IBGE Brasil MCP Server

Live, exact Brazilian public data for your AI assistant — with provenance, not guesswork.

Ask an LLM "what was Belo Horizonte's population in the 2022 Census?" and you get a plausible number from its training data: maybe right, maybe outdated, with no source. ibge-br-mcp instead has your assistant query the official IBGE APIs in real time — returning the exact figure together with the table and period it came from.

🇧🇷 Leia em Português

This server implements the Model Context Protocol (MCP) to give AI assistants live, structured access to Brazil's public geographic, demographic, economic, and health data — sourced from the IBGE APIs (including health indicators served through IBGE's SIDRA system).

See it in action

Ask your assistant, in English or Portuguese:

• "What was Belo Horizonte's population in the 2022 Census?" → ibge_cidades / ibge_censo
• "List the municipalities of Espírito Santo." → ibge_municipios
• "Compare GDP across the Southeast state capitals." → ibge_comparar

The answers come live from the official IBGE APIs — exact figures with the table and period they came from, not numbers guessed from training data.

Want to see a whole analysis rather than a single answer? The end-to-end demo works one real question — which state grew most between the 2010 and 2022 Censuses, and what drove it — from first call to conclusion, with every figure as it came back. The practical examples are seven shorter recipes, including ranking all 5,570 municipalities in a single call.

Features

• 23 tools covering all major IBGE data domains — 21 ibge_* data tools plus search/fetch for ChatGPT Deep Research
• Provenance block on every response — source, canonical URL, reference period, real extraction timestamp, ready-to-use citation, and legal regime (see Data provenance)
• Reference resources & analysis prompts (MCP catalogs + ready-made templates)
• 565 automated tests — 88% overall coverage, 92% across the tools
• Automatic caching with configurable TTL for optimal performance
• Retry mechanism with exponential backoff for network resilience
• Comprehensive validation for all input parameters
• Standardized error handling with helpful suggestions
• Full TypeScript support with strict typing

📖 Article (in Portuguese): Como achar a tabela certa no SIDRA — e como saber que é a certa — finding the right SIDRA table, the metadata that settles it, a full worked example on 2022 Census data, and the four traps that cost the most. Also published on the site, in Portuguese and English: sidneybissoli.com.

🔌 Tutorial: Querying SIDRA through MCP in Claude and ChatGPT — how to connect this server in claude.ai, Claude Desktop, Claude Code, ChatGPT (developer mode and Deep Research), Cursor, VS Code and Gemini CLI, then one real query end to end with the provenance block it returns. Em português.

Data provenance

Since v3.3.0 every successful tool response carries a provenance block (portfolio contract v1.0), so each number is citable, auditable, and reproducible. The block is emitted on three channels:

1. structuredContent.provenance (parseable, visible to the model) — exactly six keys: source (the IBGE API queried), source_url (canonical URL that reproduces the query), data_vintage (reference period when the source exposes one; null otherwise), retrieved_at (the REAL upstream extraction instant, preserved across cache hits, Brasília time), citation ("Fonte: IBGE — [pesquisa/tabela], [URL], extraído em [data]."), and license — plus attribution, the canonical list of source URLs.
2. _meta under br.com.sidneybissoli.ibge/provenance and .../attribution (out-of-band mirror for audit/UI, zero model tokens).
3. A compact text footer appended to the Markdown, for text-only clients.

The IBGE APIs declare no license of their own; the legal regime is Brazil's open-data framework — Lei 12.527/2011 (LAI) and Decreto 8.777/2016 (unrestricted reuse, free use, obligation limited to crediting the source). Statistics-mode responses (estatisticas=true) and ibge_comparar are marked derived with an explanatory note in the canonical block, since the aggregates are computed server-side from the raw IBGE values.

What each number is, and which version of it. A SIDRA value says neither its period nor whether it is a monthly change, a year-to-date or 12-month accumulation, an index or a level — the record's period column and its Variável label do, and each ibge_indicadores entry is pinned to the one variable its name promises (since 5.7.0; before, nine of them mixed every variable of the table). data_vintage is ordered by the SIDRA period code, so a January–December request reads "janeiro 2024–dezembro 2024". Every value is the version SIDRA publishes at retrieved_at: IBGE revises published figures (quarterly GDP, PNAD reweighting, PIM/PMC/PMS) and keeps no earlier version.

