IBGE Brasil MCP

by io.github.SidneyBissoli

Overview Discussions Admin

Metadados de tabela SIDRA

ibge_sidra_metadados

Read-onlyIdempotent

Returns metadata for a specific SIDRA table.

Features:

General info (name, survey, subject, periodicity)
Available territorial levels
Variable list with units
Classifications and categories
Available periods

Use this tool to understand table structure BEFORE querying data with ibge_sidra.

Examples:

Population table metadata: tabela="6579"
Census 2022 metadata: tabela="9514"
PNAD unemployment: tabela="4714"

Use this after finding a table code (ibge_sidra_tabelas) and before querying with ibge_sidra.

Behavior: read-only and idempotent — a live GET against the public IBGE SIDRA API. Returns Markdown.

Input Schema

TableJSON Schema

Name	Required	Description
`tabela`	Yes	Código da tabela/agregado SIDRA (ex: '6579', '9514', '4714')
`incluir_periodos`	No	Incluir lista de períodos disponíveis (padrão: true)
`incluir_localidades`	No	Incluir níveis territoriais disponíveis (padrão: false)

Output Schema

TableJSON Schema

Name	Required	Description
`url`	No	URL da tabela no SIDRA
`nome`	Yes	Nome da tabela
`codigo`	Yes	Código da tabela/agregado SIDRA
`assunto`	No	Assunto/tema da tabela
`periodos`	No	Períodos disponíveis para a tabela (quando incluir_periodos)
`pesquisa`	No	Nome da pesquisa de origem
`variaveis`	No	Variáveis da tabela, com unidades e classificações/categorias
`provenance`	Yes	Bloco de proveniência (contrato v1.1): fonte, URL, período, extração, diagnóstico de origem e licença
`attribution`	Yes	URLs canônicas das fontes desta resposta (lista de atribuição)
`periodicidade`	No	Periodicidade da pesquisa
`niveisTerritoriais`	No	Níveis territoriais disponíveis para a tabela

Schema Changelog

Changes observed during successful MCP inspections.

Changed3 schema fields changedSep 27, 2026

changedOutput schema / properties / provenance / description

Previous value: -"Bloco de proveniência (contrato v1.0): fonte, URL, período, extração e licença"New value: +"Bloco de proveniência (contrato v1.1): fonte, URL, período, extração, diagnóstico de origem e licença"

addedOutput schema / properties / provenance / properties / retrieval

Added value: +{
+  "anyOf": [
+    {
+      "additionalProperties": false,
+      "properties": {
+        "anomalies": {
+          "description": "Anomalias superadas até o sucesso, somadas por classe, em ordem fixa; [] se nenhuma",
+          "items": {
+            "additionalProperties": false,
+            "properties": {
+              "count": {
+                "description": "Ocorrências desta classe na chamada",
+                "maximum": 9007199254740991,
+                "minimum": 1,
+                "type": "integer"
+              },
+              "kind": {
+                "description": "Classe da anomalia (vocabulário fechado do contrato)",
+                "enum": [
+                  "timeout",
+                  "network",
+                  "http_4xx",
+                  "http_5xx",
+                  "rate_limited",
+                  "malformed_body"
+                ],
+                "type": "string"
+              }
+            },
+            "required": [
+              "kind",
+              "count"
+            ],
+            "type": "object"
+          },
+          "type": "array"
+        },
+        "attempts": {
+          "description": "Tentativas somadas, incluindo as repetidas (>= requests)",
+          "maximum": 9007199254740991,
+          "minimum": 1,
+          "type": "integer"
+        },
+        "requests": {
+          "description": "Idas distintas à origem que compõem esta resposta (fatias, páginas)",
+          "maximum": 9007199254740991,
+          "minimum": 1,
+          "type": "integer"
+        },
+        "unstable": {
+          "description": "true se houve repetição (attempts > requests) ou alguma anomalia",
+          "type": "boolean"
+        }
+      },
+      "required": [
+        "requests",
+        "attempts",
+        "anomalies",
+        "unstable"
+      ],
+      "type": "object"
+    },
+    {
+      "type": "null"
+    }
+  ],
+  "description": "Diagnóstico de origem desta chamada (contrato v1.1): idas à API do IBGE, tentativas somadas e anomalias contornadas; unstable=true quando houve anomalia. null quando nada foi medido (resposta servida só do cache)"
+}

changedOutput schema / properties / provenance / required

Previous value: -[
-  "source",
-  "source_url",
-  "data_vintage",
-  "retrieved_at",
-  "citation",
-  "license"
-]New value: +[
+  "source",
+  "source_url",
+  "data_vintage",
+  "retrieved_at",
+  "retrieval",
+  "citation",
+  "license"
+]

Changed1 schema field changedSep 11, 2026
- addedInput schema / additionalProperties
```
Added value: +false
```
First observedSep 6, 2026

TDQS

A4.6/5.0

Behavior4/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnlyHint, idempotentHint, openWorldHint and destructiveHint=false, so the safety profile is covered. The description adds real value beyond that: it discloses the live GET against the public IBGE SIDRA API and that the return format is Markdown. It does not mention rate limits or error behavior, but that is a minor omission given annotations handle the rest.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Front-loaded with the core action and organized under clear Features/Examples headings with scannable bullets. Slightly redundant: the 'BEFORE querying' guidance appears twice (in the intro line and the later 'Use this after...' sentence), which is minor waste but not confusing.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a read-only metadata lookup with a full output schema, the description supplies everything an agent needs: what is returned, when to call it relative to the two sibling tools, and concrete example codes. Return-value detail is correctly delegated to the output schema.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, so the baseline is 3. The description goes beyond the schema by mapping concrete table codes to content semantics (6579=population, 9514=Census 2022, 4714=PNAD unemployment) and by tying the feature list (available periods, territorial levels) to the optional booleans incluir_periodos and incluir_localidades.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb and resource ('Returns metadata for a specific SIDRA table') and enumerates exactly what that metadata includes (name, survey, periodicity, territorial levels, variables, classifications, periods). This distinguishes it cleanly from ibge_sidra (data queries) and ibge_sidra_tabelas (table code discovery).

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines5/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Explicitly states when to use it ('BEFORE querying data with ibge_sidra') and names both bracketing siblings: use after ibge_sidra_tabelas and before ibge_sidra. This is a complete when/when-not/alternative routing instruction.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

All IBGE Brasil MCP tools Inspect

Try in Browser

One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.