IBGE Brasil MCP

Busca para Deep Research

search

Read-onlyIdempotent

Searches the IBGE (Brazilian official statistics: SIDRA tables, municipalities, known indicators) catalog and returns up to 10 matching documents as { id, title, url }, ordered by relevance (an empty list means nothing matched).

This tool exists for the OpenAI Deep Research contract: ChatGPT deep research, company knowledge and research workflows over the Responses API require exactly the tools search and fetch. Pass one of the returned ids to fetch to read the document. For direct questions and for data (values, series, rankings) prefer the ibge_* tools (ibge_sidra, ibge_cidades, ibge_indicadores, ibge_comparar…), which return the actual data with provenance — this is a catalog index, not a data query.

Query: natural language or keywords, Portuguese or English; accents and case are ignored.

Behavior: read-only and idempotent — the catalog comes from the public source and is cached in memory.

Input Schema

TableJSON Schema

Name	Required	Description	Default
`query`	Yes	Termos de busca em linguagem natural ou palavras-chave (acentos e caixa são ignorados)

Output Schema

TableJSON Schema

Name	Required	Description
`results`	Yes	Documentos encontrados, em ordem de relevância
`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)

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"
+]

First observedSep 6, 2026

TDQS

A4.4/5.0

Behavior4/5

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

Annotations already declare readOnly, idempotent, openWorld and non-destructive, so the safety profile is covered. The description adds context beyond them: the catalog comes from the public source and is cached in memory, and an empty list means nothing matched. It does not discuss result latency or ranking nuances, but the added caching/source disclosure is substantive.

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 purpose and return shape, then structured into contract, alternatives, query notes, and behavior. Every sentence earns its place, though the Deep Research contract paragraph is somewhat verbose relative to the tool's simplicity.

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?

An output schema exists, so return values need not be explained in depth; the description still summarizes them. For a single-parameter read-only search with annotations covering safety, an agent has everything needed: what it searches, what it returns, when to use it, and which tool to chain into.

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

Parameters3/5

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

Only one parameter and schema description coverage is 100%, so the schema already documents it fully. The description restates the same facts (natural language or keywords, Portuguese or English, accents/case ignored) rather than adding new syntax or constraints. Baseline 3 applies when the schema does the heavy lifting.

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 ('searches the IBGE catalog'), names the exact return shape ({ id, title, url }, up to 10, ordered by relevance) and explicitly frames itself as a catalog index rather than a data query. An agent can distinguish it from every ibge_* sibling without opening a schema.

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?

Gives explicit when-to-use ('OpenAI Deep Research contract... require exactly the tools search and fetch'), an explicit alternative for other cases ('for direct questions and for data prefer the ibge_* tools'), and the follow-up step ('pass one of the returned ids to fetch'). Nothing is left to inference.

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.