Skip to main content
Glama
Kroger MCP Server

Kroger MCP Server

by CupOfOwls

start_authentication

Initiates Kroger OAuth flow by returning an authorization URL to open in a browser; after sign-in, copy the callback URL back to complete authentication.

Instructions

Start the OAuth authentication flow with Kroger.

This tool returns a URL that the user needs to open in their browser to authenticate with Kroger. After authorization, the user will be redirected to a callback URL that they need to copy and paste back. If Kroger shows invalid_scope instead of the sign-in page, the app is not registered for one of the requested scopes (the scope field of the result, set by KROGER_USER_SCOPES in the server's configuration).

Returns: Dictionary with authorization URL, the requested scopes, and instructions

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "start_authentication"
  }
}

Input Schema

NameRequiredDescriptionDefault

No arguments

Output Schema

NameRequiredDescriptionDefault

No arguments

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed2 schema fields changedv0.4.0
    • addedInput schema / additionalProperties
      Added value: +false
    • changedOutput schema / (root)
      Previous value: -nullNew value: +{
      +  "additionalProperties": true,
      +  "type": "object"
      +}
  2. First observed

TDQS

A4.3/5.0
Behavior4/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations, the description carries the full burden and does well: it discloses the external user interaction required, the callback copy-paste step, and a specific failure mode (invalid_scope tied to KROGER_USER_SCOPES server config). It doesn't say whether calling it invalidates an existing token or whether it's idempotent, which is the main remaining gap.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Front-loaded with the core action, then the required user steps. Slightly dense in the invalid_scope sentence but every part conveys actionable behavior rather than filler.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

An output schema exists, so explaining return values is not required, yet the description summarizes them briefly rather than redundantly. For a zero-parameter starter tool this is nearly complete; only the explicit next-step handoff to complete_authentication is missing.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Zero parameters, so the baseline is 4 per the rubric. The description correctly implies no inputs are needed, though there is nothing additional to document.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb+resource ('Start the OAuth authentication flow with Kroger') and is clearly distinguishable from siblings like complete_authentication, force_reauthenticate, and test_authentication. The agent can tell this is the flow initiator, not a status check or a finisher.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description makes the usage context clear: call it to obtain a URL the user opens, then the user returns a callback URL. However, it never explicitly names the follow-up sibling (complete_authentication) or states that this must be called first / not to use it if already authenticated, leaving the sequencing to inference.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.