io.github.felipegambettadesouza6-jpg由 GitHub 帳號 felipegambettadesouza6-jpg 發布v2.0.2更新於 Oct 24, 2026
Discover, resolve, and query official Brazilian economic data with semantic search and provenance.
唯讀 MCP 伺服器，把巴西經濟問題解析為官方資料集，並回傳 BCB、IBGE、SICONFI、Comex Stat、ANP、EPE、MTE、CVM 與 Tesouro 的資料及來源資訊。
Web executable，透過 Streamable HTTP。 遠端服務在工作區中設定後即可從網頁執行環境執行。
把這段提示詞貼上到 Claude Code、Codex、Cursor 等代理程式，或 SourceWeft 對話中。代理程式會讀取該伺服器的安裝指南，先向你展示發布者、端點和登入方式，經你同意後再把它新增到你的客戶端。金鑰不會寫進任何命令。
閱讀 https://sourceweft.com/mcp/io.github.felipegambettadesouza6-jpg%2Fopen-economics/install.md，並按其中說明把這個 MCP 伺服器接入我的客戶端。修改任何設定之前，先告訴我它的發布者、端點和登入方式，等我確認。不要把 API 金鑰寫進命令或我會提交的檔案；問我金鑰應從哪裡取得。把它新增到你客戶端的 mcpServers 設定中。
{
"mcpServers": {
"open-economics": {
"type": "http",
"url": "https://open-economics-data.knbf982hkn.chatgpt.site/api/mcp"
}
}
}A free, read-only semantic routing layer for authoritative Brazilian economic data.
Run a real economic question → · Connect the MCP server →
Open Economics 2.0 starts with a real economic-information need, resolves its meaning independently of current coverage, and then routes it to official data. Its synchronized catalog currently exposes 12,875 BCB SGS series and IBGE aggregates, plus direct SICONFI fiscal-report, MDIC Comex Stat, and ANP fuel-price access and versioned EPE electricity-consumption, MTE Novo Caged, CVM investment-fund, Tesouro RTN fiscal, and RMD Federal Public Debt data (12,886 official datasets in total). The 32 convenient v1 series IDs remain compatible.
Discovery, REST, the existing product, and MCP share one semantic core. A resolved concept is kept separate from availability, so an unsupported need is reported explicitly instead of being silently mapped to a nearby series. Units, dimensions, reference periods, source identifiers, raw values, methodology links, and retrieval provenance travel with the data.
For BCB, /api/v2/datasets/bcb-sgs:{code}/observations provides direct series
access with authoritative frequency, unit, source, coverage, formula, and
warning metadata. For IBGE, inspect /schema, then send explicit variable,
periods, locality, and classification selections to /observations.
SICONFI DCA, RREO, and RGF use the same dataset routes while retaining entity,
reporting period, annex, account, column, and raw value. Official
multidimensional structure is preserved instead of flattened away.
Comex Stat preserves trade-flow dimensions and metrics. ANP fuel-price queries
return period/geography/product aggregates calculated from official station
observations, with source counts and the transformation disclosed while station
identity and address fields are excluded. EPE and MTE serve compact, versioned
snapshots of official workbooks: electricity retains geography/class/market,
while adjusted Novo Caged stock and flows retain their separate national,
region/state, or economic-activity breakdowns. CVM daily fund reports retain
fund/class identity and quota values; classification aggregates sum only
additive measures and identify incomplete filing dates. RTN retains its monthly
account hierarchy and above-the-line cash/effective-payment conventions. RMD
debt statistics keep composition, holder, maturity, and cost tables separate,
with their official units, definitions, and publication vintage.
If you already know the exact official identifier and source contract, calling the publisher directly remains the shortest path. Open Economics is useful when the need starts in human language, spans publisher conventions, requires explicit dimensions, or must retain one consistent provenance and error model.
The same observation envelope can retrieve BCB IBC-Br (SGS 24363) and IBGE real GDP growth (SIDRA 5932/6561), without maintaining two date and response parsers:
The runnable multi-source Python example uses both series and prints their official provenance and freshness state.
GET /api/v1/indicators is the discovery endpoint. Its
meta.available_filters field lists every canonical category, frequency,
and source value. It accepts:
Invalid filters are rejected with a structured problem response; they never silently become an empty result set.
Observation requests accept start, end, order=asc|desc, limit=1..5000,
and format=json|csv. Dates use YYYY-MM-DD and end cannot be in the
future. Daily BCB requests are limited to ten years because SGS applies the
same upstream limit.
All JSON series responses use the same envelope:
date is the normalized start date for the reference period; period is the
frequency-aware identifier (YYYY-MM-DD, YYYY-MM, YYYY-QN, or YYYY).
source_date and raw_value are retained exactly from the official publisher.
Read meta.indicator.date_semantics before interpreting stock, flow, or
moving-quarter series.
