Skip to main content
Glama

Check a company (live)

consulta_cnpj
Read-onlyIdempotent

Brazilian company record by CNPJ from the Federal Revenue (Receita Federal), with the special status when there is one (bankruptcy, judicial recovery, liquidation); its sanctions (CEIS, CNEP, CEPIM, leniency agreements, TCU and the CNJ's CNIA, checked live); partners on the politically exposed persons list (CGU); tax status (federal tax debt, installment agreements, tax incentives and construction works); the Federal Revenue chronic tax debtor list (devedorContumaz.consta: barred from public tenders); environmental and labor risk (forced-labor list, Ibama embargoes and fines); government contracts (PNCP, federal contracts since 2013 and sales to municipalities in the state of SP, from TCE-SP) and BNDES financing; registrations with regulators and official registries (CVM, Central Bank, ANS, ANTT, ANP, ANEEL, Anatel, Anvisa, CNES, Cadastur, Ibama, ANAC and SICAF); CVM investment funds; and the address on the map (CNEFE/IBGE). Accepts the numeric and the alphanumeric CNPJ. Personal data in the record comes masked. sancoes has what public registries record against the whole company (the CNPJ root), updated daily: useful to vet suppliers. 10 free lookups per day per network; after that, the tool answers free_limit with resets_at.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
cnpjYesCNPJ, with or without punctuation.
temasNoComma-separated topics: dados, socios, sancoes, fiscal, divida, obras, trabalho, ibama, contratos, pep, vendas, campanhas, prefeituras, sicaf, aeronaves, fundos, rntrc, bndes, registros; todos. Omit for the full record. Basic company data always stays. Unrequested blocks are omitted; null means unchecked. Personal data remains masked.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • addedInput schema / properties / temas
      Added value: +{
      +  "description": "Comma-separated topics: dados, socios, sancoes, fiscal, divida, obras, trabalho, ibama, contratos, pep, vendas, campanhas, prefeituras, sicaf, aeronaves, fundos, rntrc, bndes, registros; todos. Omit for the full record. Basic company data always stays. Unrequested blocks are omitted; null means unchecked. Personal data remains masked.",
      +  "maxLength": 240,
      +  "type": "string"
      +}
  2. Changed1 schema field changed
    • changedInput schema / properties / cnpj / description
      Previous value: -"CNPJ, com ou sem pontuação"New value: +"CNPJ, with or without punctuation."
  3. Added

TDQS

A4.4/5.0
Behavior5/5

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

Goes well beyond the readOnly/idempotent/non-destructive annotations by disclosing rate limits (10 free lookups per day per network, with `resets_at` in the failure response), personal-data masking, the 'null means unchecked' convention, and that unrequested blocks are omitted. These are exactly the operational details an agent cannot infer from the schema.

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

Conciseness3/5

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

Purpose and the key operational caveats are front-loaded, which is good, but the middle is a single sprawling sentence enumerating a dozen data domains. It earns its length partly by substituting for an absent output schema, yet it is dense enough to be hard to scan.

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

Completeness4/5

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

With no output schema, the description must carry return-value semantics, and it does so thoroughly: it enumerates the returned blocks, explains topic selection and omission, masking, and the one error path. The remaining gap is sibling differentiation against lookups such as consulta_cadastro or empresas.

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, but the description adds a genuine nuance by stating the CNPJ may be numeric or alphanumeric (the schema only mentions punctuation), plus the live-check semantics of `sancoes`. The `temas` topic list is largely duplicated from the schema, so it does not push this higher.

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 — a live Brazilian company record keyed by CNPJ from Receita Federal — and enumerates the exact data domains returned (sanctions, PEP lists, tax status, contracts, regulators). The scope is unmistakable and clearly distinct from sibling lookups like consulta_cep or consulta_endereco.

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

Usage Guidelines4/5

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

Gives real usage context: 'useful to vet suppliers' and the guidance to pass `temas` or omit it for the full record. It also documents the free-tier ceiling and the resulting `free_limit` state. It stops short of naming when a sibling (e.g. consulta_cadastro) is the better choice, so no explicit exclusion is offered.

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

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.