data-connector

Ask AI Data Connector: сводит Shopify, Klaviyo, Google Ads, Xero и другие сервисы в один MCP-сервер

От сообществаРаботаетБез входаГлобальныйБесплатноМожет изменять данные

Что умеет

  • Сравнивать метрики из нескольких источников в одном запросе
  • Показывать сводный дашборд по выручке, трафику и маркетингу
  • Искать заказы, товары и клиентов по фильтрам
  • Выгружать данные по возвратам, скидкам и оборачиваемости склада
  • Оценивать эффективность рекламных кампаний и email-маркетинга

Какие данные видит

Ассистент получает доступ на чтение к подключённым аккаунтам Shopify, Klaviyo, рекламным кабинетам и другим источникам через OAuth; изменение данных не поддерживается.

Нужен ли аккаунт

Не нужен: сервер работает без входа

Ask AI Data Connector объединяет 18 источников данных электронной коммерции — Shopify, Klaviyo, Meta Ads, Google Ads, Xero, ShipStation и другие — в единый MCP-сервер. Ассистент отвечает на вопросы, требующие сравнения данных из разных систем: выручка по email-кампаниям против ROAS в рекламе, маржа на доставке, товары с высоким процентом возвратов. Доступ работает только на чтение, данные хранятся в зашифрованном виде.

Как подключить

Как подключить data-connector к Claude

Адрес сервера, который нужно вставить в настройках Claude:

https://data-connector--ask-ai.run.tools

  1. Откройте Claude (сайт claude.ai или приложение для компьютера).
  2. Перейдите в Настройки → Коннекторы (в английском интерфейсе: Settings → Connectors).
  3. Нажмите Добавить пользовательский коннектор (Add custom connector).
  4. Вставьте адрес сервера, скопированный ниже, в поле URL удалённого MCP-сервера и нажмите Добавить.
  5. В чате нажмите + → Коннекторы и включите новый коннектор.

Пользовательские коннекторы доступны на тарифах Free, Pro, Max, Team и Enterprise. На Free можно добавить только один. В Team и Enterprise коннектор сначала добавляет владелец организации в Настройки организации → Коннекторы.

Авторизация

После нажатия Добавить откроется окно входа в сервис. Войдите под своим аккаунтом и подтвердите доступ. Пароль Claude не видит.

Как подключить data-connector к ChatGPT

Адрес сервера, который нужно вставить в настройках ChatGPT:

https://data-connector--ask-ai.run.tools

  1. Откройте ChatGPT в браузере (chatgpt.com). Нужен тариф Plus, Pro, Business, Enterprise или Edu.
  2. Один раз включите режим разработчика: Настройки → Приложения → Дополнительные настройки → Режим разработчика (Settings → Apps → Advanced settings → Developer mode).
  3. Откройте Настройки → Коннекторы и нажмите Создать (Create).
  4. Заполните форму: Название (любое), Описание (одна фраза, что делает сервис), URL MCP-сервера (скопируйте ниже).
  5. В поле Аутентификация выберите OAuth, если сервис требует вход, иначе Нет. Нажмите Создать.
  6. В новом чате откройте + → Приложения/Коннекторы и включите коннектор.

Название раздела у OpenAI менялось (Connectors → Apps/Plugins). Если пункт называется иначе, ищите «режим разработчика» в настройках. В рабочих пространствах Business/Enterprise администратор должен разрешить пользовательские коннекторы.

Авторизация

При первом использовании ChatGPT откроет окно входа в сервис. Войдите и подтвердите доступ.

Как подключить data-connector к Cursor

Адрес сервера, который нужно вставить в настройках Cursor:

https://data-connector--ask-ai.run.tools

Быстрый способ: нажмите кнопку Открыть в Cursor ниже, Cursor сам предложит добавить сервер.

Вручную:

  1. В Cursor откройте Settings → Cursor Settings → MCP и нажмите Add new global MCP server.
  2. Вставьте JSON, скопированный ниже, в открывшийся файл ~/.cursor/mcp.json (для одного проекта: .cursor/mcp.json в корне проекта).
  3. Сохраните файл. Сервер появится в списке MCP; при необходимости пройдите авторизацию по кнопке рядом с ним.

Авторизация

Если сервис требует вход, рядом с сервером в списке MCP появится кнопка авторизации.

Список инструментов сервера (39)

Технические названия из tools/list. Нужны только разработчикам.

ask_questionQuick natural-language queries about core Shopify data ONLY (revenue, orders, products, inventory, customers). Do NOT use for reviews, email marketing, support tickets, attribution, subscriptions, analytics, SEO, or any third-party data source — use the dedicated tools instead (get_reviews, get_klaviyo, get_gorgias, get_triple_whale, get_recharge, get_ga4, get_search_console, get_youtube, get_clarity, get_loyalty, get_wishlist, get_xero, get_shipstation, get_meta_ads).
get_data_sourcesCALL THIS FIRST to see which data sources are connected and have data. Returns connection status and record counts for: Shopify (always connected), Triple Whale, Klaviyo, Gorgias, Recharge, Google Search Console, Google Analytics, Microsoft Clarity, and YouTube. Use this to understand what data is available before making other queries. If a source shows 'not_connected', those tools will return empty results.
get_complete_dashboardGet a unified dashboard with key metrics from ALL connected data sources in one call. Returns a lean snapshot of revenue, traffic, marketing, email, organic search, UX, support, reviews, subscriptions, and loyalty — only for sources that are connected. Use this for 'Give me an overview' or 'How is the business doing?' then drill into specifics with individual tools.
get_metrics_comparisonBEST FOR COMPARISONS: Get core e-commerce metrics (Revenue, Sessions, CVR, AOV, Revenue per Session) with period-over-period comparisons. Supports WoW (week-over-week), MoM (month-over-month), YoY (year-over-year), and custom period comparisons. Use this for questions like 'How is revenue vs last week?', 'Compare CVR YoY', 'How did this sale perform vs last year's sale?'
get_metrics_multi_compareGet metrics with MULTIPLE comparisons at once. Perfect for questions like 'Show me revenue WoW and YoY' or 'Compare this week to last week and same week last year'. Returns current metrics plus all requested comparisons with percentage changes.
get_daily_metrics_breakdownGet daily breakdown of metrics for charts and trend analysis. Returns daily values for revenue, sessions, CVR, AOV, and revenue per session. Use for visualizing trends over a period.
get_customer_insightsGet customer behavior and retention insights. Reports: new_vs_returning (revenue/orders/AOV split by first-time vs repeat buyers, with % share), repeat_metrics (repeat purchase rate, avg days between purchases, avg lifetime value), cohorts (monthly acquisition cohorts showing size, repeat rate, avg orders, avg revenue), by_category (repeat purchase rate and cross-category rate by product type), cohorts_by_first_purchase (cohorts grouped by what product category the customer bought first).
get_refundsGet refund/return analytics. Reports: summary (total refunds, refund rate, % of revenue), top_products (most refunded products by amount or rate).
get_discountsGet discount code analytics. Reports: summary (usage rate, AOV impact), top_codes (best performing codes by revenue/usage), code_details (specific code performance — requires 'code' param).
get_inventory_velocityGet inventory velocity analytics. Reports: summary (sell-through rate, turnover, health status), by_product (products sorted by sales velocity), restock (reorder recommendations based on velocity and lead time).
get_marketing_performanceGet marketing performance dashboard. Returns: funnel metrics (sessions, addToCartRate, checkoutRate, purchaseRate, cvr), channel breakdown (revenue/sessions/cvr per channel like Google, Facebook, Email, Direct), ROAS and MER from Triple Whale (if connected), and daily trends per channel. Use for marketing ROI, channel comparison, and funnel analysis.
get_products_by_channelGet products with marketing channel attribution showing which channels drive sales for each product. Use for questions like 'Which channels drive sales of product X?' or 'What products does Facebook sell?'
get_store_summaryGet overall store metrics: revenue, orders, average order value, items sold, discounts, unique customers — all for the specified period. Includes percentage changes vs prior period. Also returns all-time totals (orders, products, customers). Use this for high-level store performance questions.
query_ordersQuery and filter orders with various criteria. Returns individual orders with name, status, fulfillment, orderTotal (formatted), items count, country, and date. Use this for questions about specific orders or order lists.
get_ordersGet order analytics by dimension. Reports: by_status (order counts/revenue by financial status), by_country (geographic sales breakdown).
get_top_productsGet top selling products ranked by revenue or quantity. Returns: rank, productId, title, unitsSold, revenue (formatted), and orders count per product. Use this for product performance questions.
get_product_catalogGet product catalog with inventory levels, pricing, variants, and status. Returns: title, status, vendor, productType, totalInventory, variants (price, sku, stock), and tags. Use for questions about what products exist, pricing, or stock levels.
get_customersGet customer analytics by dimension. Reports: segments (one-time/returning/VIP/at-risk), top (by spend or orders — includes customerId for each customer), by_country (distribution by country).
get_inventoryGet inventory analytics. Reports: summary (total products, stock levels), low_stock (products needing reorder), out_of_stock (zero stock), by_location (breakdown by warehouse).
get_daily_revenueGet daily revenue and order count as a time series. Each row: date, revenue (formatted), orders. Use this for charting revenue trends over time.
get_weekly_trendsGet weekly revenue, orders, and items sold as a time series. Each row: weekStart, revenue (formatted), orders, itemsSold. Use this for spotting weekly patterns or seasonal trends.
get_triple_whaleGet Triple Whale marketing analytics. Reports: summary (metrics grouped by category — each metric has id, name, value, type='currency'|'percentage'|'number'; use 'category' to filter: revenue for sales/AOV/profit, ads for spend/ROAS/CPA, customers for new%/LTV/repeat, pixel for sessions/CVR, email for klaviyo revenue), attributions (order-level attribution showing customer journey touchpoints, channel, daysToConvert), by_channel (revenue/orders/AOV per marketing channel like facebook, google, email, organic).
get_klaviyoGet Klaviyo email marketing analytics. Reports: campaign_summary (overall campaign stats), campaigns (individual campaign list — A/B test variants are flagged with isAbTest:true; compare variants by matching campaign name prefix), top_campaigns (best by revenue/opens/clicks), flow_summary (automation stats), flows (individual flow list), top_flows (best automations), list_summary (subscriber overview), lists (individual lists), product_attribution (which products sell via email — revenue & orders per product attributed to email marketing), signup_trends (subscriber growth), available_metrics (tracking events).
get_gorgiasGet Gorgias customer support analytics. Reports: summary (ticket counts by status, avg first response time in seconds + formatted, avg resolution time, CSAT score on 1–5 scale, top channels, top tags), tickets (individual ticket list with subject, status, channel, assignee, messages count), by_channel (tickets/response time/CSAT per channel: email, chat, phone, etc.), satisfaction (CSAT score distribution — empty if surveys not enabled), top_tags (most common issue tags with count).
get_rechargeGet Recharge subscription analytics. Reports: summary (MRR as formatted money, activeSubscriptions, cancelledSubscriptions, churnRate as %, avgSubscriptionValue), metrics (current vs prior period comparison with % changes for MRR, active count, churn), cancellation_reasons (top reasons for cancellation with count and % share), upcoming_charges (daily charge forecast — default 30 days; use days=60 or 90 for bimonthly/quarterly subscriptions).
get_search_consoleGet Google Search Console SEO analytics. Reports: summary (clicks, impressions, CTR, position), top_queries (best keywords), top_pages (best landing pages), trends (daily performance), by_country, by_device, keyword_movers (improved/declined queries), new_keywords, page_ranking_changes, anomalies (cross-metric issues), zero_traffic (products invisible to search), branded_split (brand vs non-brand), cannibalization (competing pages).
get_clarityGet Microsoft Clarity UX/session analytics. Reports: summary (totalSessions, totalUsers, avgSessionDuration in seconds, pagesPerSession, scrollDepth %, deadClickRate %, rageClickRate %, excessiveScrollRate %), ux_issues (counts and rates for dead clicks, rage clicks, excessive scrolling, quick-backs — these indicate UX friction), by_dimension (session counts by browser/device/os/country/source — requires 'dimension' param), trends (daily breakdown of sessions, UX issue rates).
get_youtubeGet YouTube analytics. Reports: summary (channel stats, subscribers, views), videos (video list with metrics), top_videos (best performing by views gained), video_details (specific video info + transcript — requires 'videoId'), search_transcripts (search across transcripts — requires 'query').
get_reviewsGet product review analytics (Yotpo, Reviews.io, or Judge.me). Reports: summary (average rating, distribution), trends (daily volume/score), top_rated (best reviewed products), lowest_rated (worst reviewed), recent (latest reviews), search (keyword search in reviews), timing (days from purchase to review), sales_impact (reviewed vs unreviewed product sales).
get_loyaltyGet Smile.io loyalty program analytics. Reports: summary (members, points balances, VIP tiers), points_activity (earning/redemption over time), top_members (by points or spend), vip_tiers (tier distribution), redemption_patterns (popular rewards), engagement (active members, engagement rate).
get_wishlistGet Swish wishlist analytics. Reports: summary (total items, unique products, unique customers), top_products (most wishlisted), demand_trends (recently added products), metrics (complete wishlist dashboard).
get_meta_adsGet Meta (Facebook/Instagram) ad performance data. Reports: summary (total spend, ROAS, CPC, CPM, conversions for date range), campaigns (performance by campaign with spend, clicks, ROAS, purchases), daily (daily spend and conversion trends over time).
get_shipstationGet ShipStation shipping analytics. Reports: summary (total shipments, costs, avg cost, shipping margin, void rate), carrier_breakdown (shipments/cost by carrier and service level), fulfillment_speed (avg/median hours to ship, daily breakdown), daily (daily shipping volume and costs over time).
get_xeroGet Xero accounting data. Reports: financials (P&L: revenue, COGS, gross profit, operating expenses, net profit + Balance Sheet: assets, liabilities, equity), cash (bank balance, accounts receivable, accounts payable, net position), invoices (outstanding/paid/overdue counts and amounts with aging buckets: current, 1-30, 31-60, 61-90, 90+ days), bills (same aging breakdown for payables), expenses (top expense categories from P&L with amounts).
get_daily_statsGet pre-computed daily analytics from Shopify order data. Reports: daily (each day: revenue, orders, avgOrderValue, itemsSold, newCustomers, returningCustomers, discountUsageRate, fulfillmentRate, refunds), summary (period totals, daily averages, and rates). Defaults to 90 days. Use for operational dashboards and daily KPI tracking.
get_abandoned_checkoutsGet cart abandonment analytics. Reports: stats (totalCheckouts, abandonedCheckouts, recoveredCheckouts, recoveryRate %, abandonedValue as formatted money, lostRevenue as formatted money, recovery windows showing when recoveries happen, email recovery stats), top_products (most frequently abandoned products with count, quantity, and total value).
get_product_velocityGet product sales velocity data. Reports: summary (totalUnitsSold, revenue, productsTracked, inventoryHealth counts by risk level), by_product (per-product: velocity7Day and velocity30Day as units/day, stockOnHand, daysOfStock estimate, reorderUrgency high/medium/low, recentRevenue), trend (daily time series for a specific product — requires 'productId' — showing unitsSold, revenue, orders, stockOnHand per day).
get_analyticsGet Google Analytics (GA4) website traffic data. Reports: summary (sessions, activeUsers, newUsers, pageViews, engagedSessions, conversions — with % change vs prior period), trend (daily breakdown of sessions/users/pageViews), by_channel (sessions and conversions by channel group: Organic Search, Paid Search, Direct, Social, Email, etc.), by_device (desktop/mobile/tablet split), by_country (traffic by country).
get_reviewsioGet Reviews.io specific analytics. Reports: stats (aggregate product/merchant/third-party stats, NPS), nps_trend (daily NPS), stats_trend (daily review counts), surveys (survey list), survey_responses (recent responses), reply_stats (merchant reply rates), unanswered (reviews without replies).