Skip to main content
Glama
822,164 tools. Updated 2026-11-22 20:48

"Laravel Nova" matching MCP tools:

  • Authoritative 'what fired and when' stream — wraps the `alert_history` table (one row per incident, both legacy and modern) and `alert_outlet_log` (per-dispatch ledger keyed by history_id). Default mode: lists incidents newest-first. Each row is one incident with opened_at / last_event_at / resolved_at framing the lifecycle, plus aggregated outlet_types[], dispatch_count, and failed_count. `status` is computed from resolved_at: 'open' if null, 'resolved' otherwise. Drill-down mode: pass `incident_id` (the `alert_history.id`, NOT `alert_id`) to switch the call to /api/alert-history/{id}/log and return the per-outlet dispatch ledger for that one incident. Use this for 'did the email actually go' / 'what did the webhook payload look like' / 'which outlets failed' follow-ups. Filters (default mode, all client-side, AND-combined): status (open|resolved|all, default all), severity (int or array — scheme is 1-5, lower=worse), device_id, source (legacy|modern|all), hours (1-168, default 24, applied against last_event_at), search (substring on alert_label/subject). Important caps: the upstream endpoint returns at most 500 rows ordered by last_event_at DESC. We can't reach older rows than that. `meta.upstream_cap` reports this so the LLM can warn the user when results may be truncated. `severity_label` is added server-side so the LLM doesn't memorize the scale. Pagination is over the post-filter result. Tag-scope is enforced by Laravel — tag-restricted users see only incidents for devices in their slug set. Permission: alerts. Examples: alerts_history({status: 'open', severity: [1,2], hours: 1}) alerts_history({device_id: 42, hours: 24}) alerts_history({incident_id: 9182}) // dispatch ledger
    ConnectorNo auth
  • Get NOAA harmonic tide predictions (future or past) for a station. interval="hilo" (recommended for "when is high/low tide") returns the daily tide events with type H/L — up to 10 years per request. Other intervals (h, 1, 5, 6, 10, 15, 30, 60 minutes) return a height time series — up to 1 year per request. Heights are relative to the requested datum (MLLW default). Notes: - Great Lakes stations have NO tide predictions (lake levels are not tidal). - Subordinate stations (type "S") only support interval=hilo; use the station's reference (R) station for interval series. - Predictions are astronomical only — they exclude weather effects (storm surge, wind setup). Compare with noaa_get_water_levels for actual conditions.
    ConnectorNo auth
  • Atualiza uma transação existente (parcial — campo omitido/vazio mantém o valor atual). Se amount, type ou accountId mudarem, reverte o efeito de saldo da versão antiga e reaplica com os novos valores (retorna 400 se a nova conta não tiver saldo suficiente para EXPENSE/TRANSFER). Não reajusta parcelas irmãs (currentInstallment/totalInstallments) nem faturas de cartão — para mudanças que afetam cartão, prefira excluir e recriar. Dispara recálculo de projeções e insights (best-effort).
    ConnectorOAuth
  • Recent WAN speedtest results — answers 'is the internet healthy?'. Wraps GET /api/getSpeedTestHistory. Returns rows ordered by timestamp desc. Each row carries the upstream's SpeedtestLog shape — typically {id, timestamp, download_mbps, upload_mbps, latency_ms, jitter_ms, server, ...}, but any new columns added on the Laravel side flow through automatically. The tool doesn't reshape the row contents — just filters by time window and limits the return. Lower priority than ping/traceroute/netflow for general 'internet slow' investigations, but the right tool when the user specifically asks about WAN throughput trends or recent speedtest runs. Filters (client-side): hours (1-720, default 168 = 7d), limit (1-100, default 25). The upstream endpoint returns the full history with no server-side cap — narrow with hours rather than fetching unbounded. Permission: tools. Example: speedtest_history({hours: 24})
    ConnectorNo auth
  • Altera a status page pública da conta: nome (título), endereço (subdomínio em <slug>.tarodando.com.br), descrição, link do site, link de contato, logo e favicon — tudo que a aba Nome e endereço da Status page no painel edita, com as mesmas regras. Seções e a lista de monitores da página são estruturar_pagina; quem recebe alerta é vincular_canal (esta tool não mexe em alertas). Só os campos enviados mudam. O slug é normalizado (minúsculas, sem acento, hífens) e precisa de 3+ caracteres; endereço em uso devolve slug_taken; endereço reservado, reserved_slug. Se a conta ainda não tem status page (statusPage null em ver_conta), a tool cria: aí `name`, `slug` e `monitorIds` são obrigatórios (sem os três devolve no_page; se a conta já ganhou página no meio do caminho, page_exists). `monitorIds` decide o que fica PÚBLICO: ids de listar_monitores, "all" ou [] pra nenhum. Se algum id não for monitor da conta, nada é criado e volta monitor_not_found com os ids recusados. Devolve a URL nova; ao trocar o endereço, o antigo passa a redirecionar pro novo e fica reservado para a página, e a resposta lista monitores que ainda checam o endereço antigo (não altera nada sozinha).
    ConnectorOAuth
  • The product-tagging worksheet of ONE workspace — the template as JSON: the drawers (tag groups) the workspace has, and a row per (account, ASIN, SKU) catalog product with its CURRENT tags per drawer (`tags: {Brand: ['Acme']}`; predefined rule-based drawers are computed and never listed). Use it to match a seller's tagging file to exact SKUs/ASINs before building import_product_tags rows; drawer + untaggedOnly=true lists the products not yet tagged in that drawer. CHANNELS: lists Seller Central (3P) products by default; pass channels=['VENDOR'] for the Vendor Central (1P) products, or ['SELLER','VENDOR'] for both. Each row then carries `channel`; a 1P row is one product per (account, ASIN), tagged under its ASIN: its `sku` IS the ASIN (copy it as is into import_product_tags with channel 'VENDOR') and `vendorCode` is the code the 1P pages print. An ASIN sold on both channels is two rows, tagged apart. One workspace in scope = implicit; several = pass `workspace`. Paginate with limit/offset.
    ConnectorOAuth

Matching MCP Servers

  • A
    license
    Not graded
    quality
    B
    maintenance
    Connects AI assistants to Laravel Nova resources, allowing them to discover resources, read records, and perform authorized operations while enforcing existing Nova permissions and per-token restrictions.
    1
    MIT

Matching MCP Connectors

  • Read and send mail from your Nova Inbox (@nova.civai.co) for OTPs, directory signups, and inbound m…

  • Paid NOVA research, company intelligence, and output recovery for agents.

  • Edita um PRAZO processual do Astrea no lugar, PRESERVANDO o prazo_id (mudar data fatal, título, responsável, observações ou etiquetas). NÃO exclua e recrie: isso gera um id novo e apaga as tarefas vinculadas. - prazo_id: id do prazo (de astrea_prazo_criar ou de um DEADLINE em astrea_agenda). - Informe ao menos um campo; o que você omitir fica como está. - Nova data fatal, de UM destes jeitos: due_date (AAAA-MM-DD pronta) ou dias + data_inicial (+ contagem "uteis"|"corridos", + considerar_recesso), e o Astrea calcula, como em astrea_prazo_criar. - Ao mudar a data fatal, as TAREFAS ABERTAS do prazo andam junto, pelo mesmo número de dias (a tarefa D-3 continua D-3). O Astrea sozinho não move as tarefas; esta tool move. mover_tarefas=false deixa as tarefas nas datas antigas. Tarefa concluída ou sem data não muda. A resposta lista cada tarefa com a data de e para. - title / comments / responsible_id (ver astrea_responsaveis) / tag_ids (substitui a lista de etiquetas do prazo).
    ConnectorNo auth
  • Open an interactive ER diagram of a database schema on erddocs.com. Use it when the user wants to see, understand, review or document their database structure, or asks for an ER diagram. Pass the schema text exactly as it is in the project. It reads SQL dumps and DDL (PostgreSQL, MySQL, SQL Server, SQLite), Prisma schema.prisma, DBML, Mermaid erDiagram, PlantUML, Django models.py, SQLAlchemy models, Sequelize models, TypeORM entities and a folder of Laravel migrations (concatenate the files). For SQL, the structure is enough: no INSERT data. Returns a link. The user opens it in a browser and gets the diagram with every table and relation laid out, relations without declared foreign keys found by column name and drawn dashed, and a data dictionary. Nothing is stored on the server: the schema travels inside the link and is parsed in the user's browser. A link holds a schema of a few dozen tables (about 100–200 characters of link per table, depending on comments); for a larger one the tool says so and the user pastes it on erddocs.com instead.
