List the IBGE microdata families currently supported by this local-first MCP.

Use this first when deciding whether the server can help with PNAD Contínua, POF, or another IBGE microdata source. This tool does not download data.

List official IBGE microdata download files for a supported survey.

For PNAD Contínua quarterly files, pass survey="pnadc_trimestral" and a year such as 2024. For POF, pass survey="pof"; this returns known edition-level public archives for 2017-2018, 2008-2009, and 2002-2003. This tool lists URLs only; it does not download large ZIP files.

List downloadable files in any official ftp.ibge.gov.br directory.

Use this for IBGE microdata families that do not yet have a survey-specific convenience tool. It only lists links; it does not download file bodies.

Crawl official ftp.ibge.gov.br directories with strict limits to find public microdata directories, data ZIPs, and documentation/layout files.

Use this when a survey-specific convenience listing is not implemented yet. The tool only fetches directory pages; it does not download microdata archives.

Parse a local official IBGE SAS/TXT input layout and return variable names, positions, widths, types, and descriptions.

Use this before converting fixed-width microdata to Parquet so you can choose selectedVariables without opening the full dictionary manually.

Fetch HTTP HEAD metadata for an official IBGE microdata file URL.

Use this before downloading a large file to check its size, content type, update timestamp, and ETag.

Download or reuse a selected official IBGE microdata file in a local cache path.

This is explicit and local-first: the tool mirrors the ftp.ibge.gov.br URL under cacheRoot, checks official HEAD content-length metadata, and skips re-downloading when a cached file has the expected byte size. Use ibge_microdata_file_info first for large files so the user understands size before downloading.

List files already downloaded into a local IBGE microdata cache.

Use this after one or more ibge_microdata_download_file calls to rediscover local paths, original ftp.ibge.gov.br URLs, byte sizes, and modification timestamps without hitting IBGE again. The tool only reads the local cache and supports limit/offset pagination.

Preview or delete selected files from the local IBGE microdata cache.

The tool only considers files under cacheRoot/ftp.ibge.gov.br and requires at least one filter such as olderThanDays, minBytes, or urlPrefix. It defaults to dryRun=true, so use it first to preview what would be deleted. Set dryRun=false only after the user explicitly agrees to delete the matched cached files.

Analyze an extracted PNAD Contínua fixed-width TXT file using the official SAS/TXT input layout.

This is a PNAD-specific convenience helper for a small predefined set of variables. For custom public workflows, prefer converting selected variables to Parquet and using the generic query or weighted-distribution tools. Use it after downloading/extracting PNAD microdata locally when this predefined summary matches your task.

Analyze a PNAD Contínua fixed-width TXT entry directly inside a local ZIP archive.

This is a PNAD-specific convenience helper for a small predefined set of variables and avoids extracting the full microdata TXT first. For custom public workflows, prefer converting selected variables to Parquet and using the generic query or weighted-distribution tools. Use it after downloading a PNAD ZIP and extracting or otherwise providing the official input layout when this predefined summary matches your task.

List file entries inside a local IBGE ZIP archive without extracting the archive.

Use this after ibge_microdata_download_file to discover the exact TXT, documentation, or table names inside official IBGE microdata ZIPs.

Extract one selected file from a local IBGE ZIP archive to a local path.

Use this to pull the PNAD fixed-width TXT file or the official input layout out of a downloaded ZIP without unpacking everything manually.

Convert a local fixed-width IBGE microdata TXT file into a local Parquet file using an official SAS/TXT input layout.

This is the generic optimization path for repeated analysis: use it for PNAD, POF, or other IBGE microdata families that publish fixed-width TXT files and input layouts. Select only needed variables to keep Parquet files small.

Convert one fixed-width TXT entry inside a local IBGE ZIP archive into a local Parquet file using an official SAS/TXT input layout.

This avoids extracting the full TXT first, writes a local columnar file, and is useful before running repeated DuckDB queries over selected PNAD, POF, or other IBGE variables.

Run a bounded read-only DuckDB SELECT/WITH query over local Parquet files.

The provided files are exposed as a view named microdata. Use this after converting IBGE fixed-width microdata to Parquet when you need repeated summaries, grouped tabulations, or weighted statistics without reparsing the original TXT files.

Run a bounded read-only DuckDB SELECT/WITH query over multiple named local Parquet views.

Use this for relational microdata workflows, especially POF, where separate records such as domicilio, morador, and rendimento_trabalho should be joined by their shared keys after conversion to Parquet.

Calculate weighted distribution summaries and top-bracket shares over local IBGE Parquet views.

Use this after converting microdata to Parquet when you need income, consumption, wealth, or other distribution statistics without hand-writing all aggregation SQL. Provide unitSql as a read-only SELECT/WITH query that returns a numeric value column, a numeric weight column, and optionally a group column. The tool ranks units by value, computes total weight/value/mean, group population and value shares, and top brackets such as top 1%, 5%, and 10%. Cutoff ties are allocated proportionally across groups.

Inspect local Parquet files as named DuckDB views and return columns, DuckDB types, optional row counts, and optional sample rows.

Use this before writing join queries over POF or other relational microdata records so the agent can see actual column names and types.

Profile local Parquet files as named DuckDB views and return bounded exploratory statistics.

Use this after converting IBGE fixed-width microdata to Parquet and before writing custom SQL. The tool reports row counts, column types, null/non-null counts, optional numeric min/max/mean, frequent values, and optional sample rows. By default it profiles the first 25 columns to keep exploration bounded; pass columns for a precise subset.

Parse the POF Excel variable dictionary and return record sheets, mapped TXT data entries, record lengths, and variable layouts.

Use this after downloading/extracting the POF documentation ZIP to understand which POF record to convert and which variables to select.

Convert one POF fixed-width TXT record inside a local Dados ZIP into Parquet using the POF Excel dictionary workbook.

This is the POF-specific optimized path: it understands POF record sheets, maps them to ZIP entries such as DOMICILIO.txt or RENDIMENTO_TRABALHO.txt, applies implied decimal scaling, and writes a local Parquet file for DuckDB queries.