Nova Data Analytics

MCPAI代理

提供方 nova-data-analytics

AI代理 HTTP · 远程 OAuth 授权 社区 / 第三方 Claude DesktopClaudeCursorGemini CLI
查看接入方式

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

一句话选型结论

按资料字段整理

Nova Data Analytics 属于AI代理类 MCP 服务器,HTTP · 远程,OAuth 授权,可直接接入 Claude Desktop、Claude、Cursor 等,有可直接复制的远程端点配置。接入前先确认权限范围;涉及写入、删除或付款的操作,建议先在测试环境验证。

分类AI代理 传输方式HTTP · 远程 鉴权OAuth 授权 部署方式远程部署
GitHub 星标 未标注 仓库热度,无公开仓库时显示未标注
工具数 未标注 暴露给模型的工具数量
资源 / 提示词 0 / 0 资源与提示词模板数量
维护方 社区 / 第三方 核验等级 仅资料核对

工具与能力

AI代理
数量来自来源目录的标注,具体工具清单以官方文档为准
工具数量未标注暴露给模型可调用的工具个数
资源数量0可读取的资源条目
提示词数量0内置提示词模板数量

能力标签

支持客户端

适用场景

e commerceAI

安装与配置

HTTP · 远程 OAuth 授权
连远程 HTTPS 端点,通常为 Streamable HTTP
https://mcp.novadata.io/api/mcp

把它填进客户端的 MCP 配置即可,不需要在本地安装运行时。

  1. 1
    准备运行环境

    确认你的客户端支持远程端点,并拿到服务地址。

  2. 2
    安装服务

    复制上面的安装命令执行;命令里带占位符的位置,换成自己的密钥或路径。

  3. 3
    写入客户端配置

    在客户端的 MCP 配置里填好启动命令和参数,保存后完全退出客户端再打开,让新配置生效。

  4. 4
    验证是否可用

    连接成功后随便调一个只读工具,确认能返回结果,再接入正式流程。

典型使用场景

3 类
按分类与标签整理的常见用法,具体以官方文档为准
给代理接外部能力

让代理在任务中途调用搜索、数据库等真实工具。

多步任务编排

把一串操作拆成步骤,由代理按顺序执行。

自动化重复流程

把固定流程交给代理跑,减少手工操作。

选择建议

选之前先看这几条
按条目字段给出的判断,不替你决定用不用

值得选的地方

  • 有现成的安装命令,不用自己找入口,照着跑就能起服务。
  • 已适配 Claude Desktop、Claude、Cursor,换客户端不用重新研究配置。

先想清楚的地方

  • 远程端点依赖网络与服务方可用性,注意密钥与调用额度。
  • 使用前要准备好OAuth 授权对应的凭据,并按最小权限配置。
  • 资料没标注工具数量,实际能力要装好后确认。
  • 版本更新与行为细节以官方仓库为准。

更适合

  • 需要在AI代理场景里让模型直接调用外部能力的人。
  • 已经在用 Claude Desktop、Claude 的用户,接入路径最短。
  • 想先快速试一下、能接受在本地或自有环境跑服务的人。

不太适合

  • 不方便管理密钥或第三方授权的人。
  • 需要厂商级 SLA 和技术支持的生产环境。

同类对比

6 个同类
同分类里挑最接近的几条,字段以各自详情页为准
MCP 服务器工具数传输方式部署方式安装命令最后核验
Nova Data Analytics当前 未标注 HTTP · 远程 远程部署 有 未标注
Filesystem 560c4363 13 未标注 本地部署 无 2026-05-17
Server Everything (everything) 11 stdio · 本地进程 本地部署 有 2026-05-17
Time 7365cb6d 2 SSE · 服务端推送 远程部署 有 2026-05-18
Everything Claude Code 未标注 stdio · 本地进程 本地部署 有 2026-05-17
Openmemory 557e1585 未标注 stdio · 本地进程 本地部署 有 2026-05-17

服务器档案

AI代理
字段来自项目仓库与公开索引,中文说明由本站标注
提供方nova-data-analytics上游标注的维护方 nova-data-analytics
分类AI代理本站按上游分类展示
连接方式HTTP · 远程连远程 HTTPS 端点,通常为 Streamable HTTP
鉴权方式OAuth 授权远程服务建议用最小权限凭据
维护方社区 / 第三方核验等级 仅资料核对
包名 / 运行时未标注 · Cross-platform本地安装时用到的包标识与运行时
部署类型远程部署上游给出的部署形态
最近核验未标注上游最后核验时间

