Servidor MCP da BNCC (Base Nacional Comum Curricular), o currículo oficial da educação básica brasileira. Dá a agentes de IA acesso às 1.721 aprendizagens da BNCC e do complemento de Computação, extraídas dos documentos homologados pelo MEC e verificadas contra a fonte. Cada habilidade e objetivo de aprendizagem traz o código, o texto oficial e a proveniência (a página do PDF de onde veio), o que permite ao agente citar a origem em vez de alucinar códigos: a numeração da BNCC tem lacunas legítimas, e o servidor responde explicando isso quando um código não existe. Sete tools: bncc_lookup (busca por código), bncc_buscar (busca textual), bncc_listar, bncc_estatisticas, bncc_decodificar (explica a anatomia de um código como EF67LP08), bncc_progressao_ei e bncc_estrutura. Casos de uso: planejamento de aulas alinhado ao currículo, geração de atividades e avaliações com habilidades corretas, análise de material didático, ferramentas para professores e edtechs brasileiras. Não requer aute
bncc-mcp is a remote MCP server published at mcp.bncc.dev. It has been probed 7 times since 9/10/2026. It answered in 7 of them (100.0%), a near-uninterrupted record. Median response time is 453 ms, placing it among the faster endpoints. It offers a narrow, focused set of 7 tools. On the protocol side it still runs 2025-11-25 and has not moved to the newer spec.
Can an LLM agent pick the right tool here — names, descriptions and parameter clarity are assessed.
bncc_buscar — Description ends abruptly with 'U' (likely a typo or incomplete text).bncc_listar — Description cuts off 'Computação' without explanation.bncc_progressao_ei — Limited scope (only EI codes) not clearly emphasized in description.Risk: medium
tools/list structure, inputSchema validity, and a functional smoke test — the components of the 0-100 score.
Derived by comparing consecutive probes — changes in era, protocol version, build and reachability.
Add this badge to your README — it updates automatically as measurements change.
[](https://mcpmetrics.io/servers/bncc-dev-bncc-mcp)<a href="https://mcpmetrics.io/servers/bncc-dev-bncc-mcp"><img src="https://mcpmetrics.io/badge/bncc-dev/bncc-mcp/era.svg" alt="mcpmetrics"></a>You are seeing the last 7 days. Sign up for the full history. Which check failed and why is in the dashboard.
Sign up free to see| Run | Era | Modern | ms | Legacy | ms | Versions |
|---|---|---|---|---|---|---|
| 2026-09-11 11:20:19 | Legacy | 404 | 491 | 200 | 412 | 2025-11-25 |
| 2026-09-11 09:28:19 | Legacy | 404 | 456 | 200 | 453 | 2025-11-25 |
| 2026-09-11 07:35:54 | Legacy | 404 | 313 | 200 | 313 | 2025-11-25 |
| 2026-09-11 05:44:28 | Legacy | 404 | 327 | 200 | 453 | 2025-11-25 |
| 2026-09-11 03:50:39 | Legacy | 404 | 315 | 200 | 369 | 2025-11-25 |
| 2026-09-11 01:59:45 | Legacy | 404 | 570 | 200 | 566 | 2025-11-25 |
| 2026-09-10 21:16:35 | Auth-gated | 401 | 488 | 401 | 378 | — |
Each block is one measurement round. Green: working response. Amber: responded but the server was returning errors (5xx). Red: no response at all.
Each cell is one probe run. Faded cells are incomplete probes — one leg did not answer, so the era is inconclusive.
The two probe legs separately: modern server/discover and legacy initialize.