"Cockpit" matching MCP tools:

• scoreconso_render_case_cockpitA

  ScoreConso — service documentaireA

  Rend dans un cockpit un résultat complet déjà produit par scoreconso_route_case, scoreconso_route_guarantee_case, scoreconso_route_advance_payment_case, scoreconso_route_subscription_case, scoreconso_route_marketplace_case ou scoreconso_route_payment_fraud_case. Appelez d'abord l'outil de routage adapté, puis transmettez son structuredContent sans le modifier. Sans prise en charge de MCP Apps, retourne le même résultat structuré exploitable en texte.

  ConnectorNo auth

• dropyour_rollbackA

  DropyourA

  Roll a GRADUATED app back to a previously published version — this is the EXPECTED FAILURE PATH of dropyour_release, which calls it for you when a check fails. Reach for it directly when you published something broken outside that loop. It only moves a pointer: no bytes travel, nothing is rebuilt, and the URL never changes. Call dropyour_list_versions first and pass a version number you saw there; an unknown number is refused. Version 0 restores the frontend shipped at graduation. This does NOT step the app back down to a regular drop — that changes what the app is, and stays a human decision in the owner's cockpit.

  ConnectorNo auth

• ads_performanceA

  VendoolyC

  READ-ONLY, DETERMINISTICO. Performance Ads dal Data-Hub con numeri calcolati dal server, SEMPRE uguali a parità di dati: finestre FISSE di 7/14/30 giorni chiuse 3 giorni prima dell'ultimo dato (attribuzione Amazon ancora incompleta), ACoS/CTR/CVR/CPC/RPC/AOV dalle somme SQL, confronto con il periodo precedente, e per ogni riga una colonna action con la regola applicata: HOLD_DATA (pochi click: non toccare), HOLD_OK, BID_DOWN (ACoS sopra target: bid suggerito = ricavo/click × ACoS target, taglio max 25%/40%), BID_DOWN_ZERO_SALES (click senza ordini, max −30%, floor 0.10), BID_UP (+10/15% se ACoS ≤ 0.8×target), NEGATIVE_EXACT (termine con click e 0 ordini), HARVEST_EXACT (termine che converte sotto target in match non esatto → nuova keyword exact), NEGATIVE_TARGET / HARVEST_TARGET (stesse regole quando il termine è un ASIN: negative product target / nuovo product target, mai keyword), REVIEW_KEYWORDS / REVIEW_ZERO_SALES (campagna da aprire a livello keyword), SCALE_CANDIDATE (manuale), SET_TARGET (manca acos_max: impostalo con set_cockpit_target). Il target ACoS viene dal cockpit ORC-058 (set_cockpit_target, per outpost) o dall'argomento acos_max. USALO al posto di execute_sql per QUALSIASI domanda su ACoS/spesa/keyword che sprecano/cosa tagliare o alzare: non riscrivere le formule. Per agire: rileggi lo stato live con ads_list_* e proponi la scrittura con ads_update_*. Org-scoped: senza account_id copre tutti gli outpost autorizzati; con account_id filtra quell'outpost. Livelli: campaign (default) | keyword | search_term.

  ConnectorOAuth

• gtm_connect_linkedinA

  GTM OttoA

  The link a human opens to connect (or reconnect) their LinkedIn account to a play — the one cockpit step the play cannot run without. Hand the URL to the human, tell them to say when it is done, then call gtm_linkedin_status: the seat reads `classic` or `sales_navigator` once bound. The link expires in 15 minutes; call again for a fresh one. Nothing is sent, nothing is read from their account by this call.

  ConnectorNo auth

• dropyour_autonomyA

  DropyourA

  Declare how much you delegate to the machine on ONE of your apps. Three modes. 'copilote' — nothing is autonomous: every call is a human gesture you are relaying, and everything your authority allows goes through. This is the state of every app until you delegate. 'jalons' — the machine acts alone on reads and on anything it can undo; structural decisions (graduating, stepping down) come back to you. 'autopilote' — it also decides structural moves alone. WHAT NO MODE EVER REACHES: an action nothing can undo — deleting a drop, deleting a secret. No delegation covers it, in any mode; that is what 'bounded' means here. Those are done from the cockpit, by the person who answers for them. Requires a connected account, never a management token: a token proves you hold this drop, not that you are the one answering for what a machine does next. Every change is filed, both ways.

