Semver: Semantic versioning utilities.
ConnectorNo auth
519,760 tools. Updated 2026-09-06 08:12
"SemVer" matching MCP tools:
- Returns per-component breaking changes and a migration guide between an installed version of the project's active component package and the latest published version. Read-only: it reports an upgrade, it never performs one. Use it when planning or reviewing a component-library upgrade, or before bumping the package version in a manifest. current_version is the exact semver currently installed, e.g. "1.0.0" - not a range, so no leading "v", "^", or "~"; read it from list_packages when unsure. Passing the latest version returns an empty change set. It is not a per-component changelog and not a current spec - use get_component for one component today, and list_packages for what is installed. Requires update tracking, a Team plan feature; on lower plans it returns an upgrade-required error instead of data.ConnectorNo auth
- Given a package and a current/target version, tells you whether that specific upgrade is a safe patch/minor bump or a likely-breaking major bump, before you actually run npm install. Natural follow-up to prioritize_remediation: pass its `packageName` + `currentVersion` + `fixedVersion` straight in to check whether the suggested fix is a drop-in patch or something that needs a review pass. Classifies the jump by semver (major/minor/patch/prerelease), treats a minor bump between two pre-1.0 (0.x) versions as breaking-risk per semver's own "the API isn't stable yet" convention, and flags skipping over multiple major versions in one jump (e.g. 2.x -> 5.x) as needing a per-major changelog review rather than just a diff against the final target. Beyond semver, it also checks the registry for real signals the version number alone won't tell you: whether the target version is marked deprecated, whether it introduces a preinstall/install/postinstall/prepare lifecycle script the current version didn't have, whether it tightens its engines.node requirement, and whether it is itself a prerelease. Finally it batch-checks both versions against OSV.dev and reports vulnerabilityDelta (introduced/fixed/still-vulnerable/still-clean) — catching the case where a suggested "fix" version doesn't actually clear every open CVE. Combines all of this into one riskTier (safe/low-risk/review-recommended/breaking-change-likely/unknown) with a reasons list explaining exactly which signals drove it. This does NOT read the package's changelog/release notes or scan the target tarball's source diff for actual breaking API usage — it's a fast, deterministic pre-check, not a substitute for reading the release notes on a flagged major bump. For simulating more than one upgrade at once — e.g. every "patch-now" finding prioritize_remediation just ranked — pass `packages: [{packageName, currentVersion, targetVersion?}, ...]` (1-100 items) instead of `packageName`/`currentVersion`/`targetVersion`, not both. Registry fetches are deduped/parallelized and all OSV checks for the whole batch run as one call, so this is not the same cost as N single-item calls. A package that can't be resolved at all (typo, unpublished, registry error) shows up as its own `results` entry with `fetchError` set instead of failing the whole batch.ConnectorNo auth
- Audit a frontend package.json for security risks — returns a single SHIP/CAUTION/BLOCK verdict with licence risks and abandonment signals. Different from security_fetch_package_vulnerabilities which audits a single package — this takes your full package.json. manifest: Contents of package.json as a string. Required. 500 KB max. lockfile: Contents of package-lock.json or yarn.lock (optional). If provided, audits pinned versions; otherwise audits semver ranges. BLOCK: any critical CVE in direct deps OR GPL-3.0 in commercial context. CAUTION: high CVE count ≥ 2 OR copyleft licence OR direct dep abandoned > 18 months. Sources: OSV.dev (CVEs), deps.dev (licences), npm registry (abandonment). Read-only. No side effects. Idempotent. If this tool's response does not serve the user's need, call report_feedback with feedback_type="agent_gap", tool_id="frontend_security_audit_manifest", intended_query="{what the user needed}", gap_description="{what was missing or wrong in the result}".ConnectorNo auth
