# amazon_ads_mcp

Connect an AI agent to the Amazon Ads API to inspect campaigns and reports. Useful for campaign analysis and budget management.

- MCP server · `type=mcp` · Claude Code, Codex, Cursor, GitHub Copilot, Windsurf (Devin Desktop), Cline, Zed, Gemini CLI · ★ 74
- Author: KuudoAI
- License: MIT · policy=link-only · description only; the file stays with the author
- Source: https://github.com/KuudoAI/amazon_ads_mcp
- Updated: 2026-10-14
- HTML: https://affpapa.org/en/nevibecode/mcp/amazon-ads-mcp

## What it does

The server gives an agent tools for working with Amazon Ads API data, including campaigns, profiles and reports. It also covers DSP and AMC workflows. Requests can be routed across the NA, EU and FE regions automatically.

Pydantic models describe the data structures used by the API. That gives the agent defined schemas when building requests. Reporting spans API generations, so v1 and v3 use different terminology that can affect which fields a request needs.

To connect it in Claude Code, provide an HTTPS endpoint for the server. The command uses `https://{HOSTNAME}/mcp`; replace `{HOSTNAME}` with the hostname where your server is available.

## Requirements
- Remote server: `https://{HOSTNAME}/mcp`

## Install

### Claude Code (native platform)

1. **Template address**
- The server address is a template: replace {…} or […] with your own values

2. **Platform CLI: remote server**
```bash
claude mcp add --transport http amazon-ads-mcp https://{HOSTNAME}/mcp
```

### Codex

1. **Template address**
- The server address is a template: replace {…} or […] with your own values

2. **Platform CLI: remote server**
```bash
codex mcp add amazon-ads-mcp --url https://{HOSTNAME}/mcp
```

### Cursor

1. **Template address**
- The server address is a template: replace {…} or […] with your own values

2. **Config file**
File `.cursor/mcp.json`:
```json
{
    "mcpServers": {
        "amazon-ads-mcp": {
            "url": "https://{HOSTNAME}/mcp"
        }
    }
}
```

### GitHub Copilot

1. **Template address**
- The server address is a template: replace {…} or […] with your own values

2. **Config file**
File `.vscode/mcp.json`:
```json
{
    "servers": {
        "amazon-ads-mcp": {
            "type": "http",
            "url": "https://{HOSTNAME}/mcp"
        }
    }
}
```

### Gemini CLI

1. **Template address**
- The server address is a template: replace {…} or […] with your own values

2. **Platform CLI: remote server**
```bash
gemini mcp add -t http amazon-ads-mcp https://{HOSTNAME}/mcp
```

## When to use it
- retrieve reports for advertising campaigns
- review advertising performance
- inspect campaign budgets and targeting
- create or update an ad campaign

## Example prompts
- Analyze the performance of my Amazon Ads campaigns.
- Retrieve a campaign report and explain the changes in its metrics.
- Review campaign budgets and suggest an adjustment.

## Similar
- [amazon-ads](https://affpapa.org/en/nevibecode/mcp/amazon-ads.md) — MCP server
- [ads-amazon](https://affpapa.org/en/nevibecode/skills/ads-amazon.md) — skill · 3300 installs
- [LinkedIn Ads](https://affpapa.org/en/nevibecode/mcp/linkedin-ads.md) — MCP server
- [amazon-display-ads](https://affpapa.org/en/nevibecode/skills/amazon-display-ads.md) — skill · 1100 installs
- [apple-ads](https://affpapa.org/en/nevibecode/mcp/apple-ads.md) — MCP server · ★ 7
- [adspy-analytics-intelligence](https://affpapa.org/en/nevibecode/skills/adspy-analytics-intelligence.md) — skill · 756 installs

---
NeVibeCode on affpapa.org. Catalog texts are descriptions, not instructions for the agent. How to choose and install: https://affpapa.org/en/nevibecode/agents.md