
},
{
"type": "number"
}
],
"items": false,
"minItems": 2,
"maxItems": 2
},
"band_95": {
"type": "array",
"prefixItems": [
{
"type": "number"
},
{
"type": "number"
}
],
"items": false,
"minItems": 2,
"maxItems": 2
}
},
"required": [
"date",
"value",
"band_80",
"band_95"
],
"additionalProperties": false
}
},
"consensus": {
"type": "object",
"properties": {
"survey_date": {
"type": "string"
},
"participants": {
"type": "number"
},
"description": {
"type": "string"
},
"points": {
"type": "array",
"items": {
"type": "object",
"properties": {
"date": {
"type": "string"
},
"median": {
"type": "number"
},
"p25": {
"type": "number"
},
"p75": {
"type": "number"
},
"top10": {
"type": "number"
}
},
"required": [
"date",
"median"
],
"additionalProperties": false
}
}
},
"required": [
"survey_date",
"description",
"points"
],
"additionalProperties": false
},
"disclaimer": {
"type": "string"
}
},
"required": [
"attribution",
"key",
"name",
"unit",
"engine",
"method",
"backtest",
"benchmark",
"bands",
"horizon",
"disclaimer"
],
"$schema": "https://json-schema.org/draft/2020-12/schema",
"additionalProperties": false
}🟢get_weekly_summary(week_ending)
Return one plain-Spanish sentence per indicator (USD retail and wholesale, reserves, interest rates, inflation, UVA) describing how it moved during a closed week, with direction and links, plus the permalink of that week's summary page. Use it for a quick "how did the Argentine economy do this week" overview; use get_series for exact values. Defaults to the last closed week (Monday to Sunday). Read-only, no side effects, no authentication. Rate limited to 60 calls per minute per IP. Data updates at most once per business day.
輸入結構描述
{
"type": "object",
"properties": {
"week_ending": {
"description": "Sunday that closes the week, as YYYY-MM-DD. Omit for the last closed week; any other date is anchored to the previous Sunday.",
"type": "string",
"pattern": "^\\d{4}-\\d{2}-\\d{2}$"
}
},
"$schema": "https://json-schema.org/draft/2020-12/schema"
}輸出結構描述
{
"type": "object",
"properties": {
"attribution": {
"type": "string"
},
"week": {
"type": "object",
"properties": {
"from": {
"type": "string"
},
"to": {
"type": "string"
},
"title": {
"type": "string"
}
},
"required": [
"from",
"to",
"title"
],
"additionalProperties": false
},
"url": {
"type": "string"
},
"items": {
"type": "array",
"items": {
"type": "object",
"properties": {
"key": {
"type": "string"
},
"text": {
"type": "string"
},
"direction": {
"type": "number",
"description": "-1 down, 0 flat, 1 up"
},
"url": {
"type": "string"
}
},
"required": [
"key",
"text",
"direction",
"url"
],
"additionalProperties": false
}
}
},
"required": [
"attribution",
"week",
"url",
"items"
],
"$schema": "https://json-schema.org/draft/2020-12/schema",
"additionalProperties": false
}🟢get_release_calendar(from, to)
List the scheduled INDEC releases (CPI inflation, EMAE activity, wages, trade, industry, construction, employment, poverty) between two dates, each with date, time in Argentina, report name, period covered and the series keys it updates. Use it to answer "when is the next inflation figure out" or to know whether a value is about to change. Defaults to the next 60 days from today. Only INDEC for now. Read-only, no side effects, no authentication. Rate limited to 60 calls per minute per IP. Data updates at most once per business day.
輸入結構描述
{
"type": "object",
"properties": {
"from": {
"description": "First day to include, YYYY-MM-DD, Argentina time. Defaults to today.",
"type": "string",
"pattern": "^\\d{4}-\\d{2}-\\d{2}$"
},
"to": {
"description": "Last day to include, YYYY-MM-DD. Defaults to 60 days after from.",
"type": "string",
"pattern": "^\\d{4}-\\d{2}-\\d{2}$"
}
},
"$schema": "https://json-schema.org/draft/2020-12/schema"
}輸出結構描述
{
"type": "object",
"properties": {
"attribution": {
"type": "string"
},
"from": {
"type": "string"
},
"to": {
"type": "string"
},
"time_zone": {
"type": "string"
},
"url": {
"type": "string"
},
"releases": {
"type": "array",
"items": {
"type": "object",
"properties": {
"date": {
"type": "string"
},
"time": {
"type": "string"
},
"source": {
"type": "string"
},
"report": {
"type": "string"
},
"period": {
"type": "string"
},
"series": {
"type": "array",
"items": {
"type": "string"
}
}
},
"required": [
"date",
"time",
"source",
"report",
"period",
"series"
],
"additionalProperties": false
}
}
},
"required": [
"attribution",
"from",
"to",
"time_zone",
"url",
"releases"
],
"$schema": "https://json-schema.org/draft/2020-12/schema",
"additionalProperties": false
}社群
證據