by cupofowls
Easily find the Kroger closest to you, browse products with prices, and manage your cart and orders using secure OAuth2
Connects AI assistants to Kroger's grocery API for finding stores, searching products with pricing, managing shopping carts, and viewing order history.
Kroger is a community-built MCP server published by cupofowls that provides AI assistants with tools and capabilities via the Model Context Protocol. Easily find the Kroger closest to you, browse products with prices, and manage your cart and orders using secure OAuth2 It is categorized under productivity, developer tools.
You can install Kroger in your AI client of choice. Use the install panel on this page to get one-click setup for Cursor, Claude Desktop, VS Code, and other MCP-compatible clients. This server runs locally on your machine via the stdio transport.
MIT
Kroger is released under the MIT license. This is a permissive open-source license, meaning you can freely use, modify, and distribute the software.
Add new capabilities to Claude beyond text generation
Example
Access external data sources, execute code, interact with tools and services
Transform Claude from chatbot to action-taking agent
Provide Claude with access to relevant context and data
Example
Load project documentation, access knowledge bases, query databases
Get more accurate, context-aware responses
Automate multi-step workflows combining AI and external tools
Example
Research → Summarize → Create document → Send notification
Complete complex tasks end-to-end without manual steps
Share your MCP server with the developer community
According to our notes, Kroger benefits from clear Model Context Protocol framing — fewer ambiguous “AI plugin” claims.
Kroger reduced integration guesswork — categories and install configs on the listing matched the upstream repo.
I recommend Kroger for teams standardizing on MCP; the explainx.ai page compares cleanly with sibling servers.
Useful MCP listing: Kroger is the kind of server we cite when onboarding engineers to host + tool permissions.
Strong directory entry: Kroger surfaces stars and publisher context so we could sanity-check maintenance before adopting.
Kroger is a well-scoped MCP server in the explainx.ai directory — install snippets and categories matched our Claude Code setup.
We wired Kroger into a staging workspace; the listing’s GitHub and npm pointers saved time versus hunting across READMEs.
Kroger has been reliable for tool-calling workflows; the MCP profile page is a good permalink for internal docs.
According to our notes, Kroger benefits from clear Model Context Protocol framing — fewer ambiguous “AI plugin” claims.
Strong directory entry: Kroger surfaces stars and publisher context so we could sanity-check maintenance before adopting.
showing 1-10 of 41
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.
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
A changelog with recent changes is here.
You will need Kroger API credentials (free from Kroger Developer Portal). Visit the Kroger Developer Portal to:
CLIENT_ID, CLIENT_SECRET, and set your REDIRECT_URIThe 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.
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:
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": {
"KROGER_CLIENT_ID": "your_client_id",
"KROGER_CLIENT_SECRET": "your_client_secret",
"KROGER_REDIRECT_URI": "http://localhost:8000/callback",
"KROGER_USER_ZIP_CODE": "10001"
}
}
}
}
# Install with uv (recommended)
uv pip install kroger-mcp
# Or install with pip
pip install kroger-mcp
# Clone the repository
git clone https://github.com/CupOfOwls/kroger-mcp
cd kroger-mcp
# Install with uv (recommended)
uv sync
# Or install with pip
pip install -e .
Create a .env file in your project root or pass in env values via the JSON config:
# Required: Your Kroger API credentials
KROGER_CLIENT_ID=your_client_id_here
KROGER_CLIENT_SECRET=your_client_secret_here
KROGER_REDIRECT_URI=http://localhost:8000/callback
# Optional: Default zip code for location searches
KROGER_USER_ZIP_CODE=90274
# With uv (recommended)
uv run kroger-mcp
# With uvx (directly from PyPI without installation)
uvx kroger-mcp
# Or with Python directly
python server.py
# With FastMCP CLI for development
fastmcp dev server.py --with-editable .