Available Tools

Localities & Geography

Tool	Description
ibge_estados	List Brazilian states with region filtering
ibge_municipios	List municipalities by state or search by name
ibge_localidade	Get details of a locality by IBGE code
ibge_geocodigo	Decode IBGE codes or search codes by name
ibge_vizinhos	Find neighboring municipalities

Statistical Data (SIDRA)

Tool	Description
ibge_sidra	Query SIDRA tables (Census, PNAD, GDP, etc.)
ibge_sidra_tabelas	List and search available SIDRA tables (accent-insensitive; everyday Portuguese resolved to the IBGE's wording, and the response says so)
ibge_sidra_metadados	Get table metadata (variables, periods, levels)
ibge_pesquisas	List IBGE research surveys and their tables

Economic & Social Indicators

Tool	Description
ibge_indicadores	Economic and social indicators (GDP, IPCA, unemployment)
ibge_censo	Census data (1970-2022) with 16 themes
ibge_comparar	Compare indicators across localities with rankings

Municipal Data (Cidades@)

Tool	Description
ibge_cidades	Municipal indicators (population, HDI, GDP per capita, etc.)

International Data

Tool	Description
ibge_paises	Country data following UN M49 methodology

Demographics

Tool	Description
ibge_nomes	Name frequency and rankings in Brazil

Classifications

Tool	Description
ibge_cnae	CNAE (National Classification of Economic Activities)

Maps & Geographic Meshes

Tool	Description
ibge_malhas	Geographic meshes (GeoJSON, TopoJSON, SVG)
ibge_malhas_tema	What a thematic recorte contains (biomes, Legal Amazon, semi-arid, coastal, border strip, metro regions, RIDEs) + the URL to download its geometry

Health

Tool	Description
ibge_datasaude	Health indicators via IBGE's SIDRA

News & Calendar

Tool	Description
ibge_noticias	IBGE news and press releases
ibge_calendario	IBGE release and collection calendar

ChatGPT Deep Research

Tool	Description
search	Searches the IBGE catalog (SIDRA tables, municipalities, known indicators) — OpenAI Deep Research contract
fetch	Returns one catalog document (table metadata, municipality hierarchy + population, indicator series) with its public URL for citation

The two are the only tools without the ibge_ prefix: their names are fixed by the OpenAI contract. For data queries keep using the ibge_* tools.

Which tool should I use?

With 23 tools, several can touch the same topic. Quick guide for the common overlaps:

Population & demographics

You want…	Use
A single municipality/state panel (population, HDI, GDP…)	ibge_cidades
Census data or historical series (1970–2022)	ibge_censo
Rank/compare 2–10 localities on one indicator	ibge_comparar
A macro indicator time series (GDP, IPCA, unemployment…)	ibge_indicadores
A specific SIDRA table / fine control	ibge_sidra
The largest/smallest/mean/median across a whole table	ibge_sidra/ibge_censo/ibge_indicadores/ibge_datasaude with estatisticas=true

Economic indicators

You want…	Use
IPCA, INPC, GDP, unemployment (IBGE, primary source)	ibge_indicadores

Localities & codes

You want…	Use
List/search municipalities	ibge_municipios
List states	ibge_estados
Resolve a name→code at any level, or decode a code's structure	ibge_geocodigo
Full record of one locality you already have the code for	ibge_localidade
Neighboring municipalities	ibge_vizinhos

SIDRA workflow

Discover → inspect → query: ibge_pesquisas / ibge_sidra_tabelas (find a table) → ibge_sidra_metadados (its structure) → ibge_sidra (query). For common data, the wrappers above (ibge_censo, ibge_indicadores, ibge_comparar, ibge_cidades) are usually easier.

Ask in your words, not the IBGE's

The IBGE names its tables in official statistical Portuguese, and ibge_sidra_tabelas matched your words against the table name as a plain substring, accents included — so populacao (no tilde, as anyone types it) returned nothing at all, and so did the everyday word for a concept the IBGE names differently. Measured over the 9,336 tables of the Aggregates API (2026-09-16), fixed since 5.1.0: both sides are normalised, every word must match (AND), and the everyday word is expanded to the IBGE's own — the response says so in notas_vocabulario, and zero results come with a way out.

you ask	hits before	the IBGE writes	hits
populacao, ocupacao, instrucao, saude, area, agua	0	população, ocupação, instrução, saúde, área, água	520, 364, 698, 518, 956, 256
desemprego	4	desocupação	33
renda	72	rendimento	1,126
inflação	0	IPCA, INPC, preços	37, 15, 75
moradia, casa	14, 101	domicílio	3,606
cidade	110	município	455
natalidade, mortes	0, 1	nascidos vivos, óbitos	84, 33
gênero	40	sexo	2,020
negros	0	cor ou raça	1,134
universidade, faculdade	0	ensino superior	12
luz, fábrica, tabagismo, convênio, idosos	0	energia elétrica, indústria, fumante, plano de saúde, 60 anos	43, 248, 94, 101, 89

Only measured pairs enter the table (src/vocabulario.ts, counts in the header): the word you ask with absent from the catalogue, the IBGE's word present. What the IBGE does not publish as an aggregate stays out and still returns zero — turismo, aposentadoria, frota — because an alias for data that does not exist promises what the source does not have. The same table feeds the Deep Research search index, which gets the everyday word as a keyword of the table whose name carries the IBGE's word.

Maps (meshes)

You want…	Use
Administrative outlines (Brazil/region/state/municipality)	ibge_malhas
Thematic areas (biomes, Legal Amazon, semi-arid, metro regions)	ibge_malhas_tema (IBGE Geosserviços WFS — the Malhas API does not publish these)

Installation

Prerequisites

• Node.js 22.x or higher (engines.node)
• npm or yarn

From npm (recommended)

npm install -g ibge-br-mcp

From source

# Clone the repository
git clone https://github.com/SidneyBissoli/ibge-br-mcp.git
cd ibge-br-mcp

# Install dependencies
npm install

# Build the project
npm run build

Configuration

Remote endpoint (nothing to install)

The server is also hosted, with the same tools, over Streamable HTTP and without a key:

https://ibge.sidneybissoli.com/mcp

It works with any client that accepts a remote MCP server — a custom connector in claude.ai (Settings → Connectors → Add custom connector), claude mcp add --transport http ibge https://ibge.sidneybissoli.com/mcp in Claude Code, an app in ChatGPT, the mcp.json of Cursor and VS Code. The step-by-step for each client is in the tutorial. The sections below cover the local form, via npx.

Claude Desktop

Add to your Claude Desktop configuration file (claude_desktop_config.json):

{
  "mcpServers": {
    "ibge-br-mcp": {
      "command": "npx",
      "args": ["-y", "ibge-br-mcp"]
    }
  }
}

Or if installed from source:

{
  "mcpServers": {
    "ibge-br-mcp": {
      "command": "node",
      "args": ["/path/to/ibge-br-mcp/dist/index.js"]
    }
  }
}

Claude Code

{
  "mcpServers": {
    "ibge-br-mcp": {
      "command": "npx",
      "args": ["-y", "ibge-br-mcp"]
    }
  }
}

ChatGPT (Deep Research)

ChatGPT deep research (and company knowledge, and research workflows over the Responses API) only uses an MCP server that exposes exactly search and fetch — this server does, on top of the ibge_* tools. Point the connector at the hosted endpoint, no key required:

https://ibge.sidneybissoli.com/mcp

search ranks the query against SIDRA tables, municipalities and the known indicators and returns { id, title, url }; fetch returns the document as readable Markdown with the canonical public URL (sidra.ibge.gov.br or cidades.ibge.gov.br), which is what ChatGPT cites. Both carry the same provenance block as every other tool. In ChatGPT's developer mode (Settings → Security and login → Developer mode) any tool is callable — the ibge_* tools remain the ones to use for data.

Tool Usage Examples

ibge_estados

List all Brazilian states.

# List all states
ibge_estados

# States in Northeast region
ibge_estados(regiao="NE")

# States sorted by abbreviation
ibge_estados(ordenar="sigla")

ibge_municipios

List Brazilian municipalities.

# Municipalities of São Paulo state
ibge_municipios(uf="SP")

# Search municipalities by name
ibge_municipios(busca="Campinas")

# Municipalities in MG containing "Belo"
ibge_municipios(uf="MG", busca="Belo")

ibge_cidades

Query municipal indicators (similar to Cidades@ portal).

# Panorama of São Paulo
ibge_cidades(tipo="panorama", municipio="3550308")

# Population history
ibge_cidades(tipo="historico", municipio="3550308", indicador="populacao")

# List available research
ibge_cidades(tipo="pesquisas")

Available indicators: populacao, area, densidade, pib_per_capita, idh, escolarizacao, mortalidade, salario_medio, receitas, despesas

ibge_paises

Query international country data.

# List all countries
ibge_paises(tipo="listar")

# Brazil details
ibge_paises(tipo="detalhes", pais="BR")

# Search countries
ibge_paises(tipo="buscar", busca="Argentina")

# Countries in Americas
ibge_paises(tipo="listar", regiao="americas")

Regions: americas, europa, africa, asia, oceania

ibge_sidra

Query SIDRA tables (IBGE's Automatic Recovery System).

