Banco Central do Brasil (BCB) — SGS MCP

Busca para Deep Research

search

Read-onlyIdempotent

Find Banco Central do Brasil (SGS) time series catalog entries by keyword or natural language; returns up to 10 matching ids, titles, and URLs to pass to fetch.

Instructions

Searches the Banco Central do Brasil time series (SGS: interest rates, inflation, exchange rates, credit, fiscal and external sector — the curated catalog plus the open data portal index) 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 bcb_* tools, 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	Um bloco por procedência que contribuiu com esta resposta (contrato v1.1; licenças nunca se fundem)
`attribution`	Yes	URLs canônicas das fontes desta resposta (lista de atribuição)

Schema Changelog

Changes observed during successful MCP inspections.

Changed9 schema fields changedv1.15.0Sep 27, 2026

changedOutput schema / properties / provenance / description

Previous value: -"Um bloco por procedência que contribuiu com esta resposta (contrato v1.0; licenças nunca se fundem)"New value: +"Um bloco por procedência que contribuiu com esta resposta (contrato v1.1; licenças nunca se fundem)"

changedOutput schema / properties / provenance / items / description

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

changedOutput schema / properties / provenance / items / properties / citation / description

Previous value: -"Citação pronta para uso"New value: +"Citação/atribuição pronta para uso"

changedOutput schema / properties / provenance / items / properties / data_vintage / description

Previous value: -"Competência do dado segundo a fonte; null quando a fonte não expõe"New value: +"Competência/vintage do dado segundo a fonte; null quando a fonte não expõe"

changedOutput schema / properties / provenance / items / properties / license / description

Previous value: -"Regime legal do dado"New value: +"Regime legal do dado (id SPDX quando há, senão o nome da licença)"

addedOutput schema / properties / provenance / items / properties / retrieval

Added value: +{
+  "description": "Diagnóstico de origem da chamada: como o dado foi obtido. Medição real do servidor; unstable=true pede ao agente que trate o dado como obtido com dificuldade; null quando o servidor não mede",
+  "oneOf": [
+    {
+      "additionalProperties": false,
+      "description": "Diagnóstico de origem da chamada: como o dado foi obtido. Medição real do servidor; unstable=true pede ao agente que trate o dado como obtido com dificuldade",
+      "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",
+                "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)",
+          "minimum": 1,
+          "type": "integer"
+        },
+        "requests": {
+          "description": "Idas distintas à origem que compõem esta resposta (fatias, páginas)",
+          "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"
+    }
+  ]
+}

changedOutput schema / properties / provenance / items / properties / retrieved_at / description

Previous value: -"Instante REAL da extração na origem (ISO-8601, horário de Brasília). Resposta servida de cache mantém o instante do fetch ORIGINAL, que é a data de extração relevante."New value: +"Instante REAL da extração na origem (ISO-8601, fuso do servidor). Resposta servida de cache mantém o instante do fetch original, que é a data de extração relevante"

changedOutput schema / properties / provenance / items / properties / source_url / description

Previous value: -"URL canônica que reproduz a consulta"New value: +"URL canônica que reproduz a consulta na fonte"

changedOutput schema / properties / provenance / items / required

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

Addedv1.12.1Sep 17, 2026

TDQS

A4.6/5.0

Behavior4/5

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

Annotations already cover read-only and idempotent safety, and the description adds value by specifying the 10-result cap, relevance ordering, empty-list meaning, language/case behavior, and in-memory caching of the public catalog. It does not contradict the annotations and provides useful operational detail beyond them.

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?

The description is front-loaded with the core search behavior and uses short labelled paragraphs for contract role, routing, query semantics, and behavior. It is slightly repetitive in places (read-only/idempotent is repeated from annotations, and 'catalog index, not a data query' appears twice), but overall each section has a clear role.

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 single-parameter, read-only search tool with annotations covering safety and an output schema present, the description is complete. It covers result format and limit, empty-result behavior, relationship to sibling tools, and the follow-up step with `fetch`; nothing needed to invoke it correctly is missing.

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?

With 100% schema coverage, the description did not need to repeat the query parameter, but it adds meaning by clarifying that the query accepts natural language or keywords and that both Portuguese and English are supported, with accents and case ignored. This goes beyond the schema's own description.

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 Banco Central do Brasil time series ... catalog' and returns up to 10 documents as { id, title, url }. It explicitly contrasts itself with bcb_* data tools and positions itself as the catalog-search companion to `fetch`, so an agent can distinguish it from siblings.

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?

Provides explicit routing: it says this is for Deep Research workflows with `search`/`fetch`, and 'For direct questions and for data ... prefer the `bcb_*` tools'. It also instructs to pass returned ids to `fetch`, leaving no ambiguity about when to choose this tool.

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

Deploy Server