    ConnectorNo auth
  • Find Nova Poshta branches and parcel lockers in a Ukrainian city where a RoutersUA order can be collected, from the directory the store checkout uses. Use it when the user asks where to collect an order or which point is near them; for ship and delivery dates use routersua_estimate_delivery, and for delivery cost and payment routersua_get_store_policy. If the city name matches several places, the result lists them; call again with city_ref. At most 30 points come back; more_points true means there are more, so narrow with query. An unknown city returns an error.
    ConnectorNo auth
  • Remove chosen discovered leads (by lead_id from list_leads) from this agent's Leads Discovery scan results, for example leads from the wrong country or the wrong groups. It never deletes a CRM chat: to delete conversations use remove_chats. Call it ONCE with every lead_id to remove; the owner approves once. Later scans do not find these people again. Leads already imported keep their CRM chat; the result lists their visitor_ids.
    ConnectorNo auth
  • Search Open Food Facts by full-text query, structured tag filters, or both at once. Returns a summary list with barcodes, product names, brands, Nutri-Score, NOVA group, Green-Score, and categories — enough for triage and selection, not full label data. Use off_get_product on the returned barcodes for complete details. A text query and tag filters combine: every word of the query must match the product name, generic name, categories, labels, or brand, and every filter provided must hold (e.g. query "dark chocolate" with labels_tag "en:organic" and countries_tag "en:france" returns organic chocolate sold in France); numeric nutrient_filters express thresholds per 100 g, or per 100 ml for liquids, such as sugars below 8 g, and combine the same way, and each row then carries the indexed values the thresholds were checked against; ingredients_tag takes canonical ingredient IDs (e.g. "en:inulin") that must all appear among the ingredients Open Food Facts parsed from the label, and combines the same way; additives_tag is the one exception, filtering only on searches carrying none of query, nutrient_filters, or ingredients_tag. nutrition_grade, nova_group, and ecoscore_grade (Green-Score) each take one grade or an array matching any of them. Tag filter values are canonical tag IDs (e.g. "en:organic", "en:no-gluten") — use off_browse_taxonomy to resolve human terms to tag IDs. A case variant, synonym, or singular of a tag is resolved to its canonical ID where Open Food Facts recognizes it; anything else is matched exactly. exclude_allergens and exclude_traces drop products that declare an allergen or a "may contain" trace, but a product with no allergen or trace data entered passes them, so confirm a candidate with off_get_product before relying on it. At least one search parameter is required. The two paths read different indexes: a search carrying query, nutrient_filters, or ingredients_tag is answered by the text index, a snapshot that lags the live database, while a tag-only search reads the live database and is current, or, where this server keeps a local copy of the Open Food Facts export, can be served from that copy, which source and mirror_as_of then report and whose default order and popularity_key or unique_scans_n sort follow the values stored with each record, so they can differ from a live search, which ranks by its current scan counts — so a recently contributed product can be missing from a text search and present in the same search without query. Data is crowd-sourced; result count reflects contributed products, not all products in the market. Data under ODbL 1.0 — cite Open Food Facts in downstream use.
    ConnectorNo auth
  • Resolve a human term to the canonical Open Food Facts tag ID that off_search_products filters on. Covers categories, labels/certifications, allergens, additives, countries, ingredients, NOVA groups, and Nutri-Score grades. Pass a search term to resolve against the Open Food Facts vocabulary, which holds tens of thousands of tags; omitting it returns only a small reference list for each facet except NOVA groups and Nutri-Score grades, which are complete, and ingredients, which has no reference list and returns nothing. Most tag IDs use the "en:" prefix (e.g. "en:organic", "en:no-gluten", "en:crustaceans"); NOVA groups return bare digits "1"-"4" and Nutri-Score grades bare letters "a"-"e". Pass the id through to off_search_products exactly as returned. Category tags are frequently plural ("kombucha" resolves to "en:kombuchas") and ingredient tags singular ("oat" resolves to "en:oat", "oats" to nothing), so use the returned id rather than constructing one.
