AmzDesignKit MCP server
Connect Claude, ChatGPT, Cursor or any MCP client to 77,000+ real Amazon listing image examples. Search by image type and category, then let your AI analyse the images. Free, no API key.
- Server URL
https://mcp.amzdesignkit.com/mcp- Transport
- Streamable HTTP
- Authentication
- None. Rate limit: 120 requests per minute per IP.
What your AI can do
- list_taxonomy: every image type and Amazon category, with example counts.
- search_examples: find examples by type, category or free text (product, brand, feature).
- get_example: full details: purpose of the image, brand, category path, marketplace, listing position, bullet points, similar examples.
- get_example_images: returns up to 4 actual images so the assistant can see and analyse them.
- analyse_listing_images (prompt): "find and analyse the best listing images for my product".
Claude (claude.ai web, desktop and mobile)
- Open Settings → Connectors.
- Click Add custom connector.
- Name:
AmzDesignKit. URL:https://mcp.amzdesignkit.com/mcp. Leave OAuth fields empty. - Click Add. In a chat, open the tools menu and make sure AmzDesignKit is on.
On Team and Enterprise plans an owner may need to add the connector first.
Claude Code
claude mcp add --transport http amzdesignkit https://mcp.amzdesignkit.com/mcp
Then run /mcp in Claude Code to confirm it is connected.
ChatGPT
- Open Settings → Apps & Connectors → Advanced settings and turn on Developer mode.
- Back in Apps & Connectors, click Create.
- Name:
AmzDesignKit. MCP server URL:https://mcp.amzdesignkit.com/mcp. Authentication: No authentication. - Tick that you trust the app, then Create. In a chat, choose it from the + menu.
Cursor
Add this to ~/.cursor/mcp.json (or .cursor/mcp.json in a project):
{
"mcpServers": {
"amzdesignkit": {
"type": "http",
"url": "https://mcp.amzdesignkit.com/mcp"
}
}
}
VS Code (GitHub Copilot)
code --add-mcp '{"name":"amzdesignkit","type":"http","url":"https://mcp.amzdesignkit.com/mcp"}'
Claude Desktop (config file) and other stdio-only clients
If a client only supports local servers, bridge with mcp-remote (needs Node.js). For Claude Desktop, edit claude_desktop_config.json via Settings → Developer → Edit Config, then restart the app:
{
"mcpServers": {
"amzdesignkit": {
"command": "npx",
"args": [
"-y",
"mcp-remote",
"https://mcp.amzdesignkit.com/mcp"
]
}
}
}
Try it
- "Show me 8 Amazon infographic examples for collagen supplements and explain what they have in common."
- "Find hero image examples in Home & Kitchen and look at the top 4. What should my bed sheet main image copy?"
- "Compare A+ content examples for pet supplies and list the modules they use."
For developers
Test with the MCP Inspector:
npx @modelcontextprotocol/inspector
Choose transport Streamable HTTP and URL https://mcp.amzdesignkit.com/mcp. Plain JSON data is also available at /api/taxonomy and /api/examples, documented in llms.txt.
A free account lets you save examples to boards, share them with your team and run AI analysis. Paid plans add importing examples from any Amazon listing.
Sign up free