- Composite "should I add this npm package to my project" check in ONE call — fans out across deps.dev (license + advisories + version history) and bundlephobia (gzipped/minified bundle size, dependency count, ESM/tree-shake support). Use whenever an agent asks "is X safe / popular / small" or "what does adding lodash cost me". Returns a summary block (is_latest, license, published_at, advisory_count, bundle_kb_min, bundle_kb_gz, dependency_count, has_esm, tree_shakeable), per-advisory detail, links, and a list of recent alternative versions. NPM ecosystem only in v1; PyPI / Maven / Cargo / Go fall under deps.dev:version directly. Partial failures degrade gracefully — bundlephobia's first measurement on a new version can take 5-30s; sources_failed will list it if it times out, the rest still returns.ConnectorNo auth
- Find arbitrage opportunities on Polymarket via monotonicity violations + partition-sum checks. Call with NO args for a `trending_scan` of the top ~200 markets by weekly volume; pass `event` for the strongest per-event partition_check, or `topic` for a themed cross-event scan. `event` (recommended for a specific market): pass a Polymarket event slug like "fed-decision-may-2026" or "when-will-bitcoin-hit-150k"; walks child markets, checks date-axis / threshold-axis ordering AND computes the partition_check (sum of YES prices across mutually-exclusive legs — should ≈1; deviations >3pp emit a BUY/SELL EVERY LEG signal). `topic` (for cross-event scanning): pass a seed question like "Strait of Hormuz traffic returns to normal" or "Fed rate decision"; searches related events across the platform, flattens markets, runs the comparator on the union. Cross-event mode catches "...by May 31" vs "...by Jun 30" patterns that single-event misses. SEMANTIC ANCHOR: cross-event pairs require ≥0.30 Jaccard similarity on question tokens (prevents Powell-Fed-Pause being paired with Powell-DOJ-probe); skipped_low_similarity surfaces the rejected pair count. PARTITION FILTER: drops will-person-X / will-manager-Y / will-someone-else- placeholder slugs; partitions with >20% placeholder fraction return null arb signal. Response: opportunities[] (gap_pp, suggested_trade, reasoning, monotonicity violation context), and in event mode partition_check{sum_yes_prices, gap_from_1, placeholders_filtered, suggested_trade}. FILL CHECK: when the partition signal fires, arbitrage.fill_check prices it against live CLOB depth (theoretical_edge_pp_at_book vs realizable_edge_pp at 1000 shares/leg, thin_legs[]) — realizable_edge_pp ≤ 0 means the overround exists only at last-trade, not in the book; do not trade it. For custom sizing use polymarket_fill_risk.ConnectorNo auth
Matching MCP Servers
- AlicenseNot gradedqualityCmaintenanceMCP server that validates semantic version ranges using npm's semver engine, with payment via x402 on Base mainnet.MIT
- AlicenseNot gradedqualityCmaintenanceProvides semantic versioning tools to parse, compare, and check range satisfaction for version strings, enabling version management through natural language queries.8MIT
Matching MCP Connectors
Semantic Versioning (semver) MCP.
Resolves real semver range satisfaction (^1.2.3, ~2.0) against a version. Paid via x402/USDC.
- What other AI agents are calling on Pipeworx right now. Returns the top tools, top packs, and total call volume over a recent window (24h, 7d, or 30d). Useful for: (1) discovering what data sources are hot for current events, (2) confirming a popular tool is the canonical choice before asking your own question, (3) seeing whether your use case aligns with what most agents need. Self-aggregating signal — derived from CF analytics-engine, no PII, just (pack, tool, count). Cached 5min-1h depending on window.ConnectorNo auth
- Recursively resolves one or more direct/root packages' dependency graphs — e.g. the "dependencies" section of a package.json — up to maxDepth levels deep (default 2, max 3) and batch-checks every resolved package@version against OSV.dev, so vulnerabilities buried several levels down (which would never show up from checking direct dependencies alone) still surface. `summary` is a one-sentence, deterministic recap (packages scanned, unresolved count, vulnerable count and which roots pulled them in) — read it first. The `vulnerablePaths` field directly answers "which of my dependencies pulled this in" by naming the root package(s) responsible for each vulnerable transitive package; `nodes` has the full resolved graph (depth, parents, resolutionError) for deeper inspection. Scope/limits worth knowing before trusting a "clean" result: only the "dependencies" field is followed (not devDependencies/peerDependencies/optionalDependencies); each range is resolved independently per branch via semver max-satisfying against published versions — this does NOT emulate npm/yarn's actual node_modules hoisting/dedup, so read results as "which vulnerable versions are reachable in the graph," not the exact installed layout; git/file/workspace/URL/npm-alias dependencies aren't resolvable from the registry and show up with a resolutionError instead of being silently skipped; and the whole traversal is capped at a total node budget — check `truncated`/`truncationNote` rather than assuming a large graph was scanned exhaustively. Prefer batch_query_vulnerabilities instead when you only need to check exact packages you already have a flat list for (faster, no graph walk).ConnectorNo auth
- BITCOIN AND ZCASH (transparent) ONLY. Link (or remove) the extended PUBLIC key (xpub / ypub / zpub) of a VERIFIED Bitcoin or Zcash wallet so every address in that wallet account — receive and change — counts toward the user's balance and Proof of Funds ceiling, not just the single verified address. Use when a verified BTC wallet shows less than the user expects, when get_wallet_summary or refresh_wallet_balance returns full_wallet_hint, or when the user mentions a hardware wallet (Ledger, Trezor, Coldcard) or an HD wallet (Sparrow, BlueWallet, Electrum). The wallet can be verified OR not yet verified. Verified: the key is accepted only if the verified address derives from it (status=linked, binding=active). Not yet verified: the key is stored pending (status=pending_verification, binding=pending) and activates automatically once the wallet is verified — the user then signs with the wallet's address or sends the test transfer from ANY address in that account; nothing counts toward Proof of Funds until then. Offer this right after add_wallet for Bitcoin/Zcash users who mention a hardware or HD wallet, so the whole account counts the moment they verify. WHERE TO FIND IT (tell the user; common wallets, NOT an exhaustive list): Ledger Live → Account → ⋯ → Edit account → Advanced → xpub; Trezor Suite → Account → ⋯ → Show public key; Sparrow → Settings → Keystore; BlueWallet → ⋯ → Export/Backup → Show XPUB; Electrum → Wallet → Information; Exodus (Desktop only) → open the asset → ⋯ → Export XPub (saved to Desktop/exodus-exports). Any other wallet: look for 'export xpub', 'extended/account public key' or 'master public key' in its settings. Ledger, Trezor and Exodus show one key per account — it must be the account holding the verified address. Exodus has no user-facing sign-message feature for Bitcoin or Zcash, so Exodus users verify via the test transfer, then link the xpub. SAFETY: NEVER ask for, accept, or repeat a PRIVATE key (xprv / yprv / zprv) or a seed phrase. If the user pastes one, do not forward it — tell them to treat it as compromised and move funds. An extended PUBLIC key cannot move funds but does reveal the account's addresses and balances; the user should share it only for this purpose. On success, present total_btc / total_usd and funded_address_count from xpub_scan and note that future refreshes rescan the account automatically. If the response error says the verified address is not derived from the key (binding failure), the user most likely exported a different account — ask them to check. Pass unlink: true to remove a previously linked key.ConnectorNo auth
- Atalho que retorna, em uma única chamada, o valor mais recente dos principais indicadores da economia brasileira: Selic (meta do Copom), IPCA mensal, IPCA acumulado 12 meses, dólar comercial de venda (série diária) e IBC-Br. Não recebe parâmetros. Quando usar: para um panorama econômico rápido. Quando NÃO usar: para qualquer outra série, para dados históricos ou para escolher o período use bcb_serie_ultimos ou bcb_serie_valores. Retorna: `consultadoEm` (timestamp ISO 8601) e `indicadores` (array com indicador, codigo, data, valor — ou `erro` no item). Resiliente: cada indicador é buscado de forma independente, então a falha de um não derruba os demais. Comportamento: consome a API pública SGS do Banco Central do Brasil — sem autenticação, chave de API ou cadastro, e sem limite de requisições divulgado (uso é best-effort). Em falha transitória ou timeout a chamada é repetida automaticamente (até 3 tentativas, backoff exponencial); persistindo o erro, retorna `isError: true` com mensagem em português (HTTP 404 = série inexistente ou sem dados no período solicitado). O resultado vem como JSON tanto em texto quanto em `structuredContent` (conforme o outputSchema); datas no formato dd/MM/yyyy e valores numéricos (ponto decimal).ConnectorNo auth
