Amazon Ads MCP Server

What does “Amazon Ads” MCP Server do?

The Amazon Ads MCP Server is a Model Context Protocol (MCP) server designed to facilitate seamless integration between AI assistants and Amazon Advertising data. By connecting your Amazon Ads account via MarketplaceAdPros, this server empowers AI assistants to interact programmatically with advertising resources across Sponsored Products, Sponsored Brands, and Sponsored Display. It enables tasks such as querying campaign performance, managing ad groups, accessing keywords, generating reports (which can be queried in plain English), and leveraging Marketplace Ad Pros features like recommendations and experiments with a subscription. The Amazon Ads MCP Server streamlines ad data retrieval and management, enhancing development workflows for advertisers and agencies by offering a unified, AI-driven interface to Amazon Ads data and automation.

List of Prompts

No explicit prompt templates are mentioned in the repository or documentation.

List of Resources

• Advertising Resources: Access information on Sponsored Products, Sponsored Brands, and Sponsored Display, including Campaigns, Ad Groups, Keywords, Product Ads, and Targeting.
• Reports: Retrieve and query advertising reports using plain English.
• Recommendations: Access Marketplace Ad Pros Recommendations (with a subscription).
• Experiments: Run and manage experiments for ad optimization (with a subscription).

List of Tools

No explicit tool names or descriptions are listed in the repository or server.py code.

Use Cases of this MCP Server

• Campaign Management: Automate the retrieval and management of campaign, ad group, and keyword data for Sponsored Products, Brands, and Display.
• Data-Driven Reporting: Generate and query advertising performance reports in natural language, simplifying analytics for marketers and teams.
• Optimization Recommendations: Leverage Marketplace Ad Pros’ AI-driven recommendations to improve ad performance and campaign strategies (requires subscription).
• Experimentation: Manage and run ad experiments to test new strategies and creatives, enhancing A/B testing workflows (requires subscription).
• Integration with AI Assistants: Allow AI agents in Claude, Windsurf, Cursor, or Cline to interact directly with Amazon Ads data for streamlined automation and insights.

How to set it up

Windsurf

1. Ensure Node.js and npx are installed.
2. Obtain a BEARER_TOKEN from MarketplaceAdPros.com.
3. Locate the Windsurf MCP server configuration file.
4. Add the following JSON snippet to include the Amazon Ads MCP Server:

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

5. Save the configuration and restart Windsurf.

Claude

1. Ensure Node.js and npx are installed.
2. Obtain a BEARER_TOKEN from MarketplaceAdPros.com.
3. Edit the config file:
   • MacOS: ~/Library/Application Support/Claude/claude_desktop_config.json
   • Windows: %APPDATA%/Claude/claude_desktop_config.json
4. Insert:

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

5. Save and restart Claude.

Cursor

1. Ensure Node.js and npx are installed.
2. Obtain a BEARER_TOKEN from MarketplaceAdPros.com.
3. Locate the Cursor configuration file for MCP servers.
4. Add:

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

5. Save and restart Cursor.

Cline

1. Ensure Node.js and npx are installed.
2. Obtain a BEARER_TOKEN from MarketplaceAdPros.com.
3. Locate the Cline MCP server configuration.
4. Insert:

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

5. Save and restart Cline.

Streamable HTTP Setup (All Platforms)

Alternatively, if your client supports Streamable HTTP MCP servers, use:

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

Securing API Keys

Store your BEARER_TOKEN as an environment variable in the env section of your MCP server configuration:

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

How to use this MCP inside flows

Using MCP in FlowHunt

To integrate MCP servers into your FlowHunt workflow, start by adding the MCP component to your flow and connecting it to your AI agent:

Click on the MCP component to open the configuration panel. In the system MCP configuration section, insert your MCP server details using this JSON format:

{
  "amazon-ads": {
    "transport": "streamable_http",
    "url": "https://app.marketplaceadpros.com/mcp"
  }
}

Once configured, the AI agent is now able to use this MCP as a tool with access to all its functions and capabilities. Remember to change “amazon-ads” to whatever the actual name of your MCP server is and replace the URL with your own MCP server URL.

Overview

Based on the available information, the Amazon Ads MCP Server provides good documentation for setup and resource access, but lacks explicit prompt templates and tool descriptions in the public files. Roots and sampling support are not mentioned.

Our opinion

The Amazon Ads MCP Server is straightforward and well-documented for setup, making it accessible for developers who need to connect AI assistants to Amazon Ads data. However, it lacks visible details on prompt templates and tool interfaces, which are important for advanced LLM workflow integrations. Overall, it is functional for its main purpose, but could benefit from more transparency and detail on its programmatic capabilities.

MCP Score: 6/10

MCP Score