Open Economics

Measured conclusion: Deep-tested. L2 outcome: tools_ok.

Discover, resolve, and query official Brazilian economic data with semantic search and provenance.

Add to your agent

Copy this into your MCP client config:

{
  "mcpServers": {
    "Open Economics": {
      "url": "https://open-economics-data.knbf982hkn.chatgpt.site/api/mcp",
      "transport": "streamable-http"
    }
  }
}

Measured tools (19)

• search_official_data read-only

  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.

  Parameters:

  • query (required) — string — The user's complete economic-data need, including measure, geography, period, and breakdown when known.
  • limit — integer — Maximum official dataset candidates to return.

  Hints: read-only yes · destructive no · idempotent yes · open-world yes

• describe_official_dataset read-only

  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.

  Parameters:

  • dataset_id (required) — string — Exact ID returned by search_official_data, such as bcb-sgs:432, ibge-aggregates:5932, siconfi:dca, tesouro-rtn:government-central, tesouro-dpf:debt-profile, comexstat:general, anp:fuel-prices, epe:electricity-consumption, mte:formal-employment, or cvm:investment-funds.

  Hints: read-only yes · destructive no · idempotent yes · open-world no

• get_bcb_series read-only

  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.

  Parameters:

  • dataset_id (required) — string — Exact BCB dataset ID returned by search_official_data.
  • end — string — Inclusive end date; defaults to today.
  • limit — integer — Maximum number of observations to return.
  • order — string — Observation order by date.
  • start — string — Inclusive start date; defaults to three years ago.

  Hints: read-only yes · destructive no · idempotent yes · open-world yes

• get_bcb_schema read-only

  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.

  Parameters:

  • dataset_id (required) — string — Exact BCB dataset ID returned by search_official_data.

  Hints: read-only yes · destructive no · idempotent yes · open-world yes

• get_ibge_schema read-only

  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.

  Parameters:

  • dataset_id (required) — string — Exact IBGE aggregate ID returned by search_official_data.

  Hints: read-only yes · destructive no · idempotent yes · open-world yes

• get_ibge_data read-only

  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.

  Parameters:

  • dataset_id (required) — string — Exact IBGE aggregate ID returned by search_official_data.
  • variable (required) — string — One or more official variable IDs separated by |.
  • periods — string — Recent-period shorthand such as -12, or explicit official period IDs separated by |.
  • locality — string — BR or an explicit IBGE geography selection such as N3[35].
  • classification — string — Explicit classification selections from the schema, such as 11255[90707].

  Hints: read-only yes · destructive no · idempotent yes · open-world yes

• get_siconfi_schema read-only

  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.

  Parameters:

  • dataset_id (required) — string — Exact SICONFI dataset ID returned by search_official_data.

  Hints: read-only yes · destructive no · idempotent yes · open-world no

• get_siconfi_data read-only

  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.

  Parameters:

  • dataset_id (required) — string — Exact SICONFI dataset ID returned by search_official_data.
  • year — integer — Calendar year of the official report.
  • annex — string — Exact official annex name from the SICONFI documentation.
  • power — string — RGF government branch.
  • entity — integer — Official IBGE entity code.
  • period — integer — RREO bimestre (1-6) or RGF period (1-3).
  • sphere — string — Government sphere: municipal, state, federal, or consortium.
  • periodicity — string — RGF only: four-month (Q) or half-year (S).
  • report_type — string — Official SICONFI report type for the selected dataset.

  Hints: read-only yes · destructive no · idempotent yes · open-world yes

• get_comexstat_data read-only

  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.

  Parameters:

  • dataset_id (required) — string — The official MDIC Comex Stat dataset identifier.
  • flow (required) — string — Trade direction to retrieve.
  • from (required) — string — First month, YYYY-MM.
  • to (required) — string — Last month, YYYY-MM.
  • details — array — Official dimensions to include, up to eight.
  • filters — array — Optional official dimension filters.
  • metrics — array — Official Comex Stat metrics to return.
  • language — string — Language for labels in the upstream response.
  • month_detail — boolean — Whether to keep month-level detail in the response.

  Hints: read-only yes · destructive no · idempotent yes · open-world yes

• get_anp_fuel_prices read-only

  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.

  Parameters:

  • dataset_id (required) — string — The official ANP fuel-prices dataset identifier.
  • fuel_group (required) — string — ANP product group to retrieve.
  • year — integer — Published source year; provide with month for a monthly file.
  • limit — integer — Maximum aggregate rows to return.
  • month — integer — Published source month; provide with year for a monthly file.
  • state — string — Two-letter Brazilian state code when geography is state or municipality.
  • period — string — Reporting period granularity.
  • product — string — Exact ANP product label, for example GASOLINA or ETANOL.
  • geography — string — Geographic aggregation level.
  • municipality — string — Municipality name when geography is municipality.