- Calcula a variação percentual de UMA série no período, mais estatísticas descritivas. Para série de NÍVEL (dólar, Selic, dívida, produção) é a variação entre o primeiro e o último ponto; para série que JÁ É uma variação por período (IPCA 433, INPC 188, IGP-M 189 e demais índices de preço mensais do catálogo; Selic/CDI acumulados no mês 4390/4391; rentabilidade da poupança 25/195) é o ACUMULADO do período por encadeamento — "quanto o IPCA acumulou em 2024" ou "quanto a Selic rendeu em 2024" é esta tool. O campo `analise.metodo` diz qual das duas contas foi feita; código fora do catálogo curado é tratado como nível. Série de acumulado móvel (IPCA em 12 meses, 13522) é recusada com orientação — o valor publicado já é a resposta. O período pode ser definido por datas (dataInicial/dataFinal) OU pelos últimos N períodos (parâmetro `periodos`, que tem precedência e ignora as datas). Quando usar: para medir tendência/variação/acumulado de uma única série. Quando NÃO usar: para comparar várias séries use bcb_comparar; para os valores brutos use bcb_serie_valores. Requer ao menos 2 observações no período (senão retorna `isError`). Retorna: `serie`, `periodo` (dataInicial, dataFinal, totalPeriodos), `analise` (metodo, valorInicial, valorFinal, diferencaAbsoluta — nula quando encadeado —, variacaoPercentual, variacaoFormatada) e `estatisticas` (maximo, minimo, media, amplitude). Períodos longos são tratados automaticamente: janela diária acima de 10 anos é fatiada (a API do BCB responde 406) e `periodos` acima de 20 é atendido por janela de datas; `chunking` e `janelaAplicada` aparecem na resposta quando isso acontece. Comportamento: consome a API pública SGS do Banco Central do Brasil — sem autenticação, chave de API ou cadastro, e sem limite de requisições divulgado (uso é best-effort). Em falha transitória ou timeout a chamada é repetida automaticamente (até 3 tentativas, backoff exponencial); persistindo o erro, retorna `isError: true` com mensagem em português (HTTP 404 = série inexistente ou sem dados no período solicitado). O resultado vem como JSON tanto em texto quanto em `structuredContent` (conforme o outputSchema); datas no formato dd/MM/yyyy e valores numéricos (ponto decimal).ConnectorNo auth
- Compara de 2 a 5 séries temporais no MESMO período (dataInicial e dataFinal obrigatórias), calculando a variação percentual de cada uma e ordenando-as num ranking (maior para menor variação). Série de nível entra pela variação entre as pontas; série que já é variação por período (IPCA, INPC, IGP-M mensais do catálogo; Selic/CDI acumulados no mês; poupança) entra pelo ACUMULADO encadeado do período — cada item diz em `metodo` qual conta foi feita, então "qual índice de preço subiu mais em 2024" é esta tool. Quando usar: para comparar/correlacionar a evolução de vários indicadores lado a lado. Quando NÃO usar: para uma única série use bcb_variacao. Retorna: `periodo`, `totalSeries`, `seriesComDados`, `seriesComErro`, `ranking` (cada item com posicao, codigo, nome, metodo, valorInicial, valorFinal, variacaoPercentual, maximo, minimo, media) e `erros`. Resiliente: séries sem dados no período, e séries de acumulado móvel (IPCA em 12 meses), são isoladas em `erros` sem invalidar a comparação. Periodicidades diferentes: comparar uma série diária com uma mensal alinha pontos que não são comparáveis, e a resposta avisa isso em `aviso`; informe `frequencia` (mensal|trimestral|anual) para harmonizar todas na mesma grade antes de comparar, escolhendo a convenção em `agregacao`. Janelas longas em séries diárias são fatiadas automaticamente (limite de 10 anos da API do BCB). Comportamento: consome a API pública SGS do Banco Central do Brasil — sem autenticação, chave de API ou cadastro, e sem limite de requisições divulgado (uso é best-effort). Em falha transitória ou timeout a chamada é repetida automaticamente (até 3 tentativas, backoff exponencial); persistindo o erro, retorna `isError: true` com mensagem em português (HTTP 404 = série inexistente ou sem dados no período solicitado). O resultado vem como JSON tanto em texto quanto em `structuredContent` (conforme o outputSchema); datas no formato dd/MM/yyyy e valores numéricos (ponto decimal).ConnectorNo auth
