MCP.so
登录

Nova Data Analytics MCP Server已验证已精选

@nova-data-analytics

基本信息

分类

AI 与智能体

许可证

MIT

作者

nova-data-analytics

提交者

Maxime Huet

关于 Nova Data Analytics MCP Server

Amazon Seller Central MCP server. Connect Seller Central, Vendor Central and Amazon Ads to Claude, ChatGPT, Gemini or Cursor, and ask for net profit per SKU with your own COGS, VAT and FBM shipping costs, PPC down to the

Nova Data Analytics MCP Server 配置

使用下面的配置,将此服务器添加到你的 MCP 客户端。

{
  "mcpServers": {
    "nova": {
      "url": "https://mcp.novadata.io/api/mcp"
    }
  }
}

Nova Data Analytics MCP Server 工具

工具列表暂未提供

当前收录暂时没有可展示的工具列表,不代表服务没有工具。请查阅项目文档了解支持的能力。

点击上方按钮,直接连接服务器端点实时获取工具列表。

概览

What is Nova Amazon MCP?

Nova Amazon MCP is a remote MCP server that connects your Amazon Seller Central, Vendor Central and Amazon Ads data to Claude, ChatGPT, Gemini or Cursor, so you can ask questions about your business in plain language and get answers from your own live data.

It is a hosted service. There is nothing to install and no local process: you add one URL to your assistant and sign in with OAuth.

Endpointhttps://mcp.novadata.io/api/mcp
TransportRemote, Streamable HTTP
AuthOAuth, per seller account, revocable at any time
Coverage477 documented data points, 21 Amazon marketplaces, 24 months of history
FreshnessHourly sync
Works withClaude Desktop, Claude web, Claude Code, ChatGPT, Gemini, Cursor

What makes it different from other Amazon MCP servers

Most Amazon MCP servers read what Amazon returns. Nova also holds your own cost data, and that changes what the assistant can answer.

Amazon knows your fees. It does not know what your product cost to buy, how VAT is treated in each country you sell in, or what it costs you to ship an FBM order. Without those, an assistant can tell you your revenue and your ad spend, but it cannot tell you whether a given ACoS is actually profitable.

Nova keeps COGS, VAT treatment and FBM shipping costs alongside the Amazon data, reconciled to SKU level across 40+ Amazon fee types. That is why it can answer "which keywords have a good ACoS but a negative contribution margin", which is the question that actually matters.

Those cost inputs are also readable and writable through the MCP itself, so you can audit and fix your own cost setup inside the conversation instead of leaving for a spreadsheet.

Example questions it can answer

Profit

  • Show me profit by SKU for the last 30 days after PPC.
  • Which SKUs lost the most net profit versus last month, and why?
  • What is my true TACoS by ASIN this quarter?

Advertising

  • Which campaigns spent over $100 last week with zero orders?
  • Find search terms with ACoS under 25% and at least 3 orders.
  • Which keywords have a good ACoS but a negative contribution margin?

Inventory

  • What runs out of stock in the next three weeks across all marketplaces?
  • Which SKUs are sitting on more than 120 days of cover?

Listings

  • Which listings are suppressed or losing the buy box right now?

Tools

ToolWhat it returns
query_metricsAny metric over any period, grouped by SKU, ASIN, marketplace, account or time grain
find_moversBiggest gainers and losers for a metric against a baseline period
explain_movementCausal signals behind one SKU's move: traffic, conversion, price, buy box, ads, rank
query_advertisingSponsored Products at campaign, ad group, targeting, keyword, ASIN or SKU grain
query_search_termsCustomer search queries behind ad spend, for negatives and discovery
query_sqpSearch Query Performance: impression, click and purchase share by query
query_inventoryFBA and AWD stock health, velocity, days of cover, out of stock risk
query_listing_healthSuppressed, not buyable, buy box lost, hijackers, catalog content
query_bsrBest Seller Rank for your own ASINs, latest or as a time series
list_cost_inputsConfigured per SKU COGS, FBM cost and VAT category, for setup audits
import_cogs, import_fbm_costs, import_vat_categoriesMaintain cost inputs conversationally, with a diff shown before commit
list_metrics, describe_metricMetric catalogue and definitions
list_accounts, list_tagsSeller accounts and custom product filters

Setup

You need a Nova account with Seller Central connected and at least one completed sync. The server URL is identical in every client, only the settings panel changes.

Claude Desktop or Claude web: Settings, then Connectors, then Add custom connector. Name it Nova, paste https://mcp.novadata.io/api/mcp, then complete the OAuth sign in. Requires a paid Claude plan.

Claude Code:

claude mcp add --transport http nova https://mcp.novadata.io/api/mcp

Cursor: add to ~/.cursor/mcp.json:

{
  "mcpServers": {
    "nova": {
      "url": "https://mcp.novadata.io/api/mcp"
    }
  }
}

ChatGPT and Gemini: add the same URL as a custom or remote MCP connector in Settings, then Connectors.

Full setup notes and a prompt library are in the repository.

Security

  • OAuth against Nova. No Amazon password is ever shared with the MCP server.
  • Credentials are per seller account and revocable at any time from Nova.
  • The endpoint answers unauthenticated requests with a standard OAuth challenge and a protected resource metadata document, so clients discover the sign in flow the way the spec intends.

If you are evaluating any Amazon MCP server, including this one, the questions are the same: does it use OAuth rather than credential sharing, are read and write scoped separately, can a human approve a change before it applies, and is there an audit trail.

Pricing

Commercial. Nova plans start at $29 per month with a 14 day free trial and no card required. The MCP server is included.

Links

评论

AI 与智能体 分类下的更多 MCP 服务器