Amazon Ads

What is amazon-ads-mcp-server?

The amazon-ads-mcp-server is a server that facilitates interaction with Amazon Advertising data. It allows users to connect their Amazon Advertising accounts through MarketplaceAdPros to access various advertising resources and reports.

How to use amazon-ads-mcp-server?

To use amazon-ads-mcp-server, you can integrate it with your MCP client (e.g., Claude Desktop or LibreChat).

Installation:

1. Via npx (recommended for Claude Desktop): Configure your MCP client's server config (e.g., claude_desktop_config.json on MacOS/Windows) to use npx @marketplaceadpros/amazon-ads-mcp-server. You'll need to set the BEARER_TOKEN environment variable, which you obtain from MarketplaceAdPros.com.

2. Cloning the repository: If you prefer to build from source, clone the repository, install dependencies (npm install), and build the server (npm run build). Then, configure your MCP client to execute the built index.js file.

3. Streamable HTTP MCP Server: If your client supports streamable HTTP MCP servers, you can directly point to the MCP endpoint at https://app.marketplaceadpros.com/mcp. This method is also applicable for integration with LibreChat.

Development:

For development, you can install dependencies (npm install), build the server (npm run build), or use npm run watch for auto-rebuild. Debugging can be done using the MCP Inspector via npm run inspector.

Key Features of amazon-ads-mcp-server

• Access to Amazon Advertising Resources: Provides access to various advertising resources in Sponsored Products, Sponsored Brands, and Sponsored Display, including Campaigns, Ad Groups, Keywords, Product Ads, and Targeting.
• Reporting Capabilities: Allows users to query reports using plain English.
• Marketplace Ad Pros Integration: Offers Marketplace Ad Pros Recommendations, Experiments, and more with a purchased subscription plan.
• Multiple Integration Methods: Supports integration via npx, direct repository build, and as a Streamable HTTP MCP Server.
• Debugging Tools: Includes a built-in MCP Inspector for easier development and debugging.

Use Cases of amazon-ads-mcp-server

• Automated Ad Management: Developers and agencies can build tools to automate the management of Amazon Advertising campaigns.
• Custom Reporting and Analytics: Create custom reports and perform in-depth analysis of Amazon Advertising data beyond what's available in the standard Amazon interface.
• Integration with AI/ML Models: Leverage the plain English query capability to integrate with AI/ML models for advanced insights and campaign optimization.
• Building Custom Dashboards: Develop personalized dashboards to monitor Amazon Advertising performance.

FAQ about amazon-ads-mcp-server

• What is the BEARER_TOKEN? The BEARER_TOKEN is a unique token obtained from MarketplaceAdPros.com, required for authenticating your connection to the Amazon Ads data.
• Can I use this with any MCP client? While examples are provided for Claude Desktop and LibreChat, it should be compatible with any MCP client that supports the specified integration methods (npx, direct execution, or streamable HTTP).
• Do I need a MarketplaceAdPros subscription? While the server provides access to basic Amazon Advertising data, advanced features like Recommendations and Experiments require a purchased subscription plan from MarketplaceAdPros.
• How do I debug the server? You can use the npm run inspector command, which launches the MCP Inspector in your browser for debugging purposes.
• What is the Model Context Protocol (MCP)? The MCP is a specification that defines how models and tools can communicate and exchange context. This server is built to adhere to this protocol.

amazon-ads-mcp-server

Connect to your Amazon Advertising Data by integrating your account with MarketplaceAdPros.

Provides access to:

• Advertising Resources in Sponsored Products, Sponsored Brands and Sponsored Display, like Campaigns, Ad Groups, Keywords, Product Ads, Targeting
• Reports and ability to query them with plain english.
• Marketplace Ad Pros Recommendations, Experiments and more with purchased subscription plan

Also available as a Streamable HTTP MCP Server by connecting to https://app.marketplaceadpros.com/mcp

Installation

To add the amazon-ads-mcp-server to your MCP client of choice, add the following to the server config:

On MacOS: ~/Library/Application Support/Claude/claude_desktop_config.json

On Windows: %APPDATA%/Claude/claude_desktop_config.json

Env Vars

• BEARER_TOKEN: The Bearer token you got from MarketplaceAdPros.com

Configuration

You can use it via npx in your Claude Desktop configuration like this:

{
  "mcpServers": {
    "marketplaceadpros": {
      "command": "npx",
      "args": [
        "@marketplaceadpros/amazon-ads-mcp-server"
      ],
      "env": {
        "BEARER_TOKEN": "abcdefghijklmnop"
      }
    }
  }
}

Or, if you clone the repo, you can build and use in your Claude Desktop configuration like this:

{
  "mcpServers": {
    "marketplaceadpros": {
      "command": "node",
      "args": [
        "/path/to/amazon-ads-mcp-server/build/index.js"
      ],
      "env": {
        "BEARER_TOKEN": "abcdefghijklmnop"
      }
    }
  }
}

Or, if your client supports the Streamable HTTP MCP Servers, you can just point to the MCP endpoint at https://app.marketplaceadpros.com/mcp.

{
  "mcpServers": {
    "marketplaceadpros": {
      "type": "streamable-http",
      "url": "https://app.marketplaceadpros.com/mcp"
    }
  }
}

Or, configure in LibreChat like:

  MAP:
    type: streamable-http
    url: https://app.marketplaceadpros.com/mcp
    headers:
      Authorization: "Bearer abcdefghijklmnop"

Development

Install dependencies:

npm install

Build the server:

npm run build

For development with auto-rebuild:

npm run watch

Debugging

Since MCP servers communicate over stdio, debugging can be challenging. We recommend using the MCP Inspector, which is available as a package script:

npm run inspector

The Inspector will provide a URL to access debugging tools in your browser.

Acknowledgements

• Obviously the modelcontextprotocol and Anthropic teams for the MCP Specification. https://modelcontextprotocol.io/introduction
• MarketplaceAdPros for enabling and sponsoring this project.