Search, compare in 3D, and buy products from 5.6M+ Shopify stores. Free tier; Pro adds checkout.
Web & Searchv1.0.0ssechat.curie.app repository
| Criterion | Points | Observed |
|---|---|---|
| reachability | 25 / 25 | HTTP 200, initialize accepted in 1018ms |
| protocol | 8 / 15 | valid JSON-RPC initialize result, protocolVersion 2025-06-18, serverInfo curie-commerce-global@1.0.0 — registry declares deprecated 'sse' transport |
| tooling | 35 / 35 | tools/list OK: 30 tools e.g. "get_recommendations"; 30/30 described, 30/30 fully-typed schemas, median description 431 chars |
| latency | 7 / 10 | initialize round-trip 1018ms |
| provenance | 8 / 15 | description present; repository linked; version 1.0.0; namespace co.curie does NOT match remote host (expected *.curie.co) |
Score 83/100 · latency 1018ms · 30 tools · auth: open
Claude Code:
claude mcp add --transport http commerce https://chat.curie.app/api/mcp/global
Generic MCP client config:
{ "mcpServers": { "commerce": { "type": "http", "url": "https://chat.curie.app/api/mcp/global" } } }
MCP Queen is a graded index, not a middleman — your agent connects directly to the server above. Check the grade and evidence first; that's the point.
Share this server: permalink https://mcpqueen.com/s/co.curie/commerce · referral link https://mcpqueen.com/go/co.curie/commerce (counts as “routed via the queen”).
Live badge, re-probed continuously — put it in your README:
[](https://mcpqueen.com/s/co.curie/commerce)
Think the grade is wrong? Fix the finding the evidence shows, then the next probe cycle picks it up automatically (full cycle ≈ 3 days) — or open a dispute via the MCP endpoint.
Email alerts when the grade changes or the endpoint stops answering. Double-opt-in, one-click unwatch, free while in beta.
| When (UTC) | Grade | Score | Latency |
|---|---|---|---|
| 2026-07-12 21:30 | B | 83 | 1018ms |