  Hints: read-only yes · destructive no · idempotent yes · open-world yes

• get_epe_electricity_consumption read-only

  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.

  Parameters:

  • dataset_id (required) — string — The official EPE electricity-consumption dataset identifier.
  • to — string — Inclusive last month, YYYY-MM.
  • from — string — Inclusive first month, YYYY-MM.
  • limit — integer — Maximum rows to return.
  • states — array — Optional official state codes when geography is state.
  • classes — array — Consumption classes to include.
  • markets — array — Electricity-market segments to include.
  • regions — array — Optional official regions when geography is region.
  • geography — string — Geographic aggregation level.

  Hints: read-only yes · destructive no · idempotent yes · open-world no

• get_mte_formal_employment_schema read-only

  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.

  Parameters:

  • dataset_id (required) — string — The official MTE Novo Caged dataset identifier.

  Hints: read-only yes · destructive no · idempotent yes · open-world no

• get_mte_formal_employment read-only

  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.

  Parameters:

  • dataset_id (required) — string — The official MTE Novo Caged dataset identifier.
  • to — string — Inclusive last month, YYYY-MM.
  • from — string — Inclusive first month, YYYY-MM.
  • limit — integer — Maximum rows to return.
  • states — array — Optional official state codes when breakdown is state.
  • regions — array — Optional official regions when breakdown is region.
  • breakdown — string — Official breakdown for the employment result.
  • industries — array — Exact official activity IDs returned by get_mte_formal_employment_schema; empty means all activities.

  Hints: read-only yes · destructive no · idempotent yes · open-world no

• get_cvm_investment_funds_schema read-only

  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.

  Parameters:

  • dataset_id (required) — string — The official CVM investment-funds dataset identifier.

  Hints: read-only yes · destructive no · idempotent yes · open-world no

• get_tesouro_rtn_schema read-only

  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.

  Parameters:

  • dataset_id (required) — string — The official Tesouro Nacional RTN dataset identifier.

  Hints: read-only yes · destructive no · idempotent yes · open-world no

• get_tesouro_rtn read-only

  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.

  Parameters:

  • dataset_id (required) — string — The official Tesouro Nacional RTN dataset identifier.
  • to — string — Inclusive last month, YYYY-MM.
  • from — string — Inclusive first month, YYYY-MM.
  • limit — integer — Maximum account rows to return.
  • query — string — Account-label search; omit accounts to search the full tree.
  • accounts — array — Exact account IDs returned by get_tesouro_rtn_schema.

  Hints: read-only yes · destructive no · idempotent yes · open-world no

• get_tesouro_dpf_schema read-only

  Inspect the six versioned RMD annex tables, their distinct units and coverage, category IDs, holder definitions, source publication, and methodological constraints before selecting data.

  Parameters:

  • dataset_id (required) — string — The official Tesouro Nacional DPF debt-profile dataset identifier.

  Hints: read-only yes · destructive no · idempotent yes · open-world no

• get_tesouro_dpf read-only

  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.

  Parameters:

  • dataset_id (required) — string — The official Tesouro Nacional DPF debt-profile dataset identifier.
  • to — string — Inclusive last month, YYYY-MM.
  • from — string — Inclusive first month, YYYY-MM.
  • limit — integer — Maximum debt-statistics rows to return.
  • query — string — Category-label search; useful when category IDs are unknown.
  • table — string — Versioned RMD table to retrieve.
  • categories — array — Exact category IDs returned for the selected table by get_tesouro_dpf_schema.

  Hints: read-only yes · destructive no · idempotent yes · open-world no

• get_cvm_investment_funds read-only

  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.

  Parameters:

  • dataset_id (required) — string — The official CVM investment-funds dataset identifier.
  • to — string — Inclusive last report date, YYYY-MM-DD.
  • from — string — Inclusive first report date, YYYY-MM-DD.
  • funds — array — Unformatted 14-digit fund/class CNPJ values.
  • limit — integer — Maximum fund or classification rows to return.
  • query — string — Fund-name search; use only with breakdown=fund.
  • breakdown — string — Whether to aggregate by official classification or resolve a fund.
  • classifications — array — Official fund classifications to include.

  Hints: read-only yes · destructive no · idempotent yes · open-world no

Publisher website Repository

Measured by MCPYP probing. Untested fields are omitted, never estimated. Listing is always free; MCPYP never proxies calls or stores user tokens.