Amazon Ads MCP

Name: Amazon Ads MCP
Author: KuudoAI

作者：KuudoAI版本 0.2.4i★ –i在你的电脑上运行

注册名称io.github.tspicer/amazon_ads_mcp

安装

概览

作者提供的说明（英文原文）

Amazon Ads API MCP server for Amazon Advertising API

PopNx MCP 的三大支柱

这三项永远不会合并成一个分数：意见、测量和人气是不同的东西。

用户评价i暂无评价评价功能将在后续阶段与账户功能一起开放
我们的基础检查i1 项中通过 0 项依据公开信息检查；尚未扫描代码
使用情况i尚未统计★ –

它能帮你做什么

我们还没有为它写通俗的介绍。下面是我们从注册中心读取到的事实。

连接方式: 在你的电脑上运行
传输方式: stdio
分类: 营销与社交媒体
你需要填写：AMAZON_AD_API_CLIENT_SECRET, AMAZON_AD_API_REFRESH_TOKEN, OPENBRIDGE_REFRESH_TOKEN, OPENBRIDGE_API_KEY, AMAZON_ADS_DOWNLOAD_AUTH_TOKEN

安装

选择你使用的 AI 应用，然后复制设置。

安装之前

基础检查：1 项中通过 0 项
在你的电脑上运行，拥有你的用户账户的权限（文件、网络、应用）。
需要你自己填写： AMAZON_ADS_AUTH_METHOD, AMAZON_AD_API_CLIENT_ID, AMAZON_AD_API_CLIENT_SECRET, AMAZON_AD_API_REFRESH_TOKEN, AMAZON_AD_API_PROFILE_ID, OPENBRIDGE_REFRESH_TOKEN, OPENBRIDGE_API_KEY, OPENBRIDGE_REMOTE_IDENTITY_ID, AMAZON_ADS_REGION, AMAZON_AD_API_PACKAGES, AMAZON_ADS_DOWNLOAD_AUTH_TOKEN

标为机密的值是你账户的钥匙。千万不要分享给别人，也不要粘贴到聊天里。

你需要

PyPI已安装 Python 的 uv（用于 uvx 命令）

你用的是哪个应用？

ClaudeClaude CodeCursorVS CodeChatGPT

在上方选择你的应用。我们会记住它，下次按钮会显示“安装到 …”。

打开 Claude Desktop → Settings → Developer → Edit Config，把下面的内容粘贴到 claude_desktop_config.json

{
  "mcpServers": {
    "amazon-ads": {
      "command": "uvx",
      "args": [
        "amazon-ads-mcp"
      ],
      "env": {
        "AMAZON_ADS_AUTH_METHOD": "your-value",
        "AMAZON_AD_API_CLIENT_ID": "your-value",
        "AMAZON_AD_API_CLIENT_SECRET": "your-value",
        "AMAZON_AD_API_REFRESH_TOKEN": "your-value",
        "AMAZON_AD_API_PROFILE_ID": "your-value",
        "OPENBRIDGE_REFRESH_TOKEN": "your-value",
        "OPENBRIDGE_API_KEY": "your-value",
        "OPENBRIDGE_REMOTE_IDENTITY_ID": "your-value",
        "AMAZON_ADS_REGION": "your-value",
        "AMAZON_AD_API_PACKAGES": "your-value",
        "AMAZON_ADS_DOWNLOAD_AUTH_TOKEN": "your-value"
      }
    }
  }
}

在终端中运行这条命令

claude mcp add amazon-ads --env AMAZON_ADS_AUTH_METHOD=your-value --env AMAZON_AD_API_CLIENT_ID=your-value --env AMAZON_AD_API_CLIENT_SECRET=your-value --env AMAZON_AD_API_REFRESH_TOKEN=your-value --env AMAZON_AD_API_PROFILE_ID=your-value --env OPENBRIDGE_REFRESH_TOKEN=your-value --env OPENBRIDGE_API_KEY=your-value --env OPENBRIDGE_REMOTE_IDENTITY_ID=your-value --env AMAZON_ADS_REGION=your-value --env AMAZON_AD_API_PACKAGES=your-value --env AMAZON_ADS_DOWNLOAD_AUTH_TOKEN=your-value -- uvx amazon-ads-mcp

