How to Connect Amazon Seller Central to Gemini — via MCP

💡 No install? Use cloud.anythingmcp.com directly. Sign in, click Connectors → Amazon Seller Central (SP-API), paste your credentials, mint an MCP API key — done. No Docker, no git clone, no local server.

Amazon Seller Central + Gemini

Ask Gemini about your Amazon business — orders, FBA stock, buy-box position, fee-aware margins and SP-API reports — through Amazon's official Selling Partner API with your own private app credentials.

Prerequisites

A professional Seller Central account and a (free) self-authorized SP-API app. The connector needs these environment variables:

SPAPI_CLIENT_ID, SPAPI_CLIENT_SECRET, SPAPI_REFRESH_TOKEN, SPAPI_ENDPOINT, SPAPI_MARKETPLACE_ID, SPAPI_SELLER_ID

Step 1 — Get credentials

1. Seller Central → Apps & Services → Develop Apps (first time: complete the developer profile; Amazon reviews it manually).
2. Add new app client → type Sellers → select roles ("Inventory and Order Tracking", "Pricing", "Amazon Fulfillment", "Finance and Accounting"). No restricted PII roles needed.
3. View → copy Client ID and Client Secret (LWA credentials).
4. Authorize → copy the Refresh Token (Atzr|…).
5. SPAPI_ENDPOINT: https://sellingpartnerapi-eu.amazon.com (EU), -na (Americas) or -fe (JP/AU/SG). SPAPI_MARKETPLACE_ID: e.g. US ATVPDKIKX0DER, DE A1PA6795UKMFR9. SPAPI_SELLER_ID: your Merchant Token (Account Info).

The connector performs the Login-with-Amazon OAuth2 exchange automatically and sends the 1-hour access token in the x-amz-access-token header — no AWS keys, no SigV4.

Step 2 — Install the adapter

curl -fsSL https://raw.githubusercontent.com/HelpCode-ai/anythingmcp/main/docker-compose.quickstart.yml -o docker-compose.yml
printf 'JWT_SECRET=%s\nENCRYPTION_KEY=%s\n' "$(openssl rand -hex 32)" "$(openssl rand -hex 32)" > .env
docker compose up -d

Open the connector store, import Amazon Seller Central (SP-API), fill in the env vars, and assign it to an MCP server.

Step 3 — Add the connector in Gemini

Your server URL: in AnythingMCP, open MCP Servers → the server this connector is on, and copy its URL (https://cloud.anythingmcp.com/mcp/…). Use it wherever this guide shows YOUR_SERVER_ID.

Gemini CLI reads MCP servers from ~/.gemini/settings.json (or %APPDATA%\gemini\settings.json on Windows). Add:

{
  "mcpServers": {
    "amazon-seller": {
      "httpUrl": "https://cloud.anythingmcp.com/mcp/YOUR_SERVER_ID",
      "headers": { "X-API-Key": "YOUR_MCP_API_KEY" }
    }
  }
}

1. Get your MCP API key from AnythingMCP → MCP Servers → your server → API keys.
2. Save the file and restart gemini.
3. Run /mcp inside the Gemini CLI — Amazon Seller should be listed as available.
4. Vertex AI Studio: pass https://cloud.anythingmcp.com/mcp/YOUR_SERVER_ID to the tools array of your request with the same X-API-Key header.

Available tools

Example prompts

• "Summarize this week's orders by day and fulfillment channel."
• "Which FBA SKUs have fewer than 10 fulfillable units?"
• "Who owns the buy box for my top ASIN and at what price?"

Notes

• Buyer names/addresses (PII) are not exposed — that requires Amazon's Restricted Data Token and an approved restricted role.
• v1 is read-focused; repricing/listing writes are on the roadmap.
• Test safely first: set SPAPI_ENDPOINT to https://sandbox.sellingpartnerapi-eu.amazon.com for canned sandbox responses.

Next steps

• Turn Amazon Seller Central into an MCP server — full guide
• Automate your Amazon business with AI — real workflows
• Connect to Claude
• Connect to ChatGPT
• Connect to Cursor
• Connect to Meta Muse