Fetch and follow the instructions at https://qamcp.dev/setup.md to test my MCP server.Your AI finds your server in your project, tests it with QAmcp, explains what's wrong in plain words, fixes it with your OK, and tests again. Read the instructions
Directory / Rota Nacional
Rota Nacional
by rota-nacional.ia.br · https://rota-nacional.ia.br/mcp
AI API compatible with OpenAI and Anthropic, with personal data handled before the model.
12 of 12 checks · 10 Nov 2026
At a glance
- Runs where
- On their server. What you send to it goes to them.
- What you need
- Nothing: it answered without a login
- Tools
- 19 tools
- Its own safety labels
- 10 read-only, 2 labeled as deleting or destroying, 7 labeled as changing things
- Memory it takes
- About 4,700 tokens of your AI's memory, just for its tool descriptions
- Largest answer
- About 359.8 KB in our test
- Tools that look alike
- 1 pair of tools with nearly the same description, so the AI may pick the wrong one
- Speed
- Average answer in our test: 253 ms
Tokens are an estimate: the characters in its tool names, descriptions and inputs, divided by 4. The exact number depends on your AI model. Safety labels are what the server says about itself. From our latest test, 10 Nov 2026.
Is Rota Nacional MCP server safe?
- None of the hidden-instruction wordings we know were found in its 19 tool descriptions.
- Its error messages showed no secrets or internal details.
- 10 of its 19 tools are labeled read-only; the others may change or send things.
- Overall it scored 80/100 on 10 Nov 2026.
A test can only see what the server shows from outside, not what it does with your data behind the scenes. Connect servers from makers you trust.
What this test does not check
- Its source code and packages.
- What a tool quietly does behind the scenes, such as writing a file or calling another service.
- Instructions hidden inside live tool answers. We only look for those in tool descriptions.
- Hidden instructions worded in a way our list doesn't know yet.
- Tools that could change something. Those are read, never run.
What QAmcp can and can't see · How to tell if an MCP server is safe · Hidden instructions · Prompt injection
Known security advisories
It lists no public code, so there is nothing to look up in GitHub Security Advisories or OSV.dev. QAmcp tests how a server behaves. It does not scan source code.
What it can do
19 tools, in the server's own words.
consultar_botsread-onlyConsulta bots, tarefas, conversas e memória da organização.
atualizar_memoria_botsSalva notas comuns.
registrar_resultado_botPublica o resultado do seu trabalho na conversa, sem chamar outro modelo.
configurar_botEdita bot, memória ou gravação.
enviar_ao_botEnvia pedido ou encaminha resposta de outro bot.
cancelar_botInterrompe a tarefa atual de um bot.
native_responsesCall Responses through the organization's private OpenAI connection.
native_mistral_ocrProcess a document through the organization's private Mistral connection.
consultar_recibos_inferenciaread-onlyConsulta os recibos de inferência do pagador autenticado.
api_indexread-onlyÍndice da API do Rota Nacional: rotas, cota e como ligar o MCP.
listar_modelosread-onlyO catálogo curado de modelos `rota/*`, com janela de contexto e uso indicado.
limpar_dados_pessoaisTroca CPF, CNPJ, e-mail, telefone e nomes de um texto por marcadores (ou os remove), sem modelo nenhum.
conversarChat pelos modelos da Rota (`rota/auto` escolhe pelo conteúdo), conforme a política de privacidade da organização.
listar_radarread-onlyBriefings de engenharia reescritos pela Rota Nacional, com o link da fonte e o teste grátis.
listar_cyberread-onlyBriefings de cibersegurança e notícias reescritos pela Rota Nacional, no ângulo de prompt, documento e chave.
listar_guiasread-onlyGuias práticos da Rota Nacional, com texto próprio, passos e critérios de verificação.
listar_novidadesread-onlyIDs e datas das publicações de Radar, Cyber e Guias.
pricingread-onlyCurrent public prices and free allowances; no charge.
billingread-onlyPayment discovery and billing summary; does not create a charge.
Test results
Safe mode: only tools labeled read-only were run. How the test works
- !Ready for the newest MCP versionnote
1 warning
- !Uses an older MCP version (2025-06-18). It works today, but it isn't on the July 2026 version (2026-07-28) yet.
- !Every tool is describednote
1 warning
- !native_responses and native_mistral_ocr have nearly the same description (93% of their words are shared; the only difference: "input", "instead", "supply" vs "mistral", "ocr", "process"), so an AI may not know which to pick
- !Tools work with good inputsnote
3 warnings
- –consultar_bots: Needs you to sign in, so it was not tested (not counted against the server)
- –consultar_recibos_inferencia: Needs you to sign in, so it was not tested (not counted against the server)
- !api_index: Answered with about 360 KB of text. Many AI apps cut off tool answers this big, so the AI may never see the end of it.
- !listar_cyber: Answered with about 104 KB of text. Many AI apps cut off tool answers this big, so the AI may never see the end of it.
- !listar_novidades: Answered with about 321 KB of text. Many AI apps cut off tool answers this big, so the AI may never see the end of it.
- –atualizar_memoria_bots: Not run: labeled dangerous
- –registrar_resultado_bot: Not run: labeled as changing data
- –configurar_bot: Not run: labeled dangerous
- and 11 more
- !Bad inputs give a clean errornote
3 warnings
- –consultar_recibos_inferencia: Needs you to sign in, so bad inputs were not tested
- !listar_radar: Accepted wrong type for "page" without complaining
- !listar_cyber: Accepted wrong type for "page" without complaining
- !listar_guias: Accepted wrong type for "page" without complaining
- !Follows MCP best practices (not scored yet)note
2 tips (not scored)
- !19 tools don't say whether they reach outside services like the web (openWorldHint): consultar_bots, atualizar_memoria_bots, registrar_resultado_bot, configurar_bot, enviar_ao_bot, cancelar_bot and 13 more
- !8 tools answer with structured data but don't declare its shape (outputSchema): api_index, listar_modelos, listar_radar, listar_cyber, listar_guias, listar_novidades and 2 more. If those answers change shape, nothing can catch it; with a sc
- ✓ConnectsConnected in 980 mspass
- ✓Lists its toolsFound 19 toolspass
- ✓Tools are labeled safe or dangerousEvery tool has a safety labelpass
- ✓No known hidden instructionsNone of the hidden-instruction wordings we know were found in tool descriptions. New wordings can get past this check.pass
- ✓Fast enoughpass
All good
- ✓Connecting took 980 ms
- ✓Listing tools took 168 ms
- ✓Average tool answer: 253 ms
- ✓api_index: Slowest tool: api_index (503 ms)
- ✓No secrets leakedChecked 15 error messages: no secrets or internal detailspass
- ✓Resources and prompts workOpened 5 of 5 promptspass
- –Tools work togetherNo tool's answer could be fed into another tool, so there were no chains to test (not counted either way)not tested
Test it yourself
Free and open source. Same checks, same score.
npx qamcp-cli https://rota-nacional.ia.br/mcpShow this score on GitHub
Free for every server in the directory. Paste this into your README: the badge shows the score from our latest test.
[](https://qamcp.dev/s/br-ia-rota-nacional-rota-nacional.html)Score over time
- 10 Nov 202680
One test so far. New tests will show here.
Reviews
Coming soon: reviews from people who use Rota Nacional, signed in with GitHub, one per person. Reviews never change the score.
QAmcp Monitor tests it every hour and emails you when it goes down, the score drops, a tool changes or a secret leaks. Free for 1 server, no card.
Have a concern, or want it removed? Ask us and we'll take it off the list. How the directory works