  ConnectorNo auth

• dropyour_records_visibilityA

  DropyourA

  Declare the visibility of ONE collection of your graduated app's store. Two values, no policy language. 'partagee' (the default): all in-app reads see the whole collection — today's behaviour, nothing changes. 'par-auteur': each SIGNED-IN visitor only sees and touches their OWN rows (list, get, getMany, count/aggregate, and writes: overwriting or deleting someone else's row is refused); an in-app request with no signed visitor sees an empty set; YOU, the owner, always see everything through MCP and the cockpit. Rows written before authorship existed (author NULL) are visible to no visitor under 'par-auteur' — only to you. What this does NOT cover, so you are not surprised: the shared state blob (app.state) and realtime broadcasts stay visible to everyone — the store is the per-visitor data path. Declared, never derived from your code; reversible with the same call.

  ConnectorNo auth

• gtm_create_playA

  GTM OttoA

  Create a fully-configured play in one call: the product (an existing productId, or a websiteUrl which seeds one and kicks its research), the play itself, the ICP facets, which sourcing lanes are on, the autonomy ladder and the caps. Three rules are enforced server-side and cannot be talked around. (1) `activate` DEFAULTS TO FALSE — turning a play on spends the month's lead quota and takes real actions from the user's own LinkedIn account, so hand the human the returned cockpit link and let them press go. (2) A play with no live LinkedIn seat stays a draft whatever you pass. (3) Autonomy rules are written ONLY for the steps you name; every step you omit keeps gtmotto's own default, which is 'wait for a human'. Lanes that need their own seeds (post_engagers, competitor_posts, account_list) are refused if switched on without them.

  ConnectorNo auth

• gtm_show_sourcesA

  GTM OttoA

  All five sourcing lanes of a play, configured or not — the read to make before touching any of them. Per lane: `configured`, `on`, the parsed `config` (defaults filled), the cockpit's `summary` (null = needs setup), `blocked` (why it cannot run, judged without running: needs_config / icp_empty / null), last/next run and the last run's funnel, `addedToday`, `failures`, and the lane's memory — `accounts[]` with `found: true|false` per typed company on account_list, `harvestedPosts` on the post lanes, the cached `searches` the model wrote on Post discovery. Play level: `state` is the same verdict the cockpit shows when the Leads table is empty (no_sources / paused / draft / no_seat / seat_broken / icp_empty / needs_config / lead_quota / never_ran / no_results / provider_error / added_nothing / ok), plus provider, seat, ICP facet count and the month's remaining lead quota. Read-only.

  ConnectorNo auth

• set_cockpit_targetA

  VendoolyC

  Set the monthly sales target of one outpost (seller × marketplace) for a calendar month. Owners/admins only. vat says whether the target is VAT included (inclusa, default, same basis as the data) or excluded (esclusa: the cockpit then flags it yellow because it compares different bases). status: proposto (default) | validato | concordato; changing the numbers of a validato/concordato target without passing status puts it back to proposto. Only validato/concordato targets drive the projection light. Confirm amount, month and VAT with the user before saving.

  Connector

  Destructive

  OAuth

• gtm_linkedin_statusA

  GTM OttoA

  The play's LinkedIn seat and today's headroom against the LinkedIn limits. States: `no_seat` (nothing connected — the play cannot act), `seat_broken` (the account was disconnected or deleted; the queue is parked until a human reconnects), `pending`, `classic`, or `sales_navigator` (which search backend the ICP compiles to). Read-only. Connecting a seat is a browser flow — link the human to the cockpit for it.

  ConnectorNo auth

• check_profanityA

  CussCheckA

  Detect English profanity in text (word list with leetspeak, look-alike letters, repeated letters, dotted/spaced letters and hidden characters handled) and return the matched terms, their positions (UTF-16 start/end in your text) and, unless censor is false, a censored copy of the same length. Common innocent words (Scunthorpe, cockpit, Shiite, cumin) are whitelisted; it does not understand context and is English only. Text up to 10240 UTF-8 bytes; it is not stored or logged. matches is capped at 50 here (match_count is the full total). Read-only. Same engine, keys and limits as POST /v1/check.

  ConnectorNo auth

• gtm_list_approvalsA

  GTM OttoA

  Every drafted action that waits for the human — an invite note, a first message, a follow-up, a reply or a comment the planner wrote — with the draft, the 'why now', the lead, and a cockpit link. One play, or the whole workspace when playId is omitted. Show each draft to the human before gtm_approve / gtm_reject; never decide for them. Read-only.

  ConnectorNo auth

• gtm_approveA

  GTM OttoA

  Approve ONE drafted action by its approvalId (from gtm_list_approvals). It then leaves on the seat's next slot, inside LinkedIn's limits — this is the human's tap, moved from the cockpit to the chat, so ONLY call it after showing them the draft and getting a yes in this conversation. An already-decided card is refused.

