chat.curie.app

Item: chat.curie.app
Rating: 94
Author: wmcp.sh

https://chat.curie.app/api/mcp/global

94/100 · MCP Trust Grade · checked 5h ago · MCP 2025-06-18

✓ Watched since 2026-06-03 — behavioral baseline locked. We re-check this server's tool surface on a schedule; if it adds, removes, or silently rewrites a tool (rug-pull), we record it.

What it offers — 35 tools · Database

search_products

Deprecated alias of `search_catalog` — prefer `search_catalog` (the UCP/Shopify-canonical catalog-search tool). `search_products` is a Curie-ism kept

get_product

Get full details for a specific product by its ID. Returns name, brand, description, pricing, affiliate links, 3D model URLs, and images. Returns a si

get_recommendations

Get product recommendations similar to a given product. Useful for 'show me more like this' requests. Returns structured product items (same shape as

view_3d_model

Get the 3D model viewer URL for a product. Returns GLB and USDZ URLs for interactive 3D viewing and AR. Recommended visualization: an HTML Artifact th

get_availability

Check product availability and pricing across retailers. Returns all affiliate links with current prices.

compare_products

Compare 2 to 6 products side-by-side. Returns a comparison matrix with each product's name, price, brand, 3D model availability, key attributes, and a

get_brand_context

Returns the merchant's brand palette, typography hints, voice/tone profile, signature phrases, forbidden words, and a system_prompt_block the AI clien

get_suggested_prompts

Onboarding suggestion chips for the chat surface — the same 'What's trending?' / 'Find me a gift' / 'Compare products' chips chat.curie.app shows abov

initiate_checkout

Begin a GUEST checkout flow for one or more products — NO sign-in required. Pass `shop_domain` (e.g. "allbirds.com") on Curie's cross-merchant route s

search_catalog

Search the store catalog by name, brand, style, color, or keywords. This is the UCP/Shopify-canonical catalog-search tool (Shopify Storefront MCP's `s

lookup