运行前请先填写空着的值。

在 Cursor 中打开

或者自己复制设置

粘贴到项目中的 .cursor/mcp.json，或 ~/.cursor/mcp.json

{
  "mcpServers": {
    "amazon-ads": {
      "command": "uvx",
      "args": [
        "amazon-ads-mcp"
      ],
      "env": {
        "AMAZON_ADS_AUTH_METHOD": "your-value",
        "AMAZON_AD_API_CLIENT_ID": "your-value",
        "AMAZON_AD_API_CLIENT_SECRET": "your-value",
        "AMAZON_AD_API_REFRESH_TOKEN": "your-value",
        "AMAZON_AD_API_PROFILE_ID": "your-value",
        "OPENBRIDGE_REFRESH_TOKEN": "your-value",
        "OPENBRIDGE_API_KEY": "your-value",
        "OPENBRIDGE_REMOTE_IDENTITY_ID": "your-value",
        "AMAZON_ADS_REGION": "your-value",
        "AMAZON_AD_API_PACKAGES": "your-value",
        "AMAZON_ADS_DOWNLOAD_AUTH_TOKEN": "your-value"
      }
    }
  }
}

浏览器会先询问是否打开应用，然后应用会显示设置并请你确认。密钥的值会留空，由你自己填写。

在 VS Code 中打开

或者自己复制设置

粘贴到项目中的 .vscode/mcp.json

{
  "servers": {
    "amazon-ads": {
      "type": "stdio",
      "command": "uvx",
      "args": [
        "amazon-ads-mcp"
      ],
      "env": {
        "AMAZON_ADS_AUTH_METHOD": "your-value",
        "AMAZON_AD_API_CLIENT_ID": "your-value",
        "AMAZON_AD_API_CLIENT_SECRET": "your-value",
        "AMAZON_AD_API_REFRESH_TOKEN": "your-value",
        "AMAZON_AD_API_PROFILE_ID": "your-value",
        "OPENBRIDGE_REFRESH_TOKEN": "your-value",
        "OPENBRIDGE_API_KEY": "your-value",
        "OPENBRIDGE_REMOTE_IDENTITY_ID": "your-value",
        "AMAZON_ADS_REGION": "your-value",
        "AMAZON_AD_API_PACKAGES": "your-value",
        "AMAZON_ADS_DOWNLOAD_AUTH_TOKEN": "your-value"
      }
    }
  }
}

浏览器会先询问是否打开应用，然后应用会显示设置并请你确认。密钥的值会留空，由你自己填写。

这个服务器在你的电脑上运行，而 ChatGPT 只能连接互联网上的服务器。请选择其他应用。

你的选择通过 Cookie 保存在这台设备上，无需账户。

需要你填写的值

AMAZON_ADS_AUTH_METHOD env
Authentication method: direct or openbridge.
AMAZON_AD_API_CLIENT_ID env
Amazon Ads API client ID for direct auth.
AMAZON_AD_API_CLIENT_SECRET 机密 env
Amazon Ads API client secret for direct auth.
AMAZON_AD_API_REFRESH_TOKEN 机密 env
Amazon Ads API refresh token for direct auth.
AMAZON_AD_API_PROFILE_ID env
Amazon Ads profile ID for direct auth.
OPENBRIDGE_REFRESH_TOKEN 机密 env
Openbridge refresh token (API key).
OPENBRIDGE_API_KEY 机密 env
Openbridge API key (alias for OPENBRIDGE_REFRESH_TOKEN).
OPENBRIDGE_REMOTE_IDENTITY_ID env
Openbridge remote identity ID.
AMAZON_ADS_REGION env
Amazon Ads API region (na/eu/fe).
AMAZON_AD_API_PACKAGES env
Comma-separated API packages to load.
AMAZON_ADS_DOWNLOAD_AUTH_TOKEN 机密 env
Optional bearer token to protect download routes.