    ConnectorNo auth
  • Search for geographic locations by category (CITY, ST, CNTY, CNTRY, ZIP, CLIM_REG, etc.). Returns location IDs used in station search and data queries. Without locationCategoryId, returns all location types; noaa_climate_list_location_categories lists the valid values. Use locationCategoryId=ST to list US states (51 entries — small enough to retrieve completely). To find a location by name, pass nameContains alongside locationCategoryId — the CDO API has no name parameter, so this server enumerates the category and matches the substring itself. It works for any category under the size limit stated on nameContains, which is every category except ZIP; a datasetId or datacategoryId filter can bring a category back under that limit. For a category still too large, sort alphabetically with sortField=name and page through results. Location IDs: states as FIPS:37 (NC), cities as CITY:US530018 (Seattle), zip codes as ZIP:98101, countries as FIPS:US. Obtain location IDs here, then pass them to noaa_climate_find_stations or noaa_climate_fetch_data.
    ConnectorNo auth
  • Get NOAA's Interagency Sea Level Rise Scenario projections for a station (from the 2022 technical report): projected relative sea level (meters or feet, see units field) per decade through 2150 under the chosen scenario. Scenarios: low, intermediate-low, intermediate, intermediate-high, high, extreme, or all. Use for coastal planning questions ("how much sea level rise is projected at X by 2050?"). Pair with noaa_get_sea_level_trends (observed) and noaa_get_high_tide_flooding (flooding impact).
    ConnectorNo auth
  • Tells whether a language, runtime, framework, database or operating-system version is still supported and when it reaches end of life. Covers about 480 products (Python, Node.js, PHP, Java, Ruby, Go, Rust, Django, Laravel, Rails, React, Angular, PostgreSQL, MySQL, Ubuntu, Debian, Kubernetes and more). With product and version it returns that version's status (supported / security_only / end_of_life / upcoming), its release, active-support and end-of-life dates, days remaining or elapsed, and the cycles that are still supported; with only product it returns every release cycle; with neither it lists the product identifiers. Read-only and requires no authentication. Status is computed on every call from today's date; the dates come from endoflife.date and are refreshed every 12 hours. Use it before choosing a runtime or base image, when writing a Dockerfile or CI matrix, or when auditing an old version. It concerns the language, runtime or platform itself; for a library's own versions use package_status.
    ConnectorNo auth
  • What did a web page say on a given date? Finds the archived capture of a URL nearest that date across the Internet Archive Wayback Machine, Common Crawl and Arquivo.pt, reads it, and returns the readable text (HTML stripped) with the capture timestamp, a link to the archived copy, and the GAP between the date asked for and the capture actually used (e.g. "Captured 1.5 day(s) before the requested date"). One call replaces the find-capture, fetch-record, parse-HTML chain. If no archive holds a capture within max_gap_days (default 30) it answers status "no_capture" and names the nearest capture before and after the date with their gaps, so a distant capture is never passed off as the page on that date. Every archive's outcome is listed in sources[]; one that timed out or errored says so with its upstream status, and if all of them failed the answer is error "archives_unavailable", not no_capture. Captures are immutable and cached by capture id; served_from says whether the text came from cache or upstream. Use archive_compare to see what changed between two dates.
    ConnectorNo auth
  • Claygent-style per-row research: answer ONE question about ONE company and return a JSON object matching your output_schema, with every field wrapped in its own evidence, {value, evidence_url, quote, status}. status is NEVER self-reported by the model: "found" means this code independently verified the model's quote is a VERBATIM substring of text actually fetched; "inferred" means a value was given but the quote could not be verified; "not_established" means no source answered the field, and its value is always null, never guessed, never a blended score. Sources: "web" fetches the company's own site (entity.domain required, homepage, /about, /leadership) via fetch_url; "catalog" checks entity_profile (SEC EDGAR; resolved:false for a private company is expected, not a failure); "both" (default) tries both. max_cost (USD, default 0.02, max 0.50) scales how many pages are fetched and refuses up front if it is too small to pay for even one extraction call (floor $0.002), never silently overspends. A row where every source comes back empty costs nothing: every field is mechanically not_established with NO model call made. For a boolean/derived field (e.g. "does this company sell to healthcare"), the quote only has to SUPPORT the value, a descriptive sentence about customers/products counts, the source need not state the answer verbatim. leadership_page_status ("fetched"|"not_found"|"not_attempted", plus leadership_note) says plainly whether a leadership/team page was actually read, so a named-person field (head_of_sales) coming back not_established is distinguishable from "this company just doesn't publish one" vs. "we never checked". model_output_empty:true means the model returned nothing usable (a transport/budget problem), every field is not_established for THAT reason, never read as 20 individual "no" judgments. Use with a fixed question + schema across many rows for "Claygent over N companies with a hard cost cap" (composes with batch callers). For picking from a fixed label list instead of extracting open fields, use classify_row (cheaper, one model call).
