ClaudeのようなAIアシスタントを提供するFastMCPサーバーは、モデルコンテキストプロトコル(MCP)を介して、Krogerの食料品店のショッピング機能にアクセスします。 このサーバーは、AIアシスタントがストア、検索製品、ショッピングカートの管理、およびKroger-api pythonライブラリを介してKrogerの包括的な食料品データにアクセスできるようにします。

docs:** https://cupofowls.github.io/kroger-api/building-ai-agents/agent-lab — kroger-mcp で AI エージェントをビルドし、完全なツール参照。

デモ

このMCPサーバーでClaudeを使用して、店舗を検索し、製品を見つけ、アイテムをカートに追加します。

[https://github.com/user-attachments/assets/69055f5f-04f5-4ec1-96ac-330aa288fbd1]

変更ログ

最近の変更に伴う変更履歴はこちら

すぐにスタート

前提条件

あなたは、Kroger APIの資格情報(Kroger Developer Portalから無料)が必要になります。 Kroger Developer Portal にアクセス:

1. 開発者アカウントの作成
2. アプリケーションを登録する
3. [CLIENT_ID, [CLIENT_SECRET]], [REDIRECT_URI]]] を受け取り、 [[REDIRECT_URI]] をセットします。

ユーザ認証が必要なツールを実行すると、Webブラウザでアプリを承認するように求められます.

🛒 Kroger MCP Server 🛍️ – FastMCP for Kroger Shopping

A FastMCP server that provides AI assistants like Claude with access to Kroger’s grocery shopping functionality through the Model Context Protocol (MCP). This server enables AI assistants to find stores, search products, manage shopping carts, and access Kroger’s comprehensive grocery data via the kroger-api python library.

📚 Docs: https://cupofowls.github.io/kroger-api/building-ai-agents/agent-lab — build an AI agent with kroger-mcp, and the full tool reference.

📺 Demo

Using Claude with this MCP server to search for stores, find products, and add items to your cart:

https://github.com/user-attachments/assets/69055f5f-04f5-4ec1-96ac-330aa288fbd1

Changelog

A changelog with recent changes is here.

🚀 Quick Start

Prerequisites

You will need Kroger API credentials (free from Kroger Developer Portal). Visit the Kroger Developer Portal to:

1. Create a developer account
2. Register your application
3. Get your CLIENT_ID, CLIENT_SECRET, and set your REDIRECT_URI

The first time you run a tool requiring user authentication, you’ll be prompted to authorize your app through your web browser. You’re granting permission to your own registered app, not to any third party.

Installation

⚠️ macOS users must use installation Option 2 ⚠️

Option 1: Using uvx with Claude Desktop (Recommended)

Once published to PyPI, you can use uvx to run the package directly without cloning the repository:

Edit Claude Desktop’s configuration file:

macOS: ~/Library/Application Support/Claude/claude_desktop_config.json

Linux: ~/.config/Claude/claude_desktop_config.json

Windows: %APPDATA%/Claude/claude_desktop_config.json

{
  "mcpServers": {
    "kroger": {
      "command": "uvx",
      "args": [
        "kroger-mcp"
      ],
      "env": {
        "KROGER_CLIENT_ID": "your_client_id",
        "KROGER_CLIENT_SECRET": "your_client_secret", 
        "KROGER_REDIRECT_URI": "http://localhost:8000/callback",
        "KROGER_USER_ZIP_CODE": "10001"
      }
    }
  }
}

Benefits of this method:

• Automatically installs the package from PyPI if needed
• Creates an isolated environment for running the server
• Makes it easy to stay updated with the latest version
• Doesn’t require maintaining a local repository clone

Option 2: Using uv with a Local Clone

First, clone locally:

git clone https://github.com/CupOfOwls/kroger-mcp

Then, edit Claude Desktop’s configuration file:

{
  "mcpServers": {
    "kroger": {
      "command": "uv",
      "args": [
        "--directory",
        "/path/to/cloned/kroger-mcp",
        "run",
        "kroger-mcp"
      ],
      "env": {