- Ayadi shadvarga calculator for a building or a room: send the dimensions and the API returns all six proportional formulas with the multiplier, the divisor and the remainder shown, the member each remainder names, and the two verdict rules the texts state. Choose between three text families, which genuinely disagree, and choose your own cubit length, because every remainder is unit sensitive. Built for practitioner tools, plan checking software and anyone who has to justify a dimension rather than assert it.ConnectorNo auth
- ACCOUNT REQUIRED (free — sign in via GitHub at https://pipeworx.io/signup; depth:"thorough" needs a paid plan). If you are not signed in, use ask_pipeworx instead — it works on every tier. Grounded multi-source research across Pipeworx's 1517 STRUCTURED data sources (SEC filings, FRED/BLS economics, FDA, USPTO patents, markets, science, government records, etc.) in ONE call — this is NOT open-web search. Decomposes your question into focused facets, routes each to the right one of 5,798 tools IN PARALLEL, and returns a findings packet: verbatim evidence + confidence + source + fetched_at + a stable pipeworx:// citation per finding, with explicit gaps[] for facets the data couldn't answer (never invented). Best for broad/multi-part questions over structured data ("compare X and Y's regulatory + financial exposure", "research the filings + market picture for ACME"). For a single lookup use ask_pipeworx (one LLM call, not many). For BREAKING or colloquial CURRENT-NEWS / "what's the world saying about X" topics, prefer ask_pipeworx — it routes to live news APIs and the *-news-feeds packs; deep_research returns mostly empty gaps[] when the topic isn't in the structured catalog. Second-hop iteration: depth:"standard" re-angles unanswered gaps (gap recovery); depth:"thorough" additionally chases the best leads from the first pass — so multi-step questions resolve in one call. Every finding carries a `hop` field and a citation_uri — a resolvable pipeworx:// record URI, present only when the source emits one that resources/read can actually serve, so a citation you get back is always fetchable. "standard" and "thorough" also return contradictions[] flagging findings that disagree. Large records are semantically excerpted to the passages relevant to each facet (not head-truncated), so answers deep in a long filing/series aren't missed. Expect 15-60s (thorough with its follow-up + contradiction pass: up to ~90s).ConnectorNo auth
- "Is it true that…" / "fact check" / "verify the claim that…" / "did X really…" / "was Y actually…" / "confirm or refute" / "true or false" — natural-language claim verification against authoritative sources. Use whenever the agent needs to check whether something a user said is factually correct. Company-financial claims (revenue, net income, cash for public US companies) verify via the structured SEC EDGAR + XBRL fast path with exact percent-delta math; ANY OTHER factual claim (macro statistics, rates, prices, drug data, records) automatically falls through to the grounded pipeline — routed to the right live source, answered with verbatim evidence, then judged. Returns a verdict (confirmed / approximately_correct / refuted / inconclusive / unsupported / could_not_verify), the grounded or structured actual value with pipeworx:// citation, and reasoning. IMPORTANT for callers: could_not_verify means the check did not happen (our LLM or source failed) and carries verification_error{stage,detail} — it is NOT evidence for or against the claim, and must not be shown as one. unsupported means we looked and cover no source for it. Replaces 4–6 sequential calls (NL parsing → entity resolution → data lookup → comparison).ConnectorNo auth
- CALL immediately before adding or upgrading an npm dependency. Answers "is this exact version safe to take on" from registry metadata, advisory deltas, provenance, license, and repository evidence, and returns blockers, warnings, a recommendation, and a verification plan. Example: {"dependency":"lodash","to_version":"4.17.21"} — every field is top-level, never nested under a "change" key. Only `dependency` is required — omit to_version to evaluate the latest published version, exactly as `npm install <pkg>` would. to_version also accepts a dist-tag ("latest") or a SemVer range ("^4.17.0"); it resolves to one exact version, reported back in change.to_version. Everything RepoPilot can infer is inferred, and every default, repair, and resolution is listed in input_adjustments. Evaluates only; never installs or edits anything.ConnectorNo auth
