Skip to main content
Glama

MCP Compras.gov.br

compras_healthcheck

Read-onlyIdempotent

Diz, em ~30 segundos, o que está de pé neste servidor agora.

Estende compras_versao: além de versão e configuração, dispara um probe paralelo (timeout curto) contra as rotas upstream reais e devolve a situação por módulo funcional.

Por que existe: em 04/08/2026 a tool de pesquisa de preço de material estava quebrada havia semanas e ninguém sabia — a SEGES trocou a assinatura da rota sem versionar. A descoberta veio de um analista tentando usar a ferramenta. Antes de uma demonstração ou de instruir processo, rode isto: o objetivo é que a descoberta aconteça aqui, não no palco.

Args: profundidade: basico responde só versão/config (instantâneo); rotas (padrão) executa o probe upstream. modulo: restringe o probe a um módulo (ex.: pesquisa_preco, atas, pncp). Sem isso, testa todos.

Situação por módulo: - ok: todas as rotas responderam com os campos esperados. - degradado: alguma rota caiu, ou respondeu 200 sem os campos do contrato (ex.: rota de preço sem precoUnitario) — o modo de falha silencioso que só o contrato de campos pega. - fora: todas as rotas testáveis do módulo falharam. - pulado: faltou credencial (ex.: TRANSPARENCIA_API_KEY).

Rota que estoura o relógio é reexecutada em série antes de virar fora: com dezenas de rotas em paralelo, uma rota apenas lenta seria reportada como quebrada. Quando passa na segunda tentativa, o campo problemas do módulo registra "lenta sob carga" em vez de escondê-lo.

O campo pronto_para_uso é o resumo honesto: False quando existe qualquer módulo fora ou degradado.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
moduloNoRestringe o probe a um módulo funcional: 'pesquisa_preco', 'catalogo', 'organizacoes', 'atas', 'contratacoes', 'contratos', 'fornecedores', 'indicadores', 'legado', 'planejamento', 'pncp', 'sancoes', 'comprasnet', 'enriquecimento'. Sem valor, testa todos.
profundidadeNo'rotas' (padrão) testa as rotas upstream reais em paralelo e devolve situação por módulo (ok/degradado/fora) em ~30s. 'basico' devolve só versão e configuração, sem tocar a rede.rotas

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault

No arguments

Schema Changelog

Changes observed during successful MCP inspections. Dates show when Glama detected each change.

  1. First observed

TDQS

A4.6/5.0
Behavior5/5

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

Annotations already mark the tool as readOnly, idempotent, and non-destructive. The description goes beyond annotations by detailing the parallel probe, short timeout, retry-then-mark-out behavior, per-module status semantics (ok/degradado/fora/pulado), and the 'pronto_para_uso' summary field. This is rich behavioral disclosure without contradicting the annotations.

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 opens with a concise one-sentence summary and then uses clear sections for args, statuses, retry behavior, and the summary field. It is longer than average due to the historical rationale, but that rationale reinforces when to use the tool. It is organized and front-loaded, with minimal unnecessary repetition.

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?

The description covers what the tool does, how long it takes, what parameters do, how statuses are derived, what happens on timeouts, what happens with missing credentials, and how to interpret 'pronto_para_uso'. Even with an output schema present, the description provides enough semantic context for an agent to call the tool correctly and interpret results.

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?

The input schema already covers both parameters with 100% coverage, so the baseline is 3. The description adds value by giving concrete module examples ('pesquisa_preco', 'atas', 'pncp'), clarifying that 'basico' avoids network access, and explaining default behavior. This is useful extra context beyond the schema.

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?

The description states a specific verb and resource: 'Diz, em ~30 segundos, o que está de pé neste servidor agora.' It explicitly distinguishes itself from the sibling compras_versao by saying it 'estende compras_versao' and adds upstream route probing. This is a clear healthcheck purpose that an agent can differentiate from other compras_* tools.

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?

The description gives explicit usage context: 'Antes de uma demonstração ou de instruir processo, rode isto.' It also references compras_versao as the more limited alternative and explains the historical failure that motivated the tool. It does not explicitly list when-not-to-use scenarios, but the context and alternative are clear enough.

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.

TDQS

A3.6/5.0
Disambiguation3/5

Most tools target distinct resources, and descriptions are extremely detailed, often explicitly warning about look-alikes. However, there is real overlap between composite and single-purpose tools (e.g., compras_checar_sancoes_fornecedor vs compras_perfil_fornecedor_completo vs compras_sancao_*), and similar-looking pairs like compras_contratos_consultar vs compras_contrato_comprasnet_consultar or compras_arp_listar vs compras_pncp_atas_listar require careful reading. With 100 tools, an agent will still face meaningful selection ambiguity.

Naming Consistency3/5

The dominant pattern is snake_case with a compras_ prefix, but the order and style vary: some are domain-first (compras_catmat_buscar), some are verb-first (compras_buscar_contratacoes_similares), and some are bare entity names with no verb (compras_sancao_ceis, compras_pncp_modalidades). The many listar/consultar/buscar variants are readable, but the convention is not predictable enough for a 100-tool surface.

Tool Count1/5

100 tools is an extreme count for any MCP server, regardless of domain breadth. Even if each tool has a legitimate upstream endpoint, this volume will heavily tax context windows and make reliable tool selection harder. Many tools could be consolidated into parameterized families (e.g., contratos, sancoes, pncp resources).

Completeness4/5

The server covers the Brazilian procurement domain remarkably well: catalogs, ARPs, 14.133 contracts, legacy regime, price research, suppliers, sanctions, PGC/PCA, PNCP, and Comprasnet contract subresources. Minor gaps remain, such as listing a supplier's full contract history without specifying an órgão, and some upstream limitations are only papered over with client-side workarounds.