Use format=csv for a flat download. CSV rows repeat indicator_id,
source_id, source_url, and upstream_url, so exported values retain their
provenance outside the JSON envelope.
All endpoints support CORS and GET, HEAD, and OPTIONS. Successful and
error responses include X-Request-Id; browser clients can also read cache,
timing, and stale-response headers.
Errors use application/problem+json with a stable code, HTTP status,
human-readable title, explanatory detail, and request_id. Common cases
include INVALID_DATE, INVALID_CATEGORY, INDICATOR_NOT_FOUND,
UPSTREAM_CONNECTION_ERROR, and UPSTREAM_TIMEOUT.
The API caches successfully normalized source responses in D1 when configured.
If a refresh fails and a previous matching snapshot exists, it is returned with
meta.stale: true, meta.cache: "stale", and HTTP Warning: 110. A cache
read or write failure is treated as a cache bypass, never as a data failure.
The service is currently best-effort and has no uptime SLA. See RELIABILITY.md for the explicit availability, freshness, change-management, and incident-reporting policy.
status values.There are 32 curated indicators across inflation, interest rates, currencies, activity, labor, credit, fiscal, external, and markets. Values are never fabricated, forward-filled, or silently sign-inverted. BCB NFSP fiscal series retain BCB's financing-requirement sign convention.
BCB catalog data is published under ODbL; preserve its attribution and share-alike obligations when distributing adapted databases. Attribute IBGE as IBGE/SIDRA and retain its source links and terms. Each indicator response has the authoritative URLs and license applicable to that series.
Node.js 22.13+ is required.
Examples are available in examples/python.py,
examples/multi_source_python.py, and
examples/javascript.mjs. The D1 migration in
drizzle/ is the deployment record for cache snapshots.
The API implementation is released under the MIT License. Upstream data remains governed by each publisher's own terms and licenses.
來源：README.md，提交 d8ba0fc
Search Brazilian official economic data
Start here for a natural-language Brazilian economic-information need in Portuguese or English. Resolves the economic concept independently of current coverage, returns ranked official datasets, stable-series shortcuts, confidence, missing source integrations, and an explicit unresolved/partial state. Use this before any data query when the exact official dataset ID is unknown.
limitquery必填Describe an official dataset
Get identity, publisher, collection, provenance links, query capability, and any stable Open Economics series shortcuts for an exact dataset ID returned by search_official_data. This does not fetch observations.
dataset_id必填Get observations from a BCB SGS series
Retrieve official observations and authoritative schema metadata for an exact BCB SGS dataset ID. Use only after search_official_data identifies the series. Dates, units, periodicity, source, and raw values are preserved; generic access does not guess transformations.
endlimitorderstartdataset_id必填Inspect BCB series meaning and units
Fetch authoritative metadata for an exact BCB SGS series, including full name, subject hierarchy, periodicity, unit, source, coverage dates, decimals, formula, and warnings. Use when interpreting a BCB series without retrieving observations.
dataset_id必填Inspect an IBGE aggregate's measures and dimensions
Fetch official metadata for an IBGE aggregate selected by search_official_data. Always use this before get_ibge_data unless the official variable, locality, and classification IDs are already known. It prevents guessing a measure or dimensional slice.
dataset_id必填Query multidimensional IBGE data
Retrieve an explicit slice of an IBGE aggregate after inspecting its schema. Returns variables containing classification selections, geographies, and observations; official suppression, missing, quality-flag, and zero states remain distinct.
periodslocalityvariable必填dataset_id必填classificationInspect a SICONFI fiscal report
Get the meaning and required selection fields for an exact SICONFI dataset returned by search_official_data. Use this before get_siconfi_data so entity, reporting period, report type, government branch, and annex are explicit rather than guessed.
dataset_id必填Query official SICONFI fiscal data
Retrieve an explicit official SICONFI DCA, RREO, RGF, or entity-registry selection. First inspect the schema. This tool preserves account, column, annex, period, entity, raw value fields, and upstream provenance without aggregating or substituting concepts.
yearannexpowerentityperiodspheredataset_id必填periodicityreport_typeQuery official Brazilian merchandise trade
Retrieve a bounded, explicit MDIC Comex Stat export or import slice from 1997 onward. Use comexstat:general only after search_official_data. Select period, dimensions, metrics, and optional official filter codes; partner, product, state, transport, classification, and raw metric fields remain attached to the result.
to必填flow必填from必填detailsfiltersmetricslanguagedataset_id必填month_detailQuery official ANP fuel prices
Retrieve auditable fuel and GLP price statistics calculated from official ANP station observations. Omit year and month for the rolling latest four weeks, or provide both for a published monthly file from 2023 onward. Results retain period, product, geography, unit, sample count, source URL, and the disclosed aggregation method while excluding station identity and addresses.