详细介绍

7.4 KB
来自项目仓库与上游目录的原文,未做删改

Nova Amazon MCP Server

Connect Amazon Seller Central, Vendor Central, Amazon Ads and DSP data to Claude, ChatGPT, Microsoft Copilot, Grok, Gemini or Cursor through the Model Context Protocol, and ask questions in plain language.Which SKUs lost the most net profit versus last month, and why? Which search terms spent more than $100 last week with zero sales? What runs out of stock in the next three weeks across all marketplaces?

This repository is the setup kit and reference for Nova MCP, a hosted MCP server. It contains ready to paste client configurations, the tool reference and an example prompt library. The server itself is a commercial service operated by Nova; this repo does not contain server code.


What it is

Endpoint · https://mcp.novadata.io/api/mcp
Transport · Remote, Streamable HTTP
Auth · OAuth 2.0 with dynamic client registration, per Amazon account, revocable in Nova
Amazon data · Seller Central (3P), Vendor Central (1P), Amazon Ads, Amazon DSP, Search Query Performance, reviews, Subscribe & Save
Marketplaces · 23 Amazon marketplaces
Freshness · Orders and units within seconds of the sale. Finance transactions hourly, ad spend every two hours, search terms three times a day, other reports daily
Assistants · Claude, ChatGPT, Microsoft Copilot, Grok, Gemini, Cursor, and any MCP client
Pricing · Commercial. From $49/month per Amazon account, 14 day free trial, no card

Why a data layer rather than raw Amazon APIs

Amazon's Selling Partner, Vendor and Advertising APIs return raw reports split across many endpoints, with no reconciliation between them. An assistant pointed at them spends its context paginating and joining, and two questions can get two different numbers.

Nova MCP exposes a pre-modelled layer instead: orders, settlements and every Amazon fee reconciled at SKU level, your own costs applied (COGS, FBM shipping, VAT), Sponsored ads down to the customer search term, DSP by order and line item, FBA and AWD inventory with days of cover, listing health and Buy Box, Best Seller Rank. Filtering and ranking run server side, so one seller question is usually one tool call, and the answer matches the Nova dashboard.

Setup

You need a Nova account with at least one Amazon account connected. Start a trial at novadata.io if you do not have one.

  • Claude (web and desktop)
  • Claude Code
  • ChatGPT
  • Microsoft Copilot
  • Grok
  • Gemini
  • Cursor
  • Custom enterprise AI: any MCP client that supports remote servers and OAuth. See novadata.io/amazon-ai-agents/connect-enterprise-ai

The server URL is identical everywhere. Each client adds it in its own connector settings.

Tools

52 tools. Full reference in docs/tools.md.

Tool What it returns
query_metrics Any metric over any period (sales, fees, profit, ads, sessions...), by SKU, ASIN, marketplace, account or time grain
find_movers Biggest gainers and losers for a metric versus a baseline period
query_pnl_bridge Order-based and cash-based P&L of the same months side by side, and what separates them
explain_movement Causal signals behind one product's movement: traffic, conversion, price, Buy Box, ads, rank
query_advertising Sponsored Products, Brands and Display, from campaign down to keyword and ASIN
query_search_terms Customer search queries behind ad spend, for negatives and discovery
query_dsp Amazon DSP spend and results by advertiser, order, line item, product, device, creative or audience
query_sqp Search Query Performance: search volume, impression and purchase share by query, you versus the whole market
query_inventory FBA and AWD stock, velocity, days of cover, stockout risk, reorder quantities
query_listing_health Suppressed, not buyable, Buy Box lost, catalog issues
query_reviews Reviews, critical reviews and star rating per ASIN
query_subscribe_and_save Subscribe & Save health, offers and eligibility
query_vendor_purchase_orders / query_vendor_inventory / query_vendor_invoices / query_vendor_remittances Vendor Central: Amazon's purchase orders, the stock Amazon holds, your invoices, Amazon's payments and deductions
get_listing_content / update_listing_content Read and edit listing content on Amazon (title, bullets, backend keywords, attributes), previewed before it is confirmed
import_cogs / import_fbm_costs / import_vat_categories Maintain your cost inputs from the conversation, previewed before anything is saved

Example prompts

A longer library organised by job lives in prompts/ and at novadata.io/amazon-mcp-prompts.