- Recursively resolves one or more direct/root packages' dependency graphs — e.g. the "dependencies" section of a package.json — up to maxDepth levels deep (default 2, max 3) and batch-checks every resolved package@version against OSV.dev, so vulnerabilities buried several levels down (which would never show up from checking direct dependencies alone) still surface. `summary` is a one-sentence, deterministic recap (packages scanned, unresolved count, vulnerable count and which roots pulled them in) — read it first. The `vulnerablePaths` field directly answers "which of my dependencies pulled this in" by naming the root package(s) responsible for each vulnerable transitive package; `nodes` has the full resolved graph (depth, parents, resolutionError) for deeper inspection. Scope/limits worth knowing before trusting a "clean" result: only the "dependencies" field is followed (not devDependencies/peerDependencies/optionalDependencies); each range is resolved independently per branch via semver max-satisfying against published versions — this does NOT emulate npm/yarn's actual node_modules hoisting/dedup, so read results as "which vulnerable versions are reachable in the graph," not the exact installed layout; git/file/workspace/URL/npm-alias dependencies aren't resolvable from the registry and show up with a resolutionError instead of being silently skipped; and the whole traversal is capped at a total node budget — check `truncated`/`truncationNote` rather than assuming a large graph was scanned exhaustively. Prefer batch_query_vulnerabilities instead when you only need to check exact packages you already have a flat list for (faster, no graph walk).ConnectorNo auth
- Given a package and a current/target version, tells you whether that specific upgrade is a safe patch/minor bump or a likely-breaking major bump, before you actually run npm install. Natural follow-up to prioritize_remediation: pass its `packageName` + `currentVersion` + `fixedVersion` straight in to check whether the suggested fix is a drop-in patch or something that needs a review pass. Classifies the jump by semver (major/minor/patch/prerelease), treats a minor bump between two pre-1.0 (0.x) versions as breaking-risk per semver's own "the API isn't stable yet" convention, and flags skipping over multiple major versions in one jump (e.g. 2.x -> 5.x) as needing a per-major changelog review rather than just a diff against the final target. Beyond semver, it also checks the registry for real signals the version number alone won't tell you: whether the target version is marked deprecated, whether it introduces a preinstall/install/postinstall/prepare lifecycle script the current version didn't have, whether it tightens its engines.node requirement, and whether it is itself a prerelease. Finally it batch-checks both versions against OSV.dev and reports vulnerabilityDelta (introduced/fixed/still-vulnerable/still-clean) — catching the case where a suggested "fix" version doesn't actually clear every open CVE. Combines all of this into one riskTier (safe/low-risk/review-recommended/breaking-change-likely/unknown) with a reasons list explaining exactly which signals drove it. This does NOT read the package's changelog/release notes or scan the target tarball's source diff for actual breaking API usage — it's a fast, deterministic pre-check, not a substitute for reading the release notes on a flagged major bump. For simulating more than one upgrade at once — e.g. every "patch-now" finding prioritize_remediation just ranked — pass `packages: [{packageName, currentVersion, targetVersion?}, ...]` (1-100 items) instead of `packageName`/`currentVersion`/`targetVersion`, not both. Registry fetches are deduped/parallelized and all OSV checks for the whole batch run as one call, so this is not the same cost as N single-item calls. A package that can't be resolved at all (typo, unpublished, registry error) shows up as its own `results` entry with `fetchError` set instead of failing the whole batch.ConnectorNo auth
