Skip to main content
Glama

Connect a running site and get its verify command

storefront_connect

Store key: call when the site is served from a process that keeps running (background, fixed port) and menu items show at that origin. Use http://localhost:, not 127.0.0.1: the sandbox key allows only localhost. Returns whether the origin is allowed, a runId and the exact verify command; run it as returned while the site runs. Sign-in and every check after it WAIT until the sandbox guest exists: report them, never stub sign-in. If originAllowed is false, read kit_docs_get topic onboarding. Each call starts a new run; use the latest runId. Example: {"storefrontKey":"pk_test_…","origin":"http://localhost:5173"}.

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": "storefront_connect"
  }
}

Input Schema

NameRequiredDescriptionDefault
pathNoOptional path the site is served under, for example /sandbox/, when origin has none.
originNoThe site's origin or full URL, for example http://localhost:4321 or https://example.no/shop/. A path in it goes into the verify command's --url.
storefrontKeyNoThe site's publishable storefront key (pk_test_… or pk_live_…).

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • changedInput schema / properties / origin / description
      Previous value: -"The site's origin or full URL, for example http://localhost:4321 or https://test.okam.no/sandbox/. A path in it goes into the verify command's --url."New value: +"The site's origin or full URL, for example http://localhost:4321 or https://example.no/shop/. A path in it goes into the verify command's --url."
  2. First observed

TDQS

A3.9/5.0
Behavior3/5

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

Annotations already declare readOnlyHint=false, idempotentHint=false, and openWorldHint=false; the description is consistent with that and usefully adds that each call starts a new run, that the latest runId should be used, and that sign-in and subsequent checks WAIT until the sandbox guest exists (do not stub). Those are genuine behavioral disclosures beyond the annotations. However, it does not state auth/permission or rate-limit behavior, and with a non-read-only, non-destructive mutation the bar is somewhat higher than what is given.

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-loads the trigger condition and then the return values, with the imperative warnings grouped afterward. Every sentence carries operational content, but the paragraph is dense and packs several distinct instructions (origin format, verify command usage, runId, sign-in waiting) without visual separation.

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?

There is no output schema, and the description compensates by naming the returned fields (originAllowed, runId, verify command) and describing the error path. It is close to complete for a tool of this complexity; only auth/permission requirements and the shape of the verify command's output are left implicit.

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

Parameters3/5

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

Schema description coverage is 100%, so the schema already documents origin, path, and storefrontKey in detail. The description adds some meaning beyond it, notably the localhost-only constraint on origin and the equivalence of a path inside the URL with --url, which the schema does not state. That extra context is real but partial, so it stays near the baseline.

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

Purpose4/5

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

The description states a specific action (supply a storefront key plus origin for a running site) and concrete outputs (whether the origin is allowed, a runId, and the exact verify command). It is clear what the tool does, though the opening phrase 'Store key:' is slightly indirect and it does not explicitly name a sibling it replaces (e.g. storefront_verify_result vs checkout_verify).

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

Usage Guidelines5/5

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

Gives an explicit trigger ('call when the site is served from a process that keeps running (background, fixed port) and menu items show at that origin') and an explicit fallback ('If originAllowed is false, read kit_docs_get topic onboarding'). It also states a hard constraint (use http://localhost:<port>, not 127.0.0.1) so the agent cannot pick the wrong form.

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

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources