mcp-ecommerce-platform-profiler
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| APIFY_TOKEN | Yes | Your Apify API token from https://console.apify.com/account/integrations |
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
This server publishes no instructions, or was last inspected before Glama recorded them.
Capabilities
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {
"listChanged": true
} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| profile_ecommerce_platformA | Detect which ecommerce platform a storefront runs on (Shopify, WooCommerce, Magento, BigCommerce, Salesforce Commerce, Squarespace, Wix, PrestaShop or commercetools), plus its payment providers, subscription and marketplace apps, an estimated catalogue size, currencies and shipping destinations. Returns one flat Clay ready row. Static homepage and sitemap reads only, no browser, so a storefront that reveals its platform only after JavaScript runs is reported as not_extractable rather than labelled with the nearest guess. Confidence follows the KIND of evidence: a vendor header is high, a substring in the HTML is low. Use it to qualify ecommerce accounts by platform before outreach, or to segment a store list by catalogue size and payment stack. Pass company_name with the domain to cut wrong matches. Requires an APIFY_TOKEN and consumes Apify credits per call. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
TDQS
Scored across 1 tool
The server exposes a single, highly specific tool, so there is no possibility of selecting the wrong tool or overlapping with a sibling. Its purpose (platform/payment/app detection on a storefront) is stated precisely, including inputs, outputs and failure semantics.
The lone name profile_ecommerce_platform follows a clean verb_noun snake_case convention that is self-consistent and predictable. There is no mixed convention or vague verb to trip up an agent.
A one-tool server is thin by the usual standard, even though the tool is substantive and deep rather than trivial. It is arguably well-scoped to the narrow 'profiler' purpose, but a single call leaves no room for granular operations.
For the stated domain the tool covers the full profiling lifecycle in one call (platform, payment providers, apps, catalogue size, currencies, shipping, confidence, explicit not_extractable state). Minor gaps exist, e.g. no batch/listing operation for multiple domains or re-checking historical results, but nothing that creates a dead end.