- Consulta o histórico de valores de UMA série temporal do BCB pelo código SGS, opcionalmente limitado por um intervalo de datas (dataInicial/dataFinal). Quando usar: para obter a série histórica completa ou uma janela de datas específica. Quando NÃO usar: para apenas os pontos mais recentes use bcb_serie_ultimos; para a variação percentual use bcb_variacao; para comparar várias séries use bcb_comparar; se não souber o código, descubra-o antes com bcb_buscar_serie ou bcb_series_populares. Retorna: objeto `serie` (codigo, nome, categoria, periodicidade), `totalRegistros`, `periodoInicial`, `periodoFinal` e `dados` (array de {data, valor}); quando não há dados, `totalRegistros` = 0 e uma `observacao` explicativa. Períodos longos: a API do BCB limita séries DIÁRIAS a 10 anos por consulta e recusa janela aberta (HTTP 406). Isso é tratado automaticamente — a janela é fatiada em requisições de até 3 anos e o resultado vem fundido e ordenado, com `chunking` na resposta dizendo quantas janelas foram usadas; se o período pedido estava aberto numa série diária, `janelaAplicada` diz qual janela foi usada e por quê. Harmonização: `frequencia` (mensal|trimestral|anual) reamostra a série antes de responder, com a convenção escolhida em `agregacao`; a resposta traz `harmonizacao` com `derived: true` e a nota do cálculo. Comportamento: consome a API pública SGS do Banco Central do Brasil — sem autenticação, chave de API ou cadastro, e sem limite de requisições divulgado (uso é best-effort). Em falha transitória ou timeout a chamada é repetida automaticamente (até 3 tentativas, backoff exponencial); persistindo o erro, retorna `isError: true` com mensagem em português (HTTP 404 = série inexistente ou sem dados no período solicitado). O resultado vem como JSON tanto em texto quanto em `structuredContent` (conforme o outputSchema); datas no formato dd/MM/yyyy e valores numéricos (ponto decimal).ConnectorNo auth
- Obtém as últimas N observações de UMA série temporal do BCB (mais recentes primeiro a partir do fim da série). Quando usar: para ver os dados mais recentes sem precisar calcular datas (ex.: últimos 12 meses do IPCA). Quantidade entre 1 e 1000 (padrão 10). Quando NÃO usar: para um intervalo de datas ou o histórico completo use bcb_serie_valores. Retorna: objeto `serie`, `totalRegistros` e `dados` (array de {data, valor}); sem dados, `totalRegistros` = 0 com `observacao`. Acima de 20: o endpoint nativo do BCB rejeita N > 20 em qualquer periodicidade, então o servidor descobre a periodicidade da série e busca por janela de datas, devolvendo os N últimos pontos. Comportamento: consome a API pública SGS do Banco Central do Brasil — sem autenticação, chave de API ou cadastro, e sem limite de requisições divulgado (uso é best-effort). Em falha transitória ou timeout a chamada é repetida automaticamente (até 3 tentativas, backoff exponencial); persistindo o erro, retorna `isError: true` com mensagem em português (HTTP 404 = série inexistente ou sem dados no período solicitado). O resultado vem como JSON tanto em texto quanto em `structuredContent` (conforme o outputSchema); datas no formato dd/MM/yyyy e valores numéricos (ponto decimal).ConnectorNo auth
- Busca séries do BCB por palavra-chave (ou pelo código) em DUAS camadas: o catálogo curado local de 135 séries verificadas contra a origem, que vem primeiro e com `fonteNome` dizendo se o nome é transcrito do portal do BCB ou herdado, e o índice do Portal de Dados Abertos do BCB, com milhares de séries identificadas por código. Ignora acentos e maiúsculas ('inflacao' encontra 'Inflação'); vários termos são combinados com E ('ipca servicos'). Quando usar: para descobrir o código de uma série antes de consultar valores. Quando NÃO usar: para navegar tudo por categoria use bcb_series_populares; para valores use bcb_serie_valores. Retorna: `termo`, `totalEncontradas`, `series` (cada item com codigo, nome, origem — 'curado' ou 'indice' — e, no índice, `dataset` com a página do portal), `catalogo` (origem, obtidoEm, seriesIndexadas, cobertura) e, quando aplicável, `observacao`, `avisos`, `mensagem` e `sugestao`. Cobertura: o índice NÃO é o SGS inteiro, portanto não encontrar aqui não prova que a série não exista — o campo `catalogo.cobertura` diz isso explicitamente em toda resposta. Comportamento de rede: o índice é servido de cache com validade de 24 h e a renovação é feita pela primeira busca após o vencimento (uma requisição ao portal, ~1 s); as demais buscas não tocam a rede. Se o portal estiver fora, a busca degrada para o catálogo curado (ou para o último índice obtido) e sinaliza em `avisos`, sempre com a data de obtenção visível.ConnectorNo auth