Using Cursor with DataDoe MCP

Use Cursor when you want a coding workspace that connects to DataDoe through MCP.

Prerequisites

• Cursor (opens in a new tab) installed, with an active sign-in session.
• A DataDoe MCP key. Create one in DataDoe MCP Integrations (opens in a new tab).

Step 1: Add the DataDoe MCP server

Add this to ~/.cursor/mcp.json for global setup, or .cursor/mcp.json for a project:

1{
2    "mcpServers": {
3        "datadoe": {
4            "url": "https://mcp.datadoe.com/mcp/v1",
5            "headers": {
6                "datadoe-mcp-key": "YOUR_DATADOE_MCP_KEY"
7            }
8        }
9    }
10}

Replace YOUR_DATADOE_MCP_KEY with your DataDoe MCP key. Cursor connects to remote MCP servers over Streamable HTTP directly. No local proxy process is needed.

Sharing the config with your team. Do not commit your key. Use Cursor's environment interpolation instead. Set "datadoe-mcp-key": "${env:DATADOE_MCP_KEY}" and export DATADOE_MCP_KEY in your shell.

Step 2: Reload Cursor

Restart Cursor, or reload the window, so it loads the new MCP server. You can confirm it is up in Cursor Settings → Tools & MCP (older Cursor versions call it MCP). The datadoe entry should show its tools with a green status dot.

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 Cursor returns real data, you are connected.