    ConnectorNo auth
  • Tell the Pipeworx team something is broken, missing, or needs to exist. Use when a tool returns wrong/stale data (bug), when a tool you wish existed isn't in the catalog (feature/data_gap), or when something worked surprisingly well (praise). ONLY for tools served by this Pipeworx connection, if the tool came from a different MCP server in your client (another vendor's Gmail, Splunk, Slack, etc. connector), we cannot fix it and reporting it here only delays you; file it with that server instead. Not sure? Pipeworx tool names are the ones this connection lists. Describe the issue in terms of Pipeworx tools/packs, don't paste the end-user's prompt. Filing without an account returns a `claim_token`; pass it back later as pipeworx_feedback({claim_token:"pwfb_..."}) to read whether it was fixed and what changed. The team reads digests daily and signal directly affects roadmap. Rate-limited to 5 per identifier per day. Free; doesn't count against your tool-call quota.
    ConnectorNo auth
  • Population and median household income for the county containing a point, from American Community Survey 5-year estimates. Composes two ingested datasets (§22.2): TIGER/Line resolves the coordinate to a county GEOID, then the ACS layer is read by that key. Pass `geoid` directly to skip the boundary lookup. Values are survey ESTIMATES with margins of error, not counts, and a suppressed estimate is returned as null rather than filled in. The release that produced them is in `dataset_version` and in each metric's `period`. When to use: Use for "how many people live in this area" or "what is the median income there". Give a coordinate, or a county GEOID from admin_areas. Billed as property.area_demographics at 1c. Every response includes a sources[] array naming the data origin and licence.
    ConnectorNo auth
  • Free. Turns a US street address into a latitude/longitude plus the state, county and census tract it is in (with GEOIDs), using the U.S. Census Bureau geocoder. Use it first, then pass the point to the paid property tools. One-line address to point, with the Census Bureau's own match: the matched address, ZIP code, coordinates and the state, county and tract containing them. An address the geocoder cannot place is reported as not found, never guessed. US addresses only; PO boxes and rural routes often do not match. When to use: Use when you have a US street address and need its coordinates, county or census tract. Free. flood_zone, hazard_history and address_profile also accept the address directly, so call this only when the user wants the location itself. This tool is free and does not consume plan credits. Every response includes a sources[] array naming the data origin and licence.
    ConnectorNo auth
  • Natural-hazard history for a US county or address: FEMA declarations (major disasters, emergencies and fire management, by type, with links), NOAA storm events with deaths and reported property damage by type and year, and USGS earthquakes within 100 km since 1950. One call, each source reported apart. Three federal sources, fetched together: - **FEMA declarations** for the county since 1 January of the first year: the total (major disasters, emergencies and fire management), major disasters alone, count by incident type, and the declarations themselves with FEMA ids and links. Statewide declarations are included. - **NOAA Storm Events** for the county: events, deaths, injuries and reported property and crop damage (nominal dollars; unreported damage counts as 0, so it is a floor), by type and by year, plus the worst events. Events NOAA records for a forecast zone covering only this county (most heat and winter-storm deaths) count as the county's own; a zone covering several counties is counted, but its casualties and damage are reported apart in `zone_based`, because they are shared. The current year is incomplete; NOAA can trail by months. - **USGS earthquakes** of magnitude 2.5 or more within 100 km of the point since 1950: the count and the five largest. This needs a point, so it is skipped when only a county GEOID is given. Each section has its own `status`; if one source is down the others still answer. If neither FEMA nor NOAA can answer, the call fails and is not charged. Connecticut's planning regions (since 2022) are not yet matched to the old counties FEMA and NOAA still use, so they are not answered; the old county GEOIDs (09001-09015) work. A GEOID that is not a county is not found. A `geoid` is used only when no address or coordinate is given. When to use: Use for "has this area had floods, hurricanes or earthquakes", disaster declarations, storm damage history, or natural-hazard due diligence for a US property or county. For the flood zone at a property use flood_zone; for everything about an address in one call use address_profile. Billed as property.hazard_history at 2c. Every response includes a sources[] array naming the data origin and licence.
    ConnectorNo auth