Your coding assistant needs its own credential to talk to Postman on your behalf — this API key is what the MCP server uses to authenticate as you.

1. Go to go.postman.co/settings/me/api-keys.
2. Generate a new API key and copy it somewhere safe — you won't be able to see it again.

The Postman MCP Server implements the Model Context Protocol so any compatible agent or IDE can read and act on your Postman workspaces, collections, specs, and environments.

Remote server (recommended) — add this to your editor's MCP configuration, using your API key from Step 1:

{
  "mcpServers": {
    "postman": {
      "url": "https://mcp.postman.com/minimal",
      "headers": {
        "Authorization": "Bearer YOUR_POSTMAN_API_KEY"
      }
    }
  }
}

Local server — an alternative if you'd rather run it locally, or if you ever need MCP to reach an API running on your own machine:

export POSTMAN_API_KEY=YOUR_POSTMAN_API_KEY
npx @postman/postman-mcp-server

Change /minimal to /code or /mcp (or add --code / --full locally) for more tools. minimal is enough for this module.

Every major agent and IDE has its own config file location — see the IDE-specific setup docs for Claude Code, Cursor, VS Code, Windsurf, Gemini CLI, and others.

With the MCP server connected, your assistant can now see your Postman account directly. Confirm it actually works by pointing it at the workspace you built in the previous module.

1. In your editor, ask your assistant something like:

   Copy prompt

   Using the Postman MCP tools, find my "[Your Name] - AI Basics" workspace and tell me what collections are in it.

2. Confirm it finds the workspace and collection you created in Getting Started with Agent Mode.