ElkassabgiData
A growing family of free academic data libraries: finance, economics, and beyond (ElkassabgiData).
我该使用它吗
质量与安全性
发现(1)
- LOW在 get_econ_series_metadata 中
基于对工具定义和协议合规性的自动分析。
上下文开销
这是每次将服务器的工具加载到模型上下文窗口时所消耗的大致 token 数。数值越高,可用于其他任务的注意力就越少。
安装
一键安装
将以下内容添加到你的 `claude_desktop_config.json` 文件中:
{
"mcpServers": {
"elkassabgidata": {
"url": "https://elkassabgidata-mcp.elkassabgi.workers.dev/mcp"
}
}
}远程端点
https://elkassabgidata-mcp.elkassabgi.workers.dev/mcpstreamable-http它能做什么
工具清单
工具(12)
🟢search_econ_series(query, source, limit, offset, lang)
Search the Econ Data Library catalog (billions of series from hundreds of sources: national accounts, prices, trade, labor, energy, markets…). Free, no key needed. Returns series ids usable with get_econ_series. Page with offset; lang returns source-official translated titles where the publisher provides them.
输入模式
{
"type": "object",
"properties": {
"query": {
"type": "string",
"minLength": 2,
"description": "Free-text search, e.g. 'germany inflation' or 'GDP per capita'"
},
"source": {
"type": "string",
"description": "Restrict to one source id, e.g. 'worldbank', 'ecb', 'imf_weo'"
},
"limit": {
"type": "integer",
"minimum": 1,
"maximum": 50,
"default": 15
},
"offset": {
"type": "integer",
"minimum": 0,
"default": 0,
"description": "Skip this many results (paging). The API caps how deep it pages and says so if exceeded."
},
"lang": {
"type": "string",
"enum": [
"en",
"ar",
"es",
"fr",
"ru",
"zh"
],
"default": "en",
"description": "Title language. Only official translations are shown; a title without one stays in English."
}
},
"required": [
"query"
],
"additionalProperties": false,
"$schema": "http://json-schema.org/draft-07/schema#"
}🟢get_econ_series(series_id, date_from, date_to, max_rows)
Download an economic time series as rows (long format: date, value) with its citation and license. REQUIRES the free ElkassabgiData API key. Use date_from/date_to to window long series.
输入模式
{
"type": "object",
"properties": {
"series_id": {
"type": "string",
"description": "Exact catalog id from search_econ_series, e.g. 'worldbank:NY.GDP.MKTP.CD:DEU'"
},
"date_from": {
"type": "string",
"pattern": "^\\d{4}-\\d{2}-\\d{2}$"
},
"date_to": {
"type": "string",
"pattern": "^\\d{4}-\\d{2}-\\d{2}$"
},
"max_rows": {
"type": "integer",
"minimum": 10,
"maximum": 2000,
"default": 400
}
},
"required": [
"series_id"
],
"additionalProperties": false,
"$schema": "http://json-schema.org/draft-07/schema#"
}🟢get_econ_series_metadata(series_id)
Full metadata for one econ series: title, frequency, geography, unit, license (incl. commercial-use flag), attribution/citation, coverage dates. Free, no key needed.
输入模式
{
"type": "object",
"properties": {
"series_id": {
"type": "string"
}
},
"required": [
"series_id"
],
"additionalProperties": false,
"$schema": "http://json-schema.org/draft-07/schema#"
}🟢list_econ_sources(contains)
List the Econ Data Library's sources (statistical offices, monetary authorities, IGOs, research datasets) with their licenses, counted live. Free.
输入模式
{
"type": "object",
"properties": {
"contains": {
"type": "string",
"description": "Case-insensitive filter on source id/name, e.g. 'bank' or 'imf'"
}
},
"additionalProperties": false,
"$schema": "http://json-schema.org/draft-07/schema#"
}🟢get_data_freshness(source)
Live per-source update status straight from the automated updater's ledger: last successful update, data frontier, and honest stale/failure flags (dates are NEVER fabricated — a silent upstream outage shows here as stale, not papered over). Free.
输入模式
{
"type": "object",
"properties": {
"source": {
"type": "string",
"description": "One source id; omit for the full board"
}
},
"additionalProperties": false,
"$schema": "http://json-schema.org/draft-07/schema#"
}🟢get_econ_bundle_manifest(ids, source)
A citable bundle manifest (Frictionless data package) for several econ series - up to 50 explicit ids, or every series of one small source (up to 1,000 series): the per-series download URLs grouped by source, each source's attribution and licence, and any id that could not be resolved (reported, never dropped). The URLs serve the CURRENT data - this is not a frozen vintage. Free, no key needed for the manifest; downloading the URLs needs the key.
输入模式
{
"type": "object",
"properties": {
"ids": {
"type": "array",
"items": {
"type": "string",
"minLength": 3
},
"minItems": 1,
"maxItems": 50,
"description": "Up to 50 exact catalog ids from search_econ_series"
},
"source": {
"type": "string",
"description": "One source id - every series of that source, if it has at most 1,000"
}
},
"additionalProperties": false,
"$schema": "http://json-schema.org/draft-07/schema#"
}🟢get_hf_download_link(ticker, dataset, version, format)
Authenticated download instructions for HF Data Library's 1-minute OHLCV bars (per-ticker US stocks/ETFs from IEX Exchange HIST, 2022-03-07 onward; parquet or csv) or the 25 pre-computed academic variables. Each file holds a ticker's whole history, so it is fetched by YOUR code, not returned inline. HF downloads are paused while the dataset is restructured (the URL answers 503 data_paused). Works with the same ElkassabgiData key.
输入模式
{
"type": "object",
"properties": {
"ticker": {
"type": "string",
"pattern": "^[A-Za-z0-9.]{1,10}$",
"description": "e.g. AAPL, SPY"
},
"dataset": {
"type": "string",
"enum": [
"bars",
"variables",
"quality"
],
"default": "bars"
},
"version": {
"type": "string",
"enum": [
"clean",
"raw"
],
"default": "clean"
},
"format": {
"type": "string",
"enum": [
"parquet",
"csv"
],
"default": "parquet",
"description": "csv only applies to bars"
}
},
"required": [
"ticker"
],
"additionalProperties": false,
"$schema": "http://json-schema.org/draft-07/schema#"
}🟢get_hf_variables_dictionary
The exact definitions/formulas of HF Data Library's 25 pre-computed academic variables (realized volatility family, spreads, jumps, liquidity, data-quality). Verbatim from the published dictionary. Free.
输入模式
{
"type": "object",
"properties": {},
"$schema": "http://json-schema.org/draft-07/schema#"
}🟢list_ip_bundles
List the IP Data Library's snapshot-pinned patent/innovation bundles (patent-level measures on US patents; assignee-year panels) with sizes, vintages and download paths. Free, no key needed.
输入模式
{
"type": "object",
"properties": {},
"$schema": "http://json-schema.org/draft-07/schema#"
}🟢get_ip_download_link(file, vintage)
Authenticated download instructions for an IP Data Library bundle — patent-level innovation measures (citations, originality/generality, grant lag, team size) or the assignee-year panel. Parquet, full-history files fetched by YOUR code, not returned inline. Works with the same ElkassabgiData key as every family library.
输入模式
{
"type": "object",
"properties": {
"file": {
"type": "string",
"enum": [
"patent_measures.parquet",
"assignee_year.parquet"
]
},
"vintage": {
"type": "string",
"pattern": "^v[\\w.-]+$",
"description": "Snapshot vintage from list_ip_bundles; omit for the newest"
}
},
"required": [
"file"
],
"additionalProperties": false,
"$schema": "http://json-schema.org/draft-07/schema#"
}🟢get_family_status
Live status of the whole ElkassabgiData family - HF, Econ and IP: each library's headline stats and data currency, read live. Free.
输入模式
{
"type": "object",
"properties": {},
"$schema": "http://json-schema.org/draft-07/schema#"
}🟢get_auth_status
Whether this MCP connection has an ElkassabgiData API key configured (masked — the key itself is never echoed), and how to add one.
输入模式
{
"type": "object",
"properties": {},
"$schema": "http://json-schema.org/draft-07/schema#"
}社区
证据