  Connector

  Destructive

  No auth

• property_value_rangeA

  Heimster – Swiss homesA

  Use this when an OWNER asks what their flat or house is worth (Was ist meine Wohnung wert, Marktwert, valeur de mon bien, quanto vale): returns the link to Heimster's free owner valuation for that address (all of Switzerland, about two minutes, value after a short SMS check, with a personal cockpit). Heimster gives no figure for a specific property here; for area prices use area_market_facts.

  ConnectorNo auth

• estimateA

  Vixdeo — Tu Productor IAA

  What a piece would cost and whether it can launch, BEFORE anything is spent — the same verdict the human cockpit shows. Accepts the same arguments as project creation (idea, format, `source`, `cast`, `production`). $0, no LLM. The answer has two parts: `launch.ready` says whether the REQUEST is complete and allowed (`launch.blockers` names what is missing); `economics` says what it costs and whether the wallet governs it: `estimateUsd` (typical) with `estimateMinUsd`/`estimateMaxUsd` (a band, not a quote — production charges what it actually spends), `walletBalanceUsd`, and `reason`, one of: `guard_inactivo` — billing is not active in this environment: no wallet governs the launch. · `saldo_desconocido` — the wallet balance could not be read; nothing is inferred from that. · `pedido_sin_cotizar` — not enough to price yet: the request needs an idea (`prompt_seed` or `source`) and a `duration_profile` (or the platform default). · `alcanza` — the wallet covers the estimated band. · `casa_invita` — first piece of this account: the balance does not govern it; the band is informational. · `excede_bienvenida` — first piece of this account, and this request is above what a first piece can be: a shorter duration profile or no presenter fits — price the change with `estimate`. · `operador_de_la_casa` — this credential belongs to a platform operator: production is not charged to this wallet; the band is informational. · `no_alcanza` — the organization's balance does not cover the estimated band. `economics.applies` is true only when the wallet does not cover the request; `estimateMaxUsd` against `walletBalanceUsd` is what decides whether a real wallet covers the piece; `hint` restates the reason in words. WHERE THE LINE STOPS FOR FUNDS: the script (first station) is written before the balance is checked and settles with the first render; the first station that checks the balance is the studio build, then the final render — if the balance does not cover a station the line stops there (the project status reports `waitingForFunds` with the station) and what was already produced stays. `vocabulary` in the answer glosses every typed value that is not English.

  ConnectorAPI key

• get_cockpitA

  VendoolyC

  Cockpit for a calendar month: for each outpost the month-to-date sales (VAT included, from the Vendooly data-hub), the month target, the end-of-month projection, Ads ACoS/TACoS, open findings (stock-outs, blocked listings, Ads on out-of-stock items) and a traffic light rosso/giallo/grigio/verde with reasons and the next action (rules 2026-10-15). Without cockpit_id uses the first active cockpit, or all visible outposts if none exists. include_health=true also reads Account Health live (one Amazon report per outpost: slower); without it health counts as UNKNOWN (yellow). Always state the period and that amounts are VAT included.

  ConnectorOAuth

• save_cockpitA

  VendoolyC

  Create (without cockpit_id) or update a cockpit of the user's organization. Owners/admins only. outpost_ids from list_clients (omit = all outposts). status=archived / active. Max 10 active cockpits.

  ConnectorOAuth

• macro_war_room_taskA

  FXMacroDataB

  Build a multi-panel macro market cockpit that combines FX sessions, upcoming release queue, pair context, and generated risk alerts. Returns analysis in the tool response. Access: USD is available without an API key; every other currency returns subscription_required with a subscribe link.

  ConnectorNo auth

• create_taskA

  radtask-mcpA

  Add a task to the user's RadTask cockpit. Use this to capture anything the user wants done or tracked.

  ConnectorNo auth

• ads_list_accountsA

  mcpA

  Liste les comptes Google Ads connectés au compte aeotool (OAuth) : customer_id, nom, statut, is_manager (MCC, non requêtable directement, ses comptes clients apparaissent aussi dans la liste), write_enabled (pilotage en écriture, activable par compte dans le Cockpit Google Ads).

  ConnectorNo auth

• ads_list_accountsA

  mcpA

  Liste les comptes Google Ads connectés au compte aeotool (OAuth) : customer_id, nom, statut, is_manager (MCC, non requêtable directement, ses comptes clients apparaissent aussi dans la liste), write_enabled (pilotage en écriture, activable par compte dans le Cockpit Google Ads).

  ConnectorNo auth