The Amazon Ads API MCP SDK provides a framework for building AI-powered advertising applications that interact with the Amazon Advertising API using the Model Context Protocol (MCP).
From the registry: Amazon Ads API MCP server for Amazon Advertising API

$ git clone https://github.com/KuudoAI/amazon-ads-mcp.git$ cp .env.example .env$ docker compose up -dPlease install the `amazon-ads-mcp-kuudoai` MCP server into my current AI client (that's you).
Required prerequisites (do these first if not already done):
- **Clone repository** — Clone the amazon-ads-mcp repo Run: `git clone https://github.com/KuudoAI/amazon-ads-mcp.git`
- **Configure .env** — Copy .env.example to .env and configure credentials Run: `cp .env.example .env`
- **Start via Docker Compose** — Build and launch the server locally Run: `docker compose up -d`
- **Amazon Ads API access** — Either BYOA (client ID/secret) or Openbridge partner token (https://developer.amazon.com/)
Canonical MCP server config (HTTP transport):
- url: `http://localhost:9080/mcp/`
Note: Duplicate of amazon-ads-mcp — same repo. Self-hosted via Docker Compose.
Add this MCP server to my current client's config in the correct format for you. If you need secrets or credentials I haven't provided, ASK me — do not invent values or leave raw placeholders. After adding it, tell me how to verify the server is connected.AMAZON_AD_API_CLIENT_IDrequiredClient ID for your Amazon Ads API application.AMAZON_AD_API_CLIENT_SECRETrequiredClient Secret for your Amazon Ads API application.AUTH_METHODrequiredMethod of authentication for connecting to the Amazon Ads API.AMAZON_AD_API_PACKAGESrequiredComma-separated list of packages to activate for the Amazon Ads API.MCP server that exposes GraphQL operations as tools for AI models.