Atlas / MCP servers / cupofowls / Kroger

KrogerSAFE

mcp/cupofowls/kroger

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 k

Verdict
SAFE
Grade
B
Trust score
89 /100
Exposed tools
29 20r · 6w · 3d
Transport
sse · streamable-http
License
MIT
Stars
74
01

Overview

From the repository's own README, as read at the audited commit. Badges and raw HTML are left out.

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

{
"mcpSe
Read from source at commit 99ba2ba88d35OBSERVED · 2026-10-07
02

Connect

Built from this server's own package name, version and transport as found in its source — not copied from anyone's documentation, so it cannot drift against a page we do not control. Replace the environment placeholders with a token scoped to the least it needs.

claude-code
claude mcp add kroger-mcp --env KROGER_CLIENT_SECRET=${KROGER_CLIENT_SECRET} -- uvx kroger-mcp
claude-desktop
{
  "mcpServers": {
    "kroger-mcp": {
      "command": "uvx",
      "args": [
        "kroger-mcp"
      ],
      "env": {
        "KROGER_CLIENT_SECRET": "${KROGER_CLIENT_SECRET}"
      }
    }
  }
}
03

Exposed tools (29)

20 read · 6 write · 3 destructive. Blast radius: 3 tools can delete or overwrite — an agent that can be talked into calling a tool can be talked into calling this one.

ToolRiskDescription
add_items_to_cartwrite
bulk_add_to_cartwrite
bulk_search_productsread
check_chain_existsread
check_department_existsread
check_location_existsread
clear_current_cartdestructive
complete_authenticationread
force_reauthenticatedestructive
get_authentication_inforead
get_chain_detailsread
get_current_datetimeread
get_department_detailsread
get_location_detailsread
get_preferred_locationread
get_product_detailsread
get_product_imagesread
get_user_profileread
get_user_zip_coderead
list_chainsread
list_departmentsread
mark_order_placedwrite
remove_from_cartdestructive
search_products_by_idread
set_preferred_locationwrite
start_authenticationwrite
test_authenticationread
view_current_cartread
view_order_historywrite
04

Trust audit

SAFEgrade B · trust 89/100 Nothing in the source contradicts what it says it does. Grade A is reserved for packages that have also passed the behavioural sandbox.

LayerWhat it checksResult
L0Provenance & inventoryPASS
L1Static analysis of the codePASS
L2Instruction surface (what it tells the agent)PASS
L3Class-specific surfaceWARN
L4Behavioural (sandbox)SKIPPED

What the source does

Filesystem
declared (1 observation(s))
Network
declared (1 observation(s))
Shell
none-observed
Dependencies
not all pinned
Secrets in source
none-found

Findings (2)

MEDIUMFilesystem / path · mcp.destructive_tools · CWE-22, CWE-59
clear_current_cart, force_reauthenticate, remove_from_cart
Why it matters. 3 tool(s) can delete or overwrite
Fix. prefer a read-only mode or scoped tokens; the page states the blast radius
LOWSupply chain · supply.unpinned · CWE-829, CWE-1357
requirements.txt
fastmcp, kroger-api, requests, pydantic, python-dotenv
Why it matters. 5 requirement(s) not pinned with ==
Fix. pin exact versions

Gates applied: no_behavioural_pass.

Audited 2026-10-07 · audit v0.4.1 · source sha 99ba2ba88d35full audit observations/trust-audit/mcp-server/cupofowls__kroger.json · Report an issue / request a re-scan
05

Audit history

Every audit this server has had. A grade with a past is a grade somebody is still checking.

DateSourceVerdictGradeScoreChange
2026-10-0799ba2ba88d35SAFEB89first audit
06

Questions

What is the Kroger MCP server?

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 k

What tools does Kroger expose?

29 in total: 20 read-only, 6 that write, and 3 that can delete or overwrite (clear_current_cart, force_reauthenticate, remove_from_cart). Every one is listed on this page with its risk.

Is Kroger safe to connect to an agent?

The audit found nothing in the source that contradicts what it says it does, and graded it B (89/100). Grade A is held back for packages that have also passed a sandboxed behavioural run, which is why a clean server reads B. Separately from the audit: 3 of its tools can destroy data, so scope the token you give it to what you actually need.

What credentials does Kroger need?

It reads KROGER_CLIENT_SECRET from the environment. Give it a token scoped to the least it needs — an agent that can be talked into calling a tool can be talked into calling it with your credentials.

How does Kroger run?

It speaks sse and streamable-http, so it runs as a service you connect to over the network. It is published on PyPI as kroger-mcp.

How current is this page?

The grade is for one exact copy of the source (99ba2ba88d35), read on 2026-10-07. The repository is watched and re-audited when it changes.

Advertisement