Profit
- Give me last week's P&L by marketplace and name the three biggest swings.
- Which SKUs lost the most net profit versus last month, and why?
- What is my true TACoS by ASIN this quarter?

Advertising
- Which search terms spent the most last week without a sale?
- Find SKUs where ad spend is up 30% but units are flat or down.
- What did Amazon DSP cost us last month, and what did it drive?

Vendor Central
- What did Amazon order from us this week versus last week?
- Compare Vendor Central shipped revenue with Seller Central sales for the same products this month.

Inventory
- Which SKUs will run out of stock in the next 30 days at current sales speed?
- Which products should I reorder this week, given my lead times?

How it differs from Amazon's own MCP servers

Amazon is the source of truth for the data it serves, and its MCP servers are a good fit for what they cover: the Amazon Ads MCP server for campaign management, and Amazon's Selling Partner plugin for Seller Central (US stores at launch).

Nova adds the processing on top: reports pre-joined so one call returns a consistent answer, your own costs applied so the answer is profit rather than sales, ad and DSP spend inside the P&L, Vendor Central alongside Seller Central, and every account and marketplace in one question. Agencies and multi-brand teams query all their accounts at once.

More detail: novadata.io/amazon-seller-central-mcp-server

Security and permissions

  • OAuth against Nova. No Amazon password is ever shared with the MCP
  • Access is per Amazon account and revocable at any time from Nova
  • Workspace members only see the accounts they are assigned to
  • Cost tools write only to your own Nova configuration (COGS, FBM, VAT, tags, stock settings), never to Amazon, and always preview the change before saving it
  • Listing content edits (title, bullets, description, backend keywords, product attributes, never price or quantity) are available on Seller Central when enabled for your workspace, for the account owner only, previewed with Amazon's validation before they are confirmed
  • Campaign actions are in development and will follow the same preview and confirm pattern

Links

  • Amazon MCP server: novadata.io/amazon-mcp-server
  • Seller Central MCP: novadata.io/amazon-seller-central-mcp-server
  • Connection guides: novadata.io/amazon-ai-agents/connect
  • Tool list: novadata.io/amazon-mcp-tools
  • Prompt library: novadata.io/amazon-mcp-prompts
  • For agencies: novadata.io/amazon-mcp-for-agencies

Contributing

Issues and pull requests are welcome for the configs, docs and prompt library. For questions about the hosted service, contact Nova through the site.

License

MIT for the contents of this repository. See LICENSE. The Nova MCP service itself is commercial.

常见问题

8 问
答案由本站依据条目字段整理,不引用上游原文
Nova Data Analytics 怎么安装?

在客户端按下面的安装命令接入:https://mcp.novadata.io/api/mcp。装完在客户端配置里引用同一个包或端点。

Nova Data Analytics 怎么在 Claude Desktop、Claude、Cursor 里配置?

它的传输方式是HTTP · 远程,在客户端的 MCP 配置里填好启动命令和参数,保存后完全退出客户端再打开,配置才会生效。

Nova Data Analytics 收费吗?

本站不代收费用,也没有标注具体价格。是否收费取决于服务本身和背后的接口额度,正式使用前按官方说明确认。

Nova Data Analytics 需要 API Key 吗?

资料标注需要OAuth 授权认证,使用前准备好对应凭据,并按最小权限配置。

Nova Data Analytics 支持哪些客户端?

资料标注支持 Claude Desktop、Claude、Cursor、Gemini CLI、Codex、Zed;其他客户端只要能配置 MCP Server,也能用同样的命令或地址接入。

Nova Data Analytics 能提供哪些能力?

资料显示能力标签包括 e commerce、AI。具体工具清单以官方文档为准。

Nova Data Analytics 需要什么运行环境?

运行时为 Cross-platform;属于远程端点,不需要在本地装运行时。

Nova Data Analytics 是本地还是远程?

它是远程端点,连服务地址即可。传输方式为HTTP · 远程。

热门专题

按标签挑服务器
全部专题 →

服务器信息以作者仓库与官方文档为准;分类、传输方式与鉴权方式的中文说明为中文整理,最近核验 未标注。