Using Claude Code with DataDoe MCP

Use Claude Code when you want a local coding session over your repository, with DataDoe as a live Amazon data source for your AI agent.

Prerequisites

• Claude Code (opens in a new tab) installed and signed in.
• A DataDoe MCP key. Create one in DataDoe MCP Integrations (opens in a new tab).

Step 1: Add the DataDoe MCP server

Run this command in your project root:

1claude mcp add --transport http --scope project --header "datadoe-mcp-key: YOUR_API_KEY" datadoe "https://mcp.datadoe.com/mcp/v1"

Replace YOUR_API_KEY with your DataDoe MCP key.

Scope choice:

• --scope project (used above) saves the config to .mcp.json in your project - useful when you want the team to share the same MCP setup.
• --scope user saves it globally for your user - useful when you want DataDoe available across all projects.

Step 2: Reload Claude Code

In an existing Claude Code session, run /mcp to reload the server list. For a fresh session, just start Claude Code as usual - it picks up the config automatically.

Step 3: Test the connection

Run a prompt that uses DataDoe data, for example:

Show me my Amazon Seller Central sales for the last 7 days.

If Claude Code returns real data, you're connected.

Starter project

Want a working starting point? Clone our Claude Code template repository (opens in a new tab) - it ships with .mcp.json preconfigured and example prompts to get you exploring fast.