# Brazil population in 2023
ibge_sidra(tabela="6579", periodos="2023")

# Population by state
ibge_sidra(tabela="6579", nivel_territorial="3", periodos="2023")

# Census 2022 for São Paulo municipality
ibge_sidra(tabela="9514", nivel_territorial="6", localidades="3550308")

Common tables:

Code	Description
6579	Population estimates (annual)
9514	Census 2022 population
4714	Population, territorial area and density (Census 2022)
4099	Unemployment rate (PNAD Contínua, quarterly)
1846	Quarterly GDP at current prices (Brazil)
5938	Municipal GDP at current prices (annual)
6784	Annual GDP and GDP per capita (Brazil)

Territorial levels:

Code	Level
1	Brazil
2	Region (North, Northeast, etc.)
3	State (UF)
6	Municipality
7	Metropolitan Region
106	Health Region
127	Legal Amazon
128	Semi-arid

Statistics mode (also on ibge_censo, ibge_indicadores, ibge_datasaude): for largest/smallest/mean/median/distribution/ranking questions, pass estatisticas=true — the server computes the full distribution (min/max/mean/ median/std-dev/labeled percentiles) over all rows before pagination and returns top/bottom rankings (topN, default 10). agruparPor="<column label>" ranks groups by descending sum, each with its own mini-distribution.

# Which state has the largest estimated population?
ibge_sidra(tabela="6579", nivel_territorial="3", estatisticas=true)

# Census 2022 population distribution grouped by state
ibge_censo(ano="2022", tema="populacao", nivel_territorial="3", estatisticas=true, agruparPor="Unidade da Federação")

ibge_censo

Query Census data (1970-2022).

# Population Census 2022
ibge_censo(ano="2022", tema="populacao")

# Historical population series
ibge_censo(ano="todos", tema="populacao")

# Literacy by state in 2010
ibge_censo(ano="2010", tema="alfabetizacao", nivel_territorial="3")

Available themes: populacao, alfabetizacao, domicilios, idade_sexo, religiao, cor_raca, rendimento, migracao, educacao, trabalho

ibge_indicadores

Query economic and social indicators.

# GDP
ibge_indicadores(indicador="pib")

# IPCA last 12 months
ibge_indicadores(indicador="ipca", periodos="last 12")

# Unemployment by state
ibge_indicadores(indicador="desemprego", nivel_territorial="3")

# List all indicators
ibge_indicadores(indicador="listar")

Available indicators:

Category	Indicators
Economic	pib, pib_variacao, pib_per_capita, industria, comercio, servicos
Prices	ipca, ipca_acumulado, inpc
Labor	desemprego, ocupacao, rendimento, informalidade
Population	populacao, densidade
Agriculture	agricultura, pecuaria

ibge_nomes

Query name frequency and rankings.

# Frequency of "Maria"
ibge_nomes(tipo="frequencia", nomes="Maria")

# Compare names
ibge_nomes(tipo="frequencia", nomes="João,José,Pedro")

# Ranking of names in 2000s
ibge_nomes(tipo="ranking", decada=2000)

# Female names ranking
ibge_nomes(tipo="ranking", sexo="F")

ibge_malhas

Get geographic meshes (maps).

# Brazil with states
ibge_malhas(localidade="BR", resolucao="2")

# São Paulo with municipalities
ibge_malhas(localidade="SP", resolucao="5")

# Specific municipality
ibge_malhas(localidade="3550308")

# SVG format
ibge_malhas(localidade="BR", formato="svg")

Resolution levels:

Value	Internal Divisions
0	No divisions (outline only)
2	States
5	Municipalities

ibge_datasaude

Query Brazilian health indicators served through IBGE's SIDRA (some originally produced by DataSUS, e.g. mortality and births).

# Infant mortality in Brazil
ibge_datasaude(indicador="mortalidade_infantil")

# Life expectancy by state
ibge_datasaude(indicador="esperanca_vida", nivel_territorial="3")

# List indicators
ibge_datasaude(indicador="listar")

Available indicators: mortalidade_infantil, esperanca_vida, nascidos_vivos, obitos, fecundidade, saneamento_agua, saneamento_esgoto, plano_saude

APIs Used

IBGE APIs

• Localities: servicodados.ibge.gov.br/api/v1/localidades
• Names: servicodados.ibge.gov.br/api/v2/censos/nomes
• Aggregates/SIDRA: servicodados.ibge.gov.br/api/v3/agregados (SIDRA tables are read here with view=flat; apisidra.ibge.gov.br has been behind a browser-only Cloudflare challenge since 2026-09-15)
• Meshes: servicodados.ibge.gov.br/api/v3/malhas
• News: servicodados.ibge.gov.br/api/v3/noticias
• Population: servicodados.ibge.gov.br/api/v1/projecoes/populacao
• CNAE: servicodados.ibge.gov.br/api/v2/cnae
• Calendar: servicodados.ibge.gov.br/api/v3/calendario
• Countries: servicodados.ibge.gov.br/api/v1/paises
• Research: servicodados.ibge.gov.br/api/v1/pesquisas

Development

# Build
npm run build

# Watch mode
npm run watch

# Run tests
npm test

# Run tests in watch mode
npm run test:watch

# Lint
npm run lint

# Format
npm run format

# Test with MCP inspector
npm run inspector

Project Structure