yearlimitmonthstateperiodproductgeographydataset_id必填fuel_group必填municipalityQuery official electricity consumption
Retrieve monthly EPE electricity consumption and consumer counts from 2004 onward. Select a bounded period, country/region/UF geography, consumption classes, and regulated/free market. The response identifies the exact synchronized official workbook version and discloses aggregation across source system rows.
tofromlimitstatesclassesmarketsregionsgeographydataset_id必填Inspect Novo Caged dimensions and measures
Inspect the official adjusted Novo Caged selection contract, source vintage, measure meanings, available industry IDs, and the constraint that geography and industry come from separate official tables. Use before an industry query.
dataset_id必填Query official formal-employment stock and flows
Retrieve revised monthly Novo Caged stock, admissions, dismissals, balance, and relative change from 2020 onward. Select exactly one official breakdown: country, region, state, or economic activity. The response preserves the MTE workbook vintage and never synthesizes state-by-industry values.
tofromlimitstatesregionsbreakdowndataset_id必填industriesInspect CVM investment-fund measures and dimensions
Inspect the synchronized CVM daily-report window, official classifications, fund-search contract, measure meanings, and aggregation constraints. Use before querying a fund by name or comparing classes.
dataset_id必填Inspect Government Central fiscal accounts
Inspect RTN table 1.2 account IDs, hierarchy, current-value unit, coverage, source vintage, and above/below-the-line constraints. Use before selecting revenue or expenditure categories.
dataset_id必填Query Government Central revenue, expenditure, and result
Retrieve monthly current-value RTN accounts from 1997 onward. Defaults to total revenue, transfers, net revenue, total expenditure, and the above-the-line primary result; select exact account IDs or search account labels for detail.
tofromlimitqueryaccountsdataset_id必填Inspect Federal Public Debt statistics
Inspect the six versioned RMD annex tables, their distinct units and coverage, category IDs, holder definitions, source publication, and methodological constraints before selecting data.
dataset_id必填Query Federal Public Debt statistics
Retrieve one official monthly RMD table at a time: debt composition, DPMFi holders, average maturity, average maturity by indexer, monthly cost, or twelve-month cost. Units remain table-specific and are never combined.
tofromlimitquerytablecategoriesdataset_id必填Query official CVM investment-fund reports
Retrieve daily CVM aggregates by official fund classification or resolve a fund/class latest report by CNPJ or name. Net assets and flows are additive; quota values stay fund-level; reported holder totals are not deduplicated people.
tofromfundslimitquerybreakdowndataset_id必填classifications已滿足適用檢查項的 100%
該評分衡量此收錄條目的完整程度，依據註冊中心條目、端點與公開來源計算得出。它不是對伺服器本身的評價，也不表示伺服器安全或目前可用：可連通性是帶日期的檢查結果，評分也不包含安裝量或使用者評價。
curl --fail --silent \ "https://open-economics-data.knbf982hkn.chatgpt.site/api/v2/search?q=desemprego%20desde%202015"
curl --fail --silent \ "https://open-economics-data.knbf982hkn.chatgpt.site/api/v2/datasets/ibge-aggregates%3A6381/schema"curl --fail --silent "https://open-economics-data.knbf982hkn.chatgpt.site/api/v1/indicators/br-ibc-br/observations?start=2024-01-01"curl --fail --silent "https://open-economics-data.knbf982hkn.chatgpt.site/api/v1/indicators/br-gdp-real-yoy/observations?start=2024-01-01"curl --fail --silent "https://open-economics-data.knbf982hkn.chatgpt.site/api/v1"curl --fail --silent "https://open-economics-data.knbf982hkn.chatgpt.site/api/v1/indicators?q=ipca&source=ibge"curl --fail --silent "https://open-economics-data.knbf982hkn.chatgpt.site/api/v1/indicators/br-ipca-monthly"curl --fail --silent \ "https://open-economics-data.knbf982hkn.chatgpt.site/api/v1/indicators/br-ipca-monthly/observations?start=2024-01-01&end=2024-12-31"
curl --fail --silent \ "https://open-economics-data.knbf982hkn.chatgpt.site/api/v1/indicators/br-selic-target/observations?start=2025-01-01&order=desc&limit=12"
curl --fail --silent \ "https://open-economics-data.knbf982hkn.chatgpt.site/api/v1/indicators/br-selic-target/latest"{ "data": [ { "date": "2024-01-01", "period": "2024-01", "source_date": "202401", "value": 0.42, "raw_value": "0.42", "status": "observed" } ], "meta": { "indicator": { "id": "br-ipca-monthly", "unit_symbol": "%" }, "provenance": { "upstream_url": "…", "retrieved_at": "…" }, "returned": 1, "available": 1, "truncated": false }}npm installnpm run devnpm run lintnpm testnpm run catalog:epe-syncnpm run catalog:mte-syncnpm run catalog:cvm-syncnpm run catalog:rtn-syncnpm run catalog:dpf-sync