这些设置是根据作者在注册中心的条目生成的。如果 README 的写法不同，请以 README 为准。

它能做什么

它在你的电脑上运行；安装后，工具列表会显示在你的 AI 应用中。

基础检查i

我们检查的是任何人都能看到的信息；我们没有阅读代码。不适用的检查项不计入总数。 · 检查于 2026年11月7日

! 注意
作者与仓库一致
发布者（tspicer）不是仓库所有者（KuudoAI）；可能是其他人代为上架的
… 尚未检查
仍在维护
我们还没有从 GitHub 读取这个仓库
… 尚未检查
有许可证
我们还没有从 GitHub 读取这个仓库
– 不适用
端点有响应
它在你的电脑上运行，没有互联网端点
– 不适用
使用 OAuth 登录
在你的电脑上运行，改用本地设置
… 尚未检查
工具描述中没有隐藏指令
它在你的电脑上运行；我们只能读取互联网端点的工具列表

与“营销与社交媒体”中的其他服务器比较i

星标数多于此分类中其他 3559 个服务器的 0%
发布到注册中心的时间比此分类中其他 3559 个服务器的 1% 更新
基础检查结果等于或优于此分类中其他 3559 个服务器的 33%

与注册中心里这个分类中所有活跃的服务器比较。只有当发布者拥有该仓库时，星标数才计入。

常见问题

Amazon Ads MCP 安全吗？

它在 1 项适用的基础检查中通过了 0 项。我们没有阅读代码。在添加密钥或令牌之前，请先看看这个服务器要求哪些权限，并使用只具备所需权限的密钥。

它需要哪些密钥或代码？

你需要填写：AMAZON_AD_API_CLIENT_SECRET, AMAZON_AD_API_REFRESH_TOKEN, OPENBRIDGE_REFRESH_TOKEN, OPENBRIDGE_API_KEY, AMAZON_ADS_DOWNLOAD_AUTH_TOKEN

它在我的电脑上运行还是在云端？

它在你的电脑上运行。你的 AI 应用会在需要时启动它，数据不会经过作者的服务器（除非它自己调用在线服务）。

它还在维护吗？

GitHub 仓库最后更新于–，最新版本（0.2.4）于9个月前进入注册中心。

哪些应用可以使用它？

支持 MCP 的应用，例如 Claude Desktop、Claude Code、Cursor 和 VS Code。你的电脑上还需要有 Python (uv)。

有什么可以替代它？

同一分类中有：MCP YouTube Transcript, Google Analytics MCP, BibiGPT YouTube Video Summarizer

替代选择

同一分类中其他作者的服务器，按星标数排序。

如何看卡片：★ GitHub 星标i三大支柱：评价 · 检查 · 使用情况i更新 = 最新版本发布到注册中心的时间i

MCP YouTube Transcript

作者：jkawamoto

An MCP server retrieving transcripts of YouTube videos

在你的电脑上运行★ 495MIT10天前更新

安装

Google Analytics MCP

作者：surendranb

GA4 MCP server for AI agents: schema discovery, server-side aggregation, analysis-ready defaults.

在你的电脑上运行★ 244MIT10天前更新

安装

BibiGPT YouTube Video Summarizer

作者：JimmyLv

AI video summarizer: summarize and transcribe YouTube, Bilibili, TikTok and podcast videos.

在云端运行★ 137MIT10天前更新

安装

作者的 README

打开 README

按原文从作者的仓库复制。PopNx MCP 没有审查或背书其内容。HTML、图片和脚本已被移除。链接会离开本站。

Kuudo Amazon Ads MCP Server

The open-source Amazon Ads MCP server from [Kuudo](https://www.kuudo.com/), also published as the Amazon Ads API MCP SDK

*Made with ❤️ + ☕ by Kuudo, an Openbridge company*

MCP registry id (for clients and catalogs that display a stable package name): io.github.KuudoAI/amazon_ads_mcp

Kuudo's Amazon Ads MCP server gives Claude, ChatGPT, Cursor and any MCP client 711 Amazon Ads API operations across 53 services: Sponsored Products, Sponsored Brands, Sponsored Display, Sponsored TV, Amazon DSP and Amazon Marketing Cloud, with read and write tools. It is MIT-licensed. Run it yourself, or have Kuudo run it in your own AWS, Google Cloud, Azure or Cloudflare account.

