amazonads-mcp

amazonads-mcp

Enables AI assistants to interact with the Amazon Advertising API to manage campaigns, keywords, product ads, and retrieve performance metrics.

Category
访问服务器

README

Amazon Ads MCP Server

A Model Context Protocol (MCP) server that provides tools for interacting with the Amazon Advertising API. This server enables AI assistants to access and manage Amazon Ads campaigns, keywords, performance data, and more.

Features

This MCP server provides the following tools:

  • get_profiles: List all available Amazon Ads profiles/accounts
  • get_campaigns: Retrieve advertising campaigns with optional filtering by state and type
  • get_campaign_performance: Get performance metrics for campaigns (impressions, clicks, cost, sales)
  • get_keywords: Retrieve keywords for campaigns or ad groups
  • update_keyword_bid: Update bid amounts for specific keywords
  • create_campaign: Create new advertising campaigns
  • get_product_ads: Retrieve product ads for campaigns or ad groups

Prerequisites

  1. Amazon Ads Account: You need an active Amazon Ads account
  2. API Credentials: Register for Amazon Ads API access and obtain:
    • Client ID
    • Client Secret
    • Refresh Token

Getting Amazon Ads API Credentials

Step 1: Register Your Application

  1. Go to Amazon Advertising API
  2. Sign in with your Amazon Ads account
  3. Navigate to the Developer Center and create a new application
  4. You'll receive a Client ID and Client Secret - save these!

Step 2: Get Your Refresh Token

We provide a helper script to obtain your refresh token through the OAuth flow:

  1. Create a .env file in the project root:

    AMAZON_ADS_CLIENT_ID=your_client_id_here
    AMAZON_ADS_CLIENT_SECRET=your_client_secret_here
    
  2. Run the OAuth helper script:

    npm run get-token
    
  3. Your browser will open to Amazon's authorization page

  4. Sign in and authorize the application

  5. The script will display your refresh token - copy it to your .env file

Step 3: Note Your Region

Determine your advertising region:

  • NA: North America (amazon.com)
  • EU: Europe (amazon.co.uk, amazon.de, etc.)
  • FE: Far East (amazon.co.jp, etc.)

Installation

  1. Clone this repository:
git clone <your-repo-url>
cd amazonads-mcp
  1. Install dependencies:
npm install
  1. Build the project:
npm run build

Configuration

Environment Variables

Create a .env file or set the following environment variables:

AMAZON_ADS_CLIENT_ID=your_client_id
AMAZON_ADS_CLIENT_SECRET=your_client_secret
AMAZON_ADS_REFRESH_TOKEN=your_refresh_token
AMAZON_ADS_REGION=NA  # Options: NA, EU, FE
AMAZON_ADS_SANDBOX=false  # Set to true for testing with sandbox API

Claude Desktop Configuration

Add this server to your Claude Desktop configuration file:

macOS: ~/Library/Application Support/Claude/claude_desktop_config.json Windows: %APPDATA%/Claude/claude_desktop_config.json

{
  "mcpServers": {
    "amazonads": {
      "command": "node",
      "args": ["/absolute/path/to/amazonads-mcp/build/index.js"],
      "env": {
        "AMAZON_ADS_CLIENT_ID": "your_client_id",
        "AMAZON_ADS_CLIENT_SECRET": "your_client_secret",
        "AMAZON_ADS_REFRESH_TOKEN": "your_refresh_token",
        "AMAZON_ADS_REGION": "NA"
      }
    }
  }
}

Usage Examples

Once configured in Claude Desktop, you can ask Claude to:

  • "Show me all my Amazon Ads campaigns"
  • "What are the performance metrics for campaign ID 12345 from Jan 1 to Jan 31?"
  • "List all keywords for campaign 12345"
  • "Update the bid for keyword 67890 to $1.50"
  • "Create a new Sponsored Products campaign with a $50 daily budget"
  • "Show me all product ads in campaign 12345"

Development

Project Structure

amazonads-mcp/
├── src/
│   ├── index.ts              # Main MCP server implementation
│   └── amazon-ads-client.ts  # Amazon Ads API client
├── build/                     # Compiled JavaScript output
├── package.json
├── tsconfig.json
└── README.md

Building

npm run build

Development Mode

Watch for changes and rebuild automatically:

npm run watch

Testing the Server

Run the server directly:

npm start

The server communicates over stdio and expects MCP protocol messages.

API Coverage

This server currently supports:

  • Sponsored Products: Full support for campaigns, keywords, and product ads
  • Sponsored Brands: Campaign management (partial support)
  • Sponsored Display: Campaign management (partial support)
  • Reporting: Basic performance metrics (simplified implementation)

Important Notes

  1. Rate Limiting: The Amazon Ads API has rate limits. The client does not currently implement rate limiting logic.

  2. Reporting API: The get_campaign_performance tool uses a simplified implementation. For production use, you should implement the full async reporting flow:

    • Create report request
    • Poll for report completion
    • Download and parse report
  3. Error Handling: API errors are returned to the caller. Ensure proper credential configuration to avoid authentication errors.

  4. Regions: Make sure to set the correct region (NA, EU, FE) based on your Amazon Ads account.

Security

  • Never commit your .env file or expose API credentials
  • Refresh tokens should be stored securely
  • Consider implementing credential rotation for production use

Resources

License

MIT

Contributing

Contributions are welcome! Please feel free to submit a Pull Request.

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