Ask AI

Ask AI

Hosted MCP server connecting Shopify, Klaviyo, GA4, Meta Ads, Google Ads, Xero, Gorgias and 20+ e-commerce data sources so AI assistants can answer merchant questions that span every source at once.

Category
访问服务器

README

Ask AI MCP Server

Hosted Model Context Protocol server that connects 20+ e-commerce and business data sources to AI assistants like Claude, ChatGPT, Gemini and Perplexity, so merchants can ask questions in plain English and get answers that span every source at once.

Website: ask-ai-data-connector.com

What it does

Instead of checking Shopify, Klaviyo, GA4 and your ad platforms separately, you connect them all and ask questions that cross every source in a single conversation, for example:

  • "Which Klaviyo campaigns drove the most Shopify revenue last month?"
  • "Compare my Meta Ads ROAS to Google Ads and show which channel's customers have the highest lifetime value."
  • "What's driving the change in revenue this week?"

Connection

Endpoint https://ask-ai-data-connector.com/mcp
Transport Streamable HTTP
Authentication OAuth 2.0 with dynamic client registration
Registry com.ask-ai-data-connector/ask-ai on the official MCP Registry
Tools 80+ query tools covering revenue, marketing, support, accounting, shipping and reviews (full list: tools.json)

Supported data sources

  • Commerce: Shopify, WooCommerce, Recharge
  • Email & SMS: Klaviyo, Sendy
  • Advertising: Meta Ads, TikTok Ads, Google Ads, Triple Whale
  • Web analytics: Google Analytics (GA4), Microsoft Clarity
  • SEO: Google Search Console
  • Customer support: Gorgias, RingCentral
  • Accounting: Xero
  • Shipping: ShipStation
  • Reviews: Judge.me, Yotpo, Reviews.io
  • Video: YouTube
  • Loyalty & wishlists: Smile.io, Swish

Tools

The server exposes 80+ tools. The complete, machine-readable catalog (name + description for every tool) lives in tools.json. Highlights by area:

  • Overview and diagnostics: get_briefing, get_complete_dashboard, get_data_sources, get_revenue_drivers, get_anomalies, get_sync_health
  • Revenue and orders: get_store_summary, get_orders, query_orders, get_daily_revenue, get_metrics_comparison, get_yoy_monthly, get_forecast
  • Products and inventory: get_top_products, get_product_catalog, get_product_health, get_inventory, get_inventory_velocity, get_product_velocity
  • Customers: get_customers, get_customer_insights, get_abandoned_checkouts
  • Marketing and ads: get_marketing_performance, get_meta_ads, get_google_ads, get_tiktok_ads, get_triple_whale, get_klaviyo, get_campaign_impact
  • Web, SEO and UX analytics: get_analytics, get_search_console, get_clarity, get_ga4_funnel
  • Support: get_gorgias, get_ringcentral
  • Accounting and finance: get_xero, get_refunds, get_spend_reconciliation
  • Reviews and loyalty: get_reviews, get_reviewsio, get_loyalty, get_wishlist
  • Multi-store: get_stores, get_store_comparison, get_product_cross_store

Data access requires OAuth; connect your account at ask-ai-data-connector.com.

Add it to your AI client

Add the remote server URL https://ask-ai-data-connector.com/mcp to any MCP-capable client. The server advertises OAuth via standard .well-known discovery, so the client walks you through connecting your account on first use.

Claude Code

claude mcp add --transport http ask-ai https://ask-ai-data-connector.com/mcp

Other clients (Claude Desktop, ChatGPT, Cursor, and more): add a remote / streamable-HTTP MCP server pointing at the same URL.

Getting started

  1. Sign up at ask-ai-data-connector.com and connect your data sources.
  2. Add the MCP endpoint to your AI client (above).
  3. Authorize when prompted, then ask questions in plain English.

Links

  • Website: https://ask-ai-data-connector.com
  • Docs and example questions: https://ask-ai-data-connector.com/example-questions
  • Supported integrations: https://ask-ai-data-connector.com/integrations

推荐服务器

Baidu Map

Baidu Map

百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。

官方
精选
JavaScript
Playwright MCP Server

Playwright MCP Server

一个模型上下文协议服务器,它使大型语言模型能够通过结构化的可访问性快照与网页进行交互,而无需视觉模型或屏幕截图。

官方
精选
TypeScript
Magic Component Platform (MCP)

Magic Component Platform (MCP)

一个由人工智能驱动的工具,可以从自然语言描述生成现代化的用户界面组件,并与流行的集成开发环境(IDE)集成,从而简化用户界面开发流程。

官方
精选
本地
TypeScript
Audiense Insights MCP Server

Audiense Insights MCP Server

通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。

官方
精选
本地
TypeScript
VeyraX

VeyraX

一个单一的 MCP 工具,连接你所有喜爱的工具:Gmail、日历以及其他 40 多个工具。

官方
精选
本地
graphlit-mcp-server

graphlit-mcp-server

模型上下文协议 (MCP) 服务器实现了 MCP 客户端与 Graphlit 服务之间的集成。 除了网络爬取之外,还可以将任何内容(从 Slack 到 Gmail 再到播客订阅源)导入到 Graphlit 项目中,然后从 MCP 客户端检索相关内容。

官方
精选
TypeScript
Kagi MCP Server

Kagi MCP Server

一个 MCP 服务器,集成了 Kagi 搜索功能和 Claude AI,使 Claude 能够在回答需要最新信息的问题时执行实时网络搜索。

官方
精选
Python
e2b-mcp-server

e2b-mcp-server

使用 MCP 通过 e2b 运行代码。

官方
精选
Neon MCP Server

Neon MCP Server

用于与 Neon 管理 API 和数据库交互的 MCP 服务器

官方
精选
Exa MCP Server

Exa MCP Server

模型上下文协议(MCP)服务器允许像 Claude 这样的 AI 助手使用 Exa AI 搜索 API 进行网络搜索。这种设置允许 AI 模型以安全和受控的方式获取实时的网络信息。

官方
精选