Home / Token cost / DataBR

The DataBR MCP server costs 5,528 tokens before the first call.

Connect DataBR and its 82 tool definitions are loaded into the model's context on every request — 2.8% of a 200k window spent before your agent does anything.

QUICK ANSWER The DataBR MCP server's tool definitions consume 5,528 tokens — 2.9× the median MCP server (1,905 tokens). A scoped grant exposing only the tools you use cuts that roughly in proportion.

MEASURED FROM SCHEMAS 82 tools · 5,528 tokens · 2.8% of 200k · 0.6% of 1M Method →

What that buys before your agent starts working.

Tool definitions are overhead: they occupy context on every request and compete with your code, documents and conversation history for the same window.

200K WINDOW 2.8%
1M WINDOW 0.6%

Corpus context: DataBR ranks #989 of 3,213 measured MCP servers by definition cost. The median is 1,905 tokens, p90 is 7,952, and the heaviest (Fusionauth) is 183,337 — 92% of a 200k window on its own.

Where the 5,528 tokens go.

Each row is one tool definition as a tools/list entry — name, description and input schema — counted with o200k_base. Average: 67 tokens per tool.

ToolCategoryTokens% of server
consultar_estabelecimento_saude Read 151 2.7%
consultar_contas_publicas Read 129 2.3%
consultar_tributos_ncm Read 128 2.3%
consultar_icms Read 120 2.2%
consultar_indicador_bcb Read 114 2.1%
consultar_indicadores_ibge Read 112 2.0%
consultar_ipea Read 112 2.0%
consultar_municipio Read 98 1.8%
consultar_fundo_investimento Read 96 1.7%
consultar_orcamento Read 90 1.6%
analise_setor Read 89 1.6%
consultar_mortalidade Read 89 1.6%
buscar_diario_oficial Read 86 1.6%
consultar_deputados Read 86 1.6%
consultar_desmatamento Read 86 1.6%
consultar_vacinacao Read 84 1.5%
consultar_dengue Read 82 1.5%
consultar_nascimentos Read 82 1.5%
consultar_hospitais Read 81 1.5%
consultar_transparencia Read 81 1.5%
consultar_acidentes_transito Read 80 1.4%
consultar_senadores Read 80 1.4%
consultar_processo_judicial Read 78 1.4%
consultar_credito_bcb Read 77 1.4%
consultar_emprego Read 77 1.4%
buscar_diarios_por_tema Read 75 1.4%
consultar_partidos Read 75 1.4%
cotacao_cambio Read 74 1.3%
consultar_beneficios_sociais Read 73 1.3%
consultar_jurisprudencia Read 73 1.3%
consultar_orcamento_funcional Read 73 1.3%
consultar_proposicoes Read 72 1.3%
consultar_empresa Read 71 1.3%
consultar_financiamento_eleitoral Read 71 1.3%
consultar_aeronave Read 69 1.2%
consultar_candidatos Read 69 1.2%
consultar_comercio_exterior Read 69 1.2%
verificar_compliance Read 69 1.2%
consultar_servidores_federais Read 68 1.2%
consultar_tarifas_energia Read 68 1.2%
cotacao_acoes Read 67 1.2%
consultar_fatos_relevantes Read 66 1.2%
consultar_cnae Read 64 1.2%
consultar_diarios_municipais Read 64 1.2%
analise_mercado_trabalho Read 62 1.1%
buscar_processos_judiciais Read 62 1.1%
consultar_geografia_brasil Read 62 1.1%
consultar_tcu_certidao Read 59 1.1%
consultar_transportador Read 59 1.1%
buscar_licitacao Read 57 1.0%
perfil_municipio Read 57 1.0%
consultar_endereco Read 56 1.0%
analise_litigio Read 54 1.0%
rede_influencia Read 54 1.0%
risco_ambiental Read 54 1.0%
analise_competicao Read 53 1.0%
credito_score Read 53 1.0%
descobrir_casos_uso Read 53 1.0%
consultar_contratos_federais Read 52 0.9%
consultar_medicamento Read 50 0.9%
due_diligence_empresa Read 50 0.9%
indicadores_macro Read 49 0.9%
analise_esg Read 48 0.9%
perfil_completo_empresa Read 48 0.9%
consultar_tcu_acordaos Read 47 0.9%
consultar_focus Read 45 0.8%
panorama_economico Read 43 0.8%
consultar_censo_escolar Read 42 0.8%
consultar_combustiveis Read 42 0.8%
consultar_pix_estatisticas Read 42 0.8%
consultar_titulos_tesouro Read 42 0.8%
consultar_embargos_ambientais Read 40 0.7%
consultar_ibovespa Read 40 0.7%
consultar_populacao Read 40 0.7%
consultar_reservas_internacionais Read 39 0.7%
consultar_tcu_inabilitados Read 39 0.7%
consultar_uso_solo Read 39 0.7%
consultar_selic Read 38 0.7%
consultar_planos_saude Read 36 0.7%
listar_municipios_diarios Read 36 0.7%
consultar_votacoes Read 34 0.6%
listar_temas_diarios Read 34 0.6%