| Tool | Description | Auth Required |
|---|---|---|
search_locations | Find Kroger stores near a zip code | No |
get_location_details | Get detailed information about a specific store | No |
set_preferred_location | Set a preferred store for future operations | No |
get_preferred_location | Get the currently set preferred store | No |
check_location_exists | Verify if a location ID is valid | No |
| Tool | Description | Auth Required |
|---|---|---|
search_products | Search for products by name, brand, or other criteria | No |
get_product_details | Get detailed product information including pricing | No |
search_products_by_id | Find products by their specific product ID | No |
get_product_images | Get product images from specific perspective (front, back, etc.) | No |
| Tool | Description | Auth Required |
|---|---|---|
add_items_to_cart | Add a single item to cart | Yes |
bulk_add_to_cart | Add multiple items to cart in one operation | Yes |
view_current_cart | View items currently in your local cart tracking | No |
remove_from_cart | Remove items from local cart tracking | No |
clear_current_cart | Clear all items from local cart tracking | No |
mark_order_placed | Move current cart to order history | No |
view_order_history | View history of placed orders | No |
| Tool | Description | Auth Required |
|---|---|---|
list_chains | Get all Kroger-owned chains | No |
get_chain_details | Get details about a specific chain | No |
check_chain_exists | Check if a chain exists | No |
list_departments | Get all store departments | No |
get_department_details | Get details about a specific department | No |
check_department_exists | Check if a department exists | No |
| Tool | Description | Auth Required |
|---|---|---|
get_user_profile | Get authenticated user's profile information | Yes |
test_authentication | Test if authentication token is valid | Yes |
get_authentication_info | Get detailed authentication status | Yes |
force_reauthenticate | Clear tokens and force re-authentication | No |
| Tool | Description | Auth Required |
|---|---|---|
get_current_datetime | Get current system date and time | No |
Since the Kroger API doesn't provide cart viewing functionality, this server maintains local tracking:
kroger_cart.jsonkroger_order_history.jsonmark_order_placedremove_from_cart and clear_current_cart tools ONLY affect local tracking, not the actual Kroger cart| API | Version | Rate Limit | Notes |
|---|---|---|---|
| Authorization | 1.0.13 | No specific limit | Token management |
| Products | 1.2.4 | 10,000 calls/day | Search and product details |
| Locations | 1.2.2 | 1,600 calls/day per endpoint | Store locations and details |
| Cart | 1.2.3 | 5,000 calls/day | Add/manage cart items |
| Identity | 1.2.3 | 5,000 calls/day | User profile information |
Note: Rate limits are enforced per endpoint, not per operation. You can distribute calls across operations using the same endpoint as needed.
Set up a preferred location:
User: "Find Kroger stores near 90274"
Assistant: [Uses search_locations tool]
User: "Set the first one as my preferred location"
Assistant: [Uses set_preferred_location tool]
Search and add products:
User: "Add milk to my cart"
Assistant: [Uses search_products, then add_items_to_cart]
User: "Add bread, eggs, and cheese to my cart"
Assistant: [Uses search_products for each, then bulk_add_to_cart]
Manage cart and orders:
User: "What's in my cart?"
Assistant: [Uses view_current_cart tool to see local memory]
User: "I placed the order on the Kroger website"
Assistant: [Uses mark_order_placed tool, moving current cart to the order history]
When Claude attempts to modify your Kroger account, you will be asked to insert a link into your browser that will handle authentication and allow Claude to add/remove items from your cart. Ensure that you have already made a Kroger account (this is different than your Kroger development account) before attempting to paste this link into your browser to initiate authentication.
Contributions are welcome! Please feel free to submit a Pull Request. For major changes, please open an issue first to discuss what you would like to change.
This project is licensed under the MIT License - see the [LICENSE](LICE
Prerequisites
Time Estimate
15-60 minutes depending on server complexity
Steps
Troubleshooting
✓ Do
✗ Don't
💡 Pro Tips
Architecture
Model Context Protocol standardizes how AI hosts (Claude, Cursor) communicate with external tools and data sources through server implementations.
Protocols
Compatibility
✓ Use when
Use when you need Claude to access external data, execute actions, or integrate with tools. Best for extending AI capabilities beyond conversation.
✗ Avoid when
Avoid when native integrations exist (use official APIs directly), for real-time critical systems, or when security/compliance requires zero external dependencies.