Kuudo · Amazon Ads MCP · Tool reference · Compare Amazon Ads MCP servers

Questions this server answers
Where this fits in Kuudo
What are MCP tools?
What is Amazon Ads API MCP SDK?
Quick start
Installation
Configuration (auth, packages, profiles, regions)
Downloading reports and exports
Example MCP client (Claude Desktop)
Context limits
Code mode
Tool audit
Background tasks
Frequently asked
Troubleshooting
Documentation map

Questions this server answers

Which MCP server connects Claude or ChatGPT to Amazon Ads, including DSP and Amazon Marketing Cloud?

Kuudo's Amazon Ads MCP covers all three in one server: Sponsored Products, Brands, Display and TV, Amazon DSP, and Amazon Marketing Cloud, 711 Amazon Ads API operations across 53 services, with read and write tools. It works from Claude, ChatGPT, Cursor and any other MCP client. See how it compares with the other Amazon Ads MCP servers: kuudo.com/compare/amazon-ads-mcp-servers.

Can I self-host an Amazon Ads MCP server in my own AWS or GCP account?

Yes. This server is MIT-licensed and runs from Docker or Python on infrastructure you control. Kuudo also provisions it, with the Selling Partner and Vendor Central servers, into your own AWS, Google Cloud, Azure or Cloudflare account, where Amazon requests go from your cloud directly to Amazon: self-host Kuudo in your own cloud.

Does it cover Seller Central and Vendor Central too?

This repository is the Amazon Ads server. Kuudo runs companion MCP servers for Seller Central (listings, inventory, orders, pricing, fulfillment and reports) and Vendor Central (purchase orders, shipments, invoices and Retail Analytics), and one AI client can use all three at once.

Can an agency run it across many client accounts?

Yes, through Kuudo. Each client authorizes its Amazon Ads account once through a time-limited invitation, with no login shared, and one connection then reaches every account and advertising profile the agency is authorized for: how account authorization works.

How is it different from Amazon's own Ads MCP Server?

Amazon's Ads MCP Server is hosted by Amazon and in open beta for Amazon Ads partners with active API credentials. This server is open source, runs where you choose, and works with your own Amazon Ads app or a partner token. The side-by-side, with every source dated: Amazon Ads MCP Server vs Kuudo.

Where this fits in Kuudo

This repository is the tool layer of a broader Amazon agent platform. Kuudo gives Amazon agents tools, knowledge, workflows, and a place to work. This repository is the tools.

Layer	What it provides	Where
MCP servers	The tools an agent calls: Amazon Ads here, plus Selling Partner and Vendor Central	this repo, and the MCP tool reference
Skills	The higher-level workflows: reusable, versioned, multi-step Amazon procedures that compose these tools and wait for a human before anything goes live	Amazon Agent Skills
Agent Atlas	The knowledge: indexed Amazon operating knowledge across Ads, Seller Central, and Vendor Central, answered with citations	Amazon Agent Atlas
Agent Flow	The place to work: your Amazon data landed in your own cloud, so an agent answers with real figures instead of guessing	Amazon Agent Flow

Read this repository as one layer of that platform rather than as the whole of it. The operations below are what an agent can call; Skills are what it runs.

What Are MCP Tools?

Think of MCP (Model Context Protocol) as a translator between an AI model and outside systems (like Amazon Ads). Each MCP tool is like a remote control button that tells the AI how to interact with Amazon Ads. Without MCP tools, the AI would have no idea how to “talk” to Amazon Ads.

With MCP tools:

The AI knows the exact endpoints to call.
The AI can request campaign reports, budgets, or targeting data safely.
Everything is structured, so the AI doesn’t break things by making random guesses.

👉 In short: MCP tools = a safe, well-labeled toolkit that lets AI work with the Amazon Ads API.

🚀 What is Amazon Ads API MCP SDK?

The Amazon Ads API MCP SDK is an open-source implementation that provides a robust foundation for creating AI-powered advertising tools, chatbots, and automated services.