Most agents use a handful of these tools. They pay for all 82.

A PolicyLayer grant exposes only the tools you allow — ungranted definitions are filtered out of the tool list, so they never enter the context window. Estimates below assume typical-weight tools (67 tokens each).

Grant scopeDefinition costReduction
All 82 tools (no gateway) 5,528 tokens
3 granted tools ~202 tokens −96%
5 granted tools ~337 tokens −94%
10 granted tools ~674 tokens −88%

DataBR token-cost questions.

How many tokens does the DataBR MCP server use?+

Its 82 tool definitions total 5,528 tokens — 2.8% of a 200k context window — measured with tiktoken o200k_base over the serialised tools/list payload. Exact counts vary slightly by client and model.

Why does DataBR consume tokens before I send a message?+

MCP clients load every connected server's tool definitions — name, description, and input schema — into the model's context so it knows what it can call. That payload is charged against your context window on every request, whether or not a tool is used.

How do I reduce DataBR's token usage?+

Expose fewer tools. A PolicyLayer grant scopes DataBR to only the tools you allow — ungranted definitions are filtered out of the tool list, so they never enter the context window. A grant of 3 typical tools costs roughly 202 tokens, a 96% reduction.

Does deferred tool loading fix this?+

Partially, in some clients. Claude Code defers MCP tool schemas behind a tool-search step by default, and VS Code has experimental grouping — but you still pay tokens per search and reload, and Cursor, Windsurf and Gemini CLI load definitions upfront. Reducing the exposed tool set cuts the cost in every client.

How these numbers were measured.

01
Serialisation

Each tool is serialised as a tools/list entry — name, description, input schema — from the schemas in the PolicyLayer scan database. Clients differ slightly in framing, so treat counts as close estimates.

02
Tokeniser

tiktoken o200k_base (GPT-4o/o-series). Anthropic's current tokeniser isn't published, so Claude's exact counts will differ; for English text and JSON schemas the totals are close enough to treat these as estimates.

03
Deferred loading

Some clients now defer schema loading (Claude Code's tool search; VS Code experimental grouping). You still pay per search and reload — and Cursor, Windsurf and Gemini CLI load everything upfront.

Computed 07-06-2026 from the PolicyLayer scan database over all 82 catalogued DataBR tools. Counts refresh with every site build.

Expose only the tools you use — the rest never enter your context.

A PolicyLayer grant scopes DataBR to the tools you actually allow. Ungranted definitions never load, and every call that does run is checked against policy first.

Free to start. No card required.

4,600+ MCP servers and 31,000+ tools scanned and risk-classified.

// GET IN TOUCH

Have a question or want to learn more? Send us a message.

Message sent.

We'll get back to you soon.