✨ Key Features

🔌 MCP Integration: Full Model Context Protocol compliance for AI application integration
🌍 Multi-Region Support: NA, EU, and FE region endpoints with automatic routing
📊 Comprehensive API Coverage: Campaigns, profiles, reporting, DSP, AMC workflows, and more
📝 Type Safety: Full Pydantic model support with comprehensive type hints
🧪 Production Ready: Includes testing, validation, and error handling

🎯 Use Cases

Claude Desktop Integration

Campaign Management: Ask Claude to create, update, or analyze campaigns
Performance Insights: Get AI-powered analysis of your advertising performance
Budget Optimization: Let Claude suggest budget adjustments based on performance
Creative Testing: Get recommendations for ad creative improvements
Reporting: Generate custom reports and insights on demand

AI Applications

Marketing Chatbots: Build conversational AI that can manage Amazon Ads campaigns
Automated Reporting: AI-powered insights and performance analysis
Smart Budget Management: Intelligent budget optimization using AI
Creative Optimization: AI-driven ad creative testing and optimization

Enterprise Services

Marketing Automation Platforms: Integrate Amazon Ads into existing marketing tools
Agency Management Systems: Multi-client, multi-account advertising management
E-commerce Integrations: Connect Amazon Ads with e-commerce platforms
Analytics Dashboards: Real-time advertising performance monitoring

Developer Tools

API Wrappers: Create custom SDKs for specific use cases
Testing Frameworks: Automated testing for Amazon Ads integrations
Development Tools: Local development and debugging utilities

Why this Ads MCP is different

Other Amazon Ads MCPs do happy path. They fall apart the moment an agent makes a reasonable mistake and Amazon's Ads API has more reasonable mistakes than almost any other large API surface. The v1 reporting catalog uses a different vocabulary than v3. The docs are scattered across migration generations. The same field can have three plausible names depending on which tutorial an agent or human was trained on.

You've felt this before

You know the symptoms even if you've never thought of them as a single problem:

"Compacting conversation…" right when you were getting somewhere
"Usage limit reached" mid-task, with nothing to show for the tokens
"Context window exceeded" start over, re-explain everything
The agent quietly forgetting the fix it figured out three turns ago
Five tool calls, four of them retries, none of them progress
Re-pasting the same error into the chat for the third time

That's not the model being dumb. That's the API surface burning context vague errors trigger thrashing, thrashing fills the window, the window fills and everything useful gets evicted. Anywhere from 4 to 12 round-trips for an agent: wrong field names, wrong body shape, wrong filter operator, wrong date placement, wrong advertiser-account format.

Here, the wrong moves return the right move

This server is built around a different premise: the error surface is the documentation surface. Every failure is a teaching opportunity, and the server is engineered to make the next attempt smarter than the last one, for the same agent or the next one, without retraining, prompt updates, or memory tricks.

The server tells you what went wrong, and *why* you got it wrong
Every failure converts to a corrective action — the model just reads the hint and moves on
A five-tool-call debugging arc collapses into a two-call corrected one
The same mistake a week later doesn't re-burn context, because the validator, alias table, and deprecated-shape table are still right there
No out-of-context tribal knowledge to forget

Every failure is cheaper than the last. Every agent learns from the same authoritative source. Every retry has direction. That compounding is what a smart agent solution looks like in practice.

Everything is an edge case, you can help

We won't catch every edge case. Amazon's API surface is enormous, the migration history is messy, and real-world failures get more creative than anything anyone can anticipate. What we're committing to is the strategy that errors should teach, that documentation should live in the surfaces agents actually touch, that every wrong move should make the next move easier.

If you hit a failure where the envelope didn't help; vague hint, wrong suggestion, no hint at all, that's exactly the feedback we want. Open an issue, paste the envelope, tell us what you expected. The strategy is only as good as the cases it covers.

Quick start

Prerequisites: Docker (recommended), Python 3.10+ if you run from source, and Amazon Ads API access (your own developer app or a partner such as Openbridge).

git clone https://github.com/KuudoAI/amazon-ads-mcp.git && cd amazon-ads-mcp
cp .env.example .env and add credentials (see Configuration).
`docker compos

只显示了开头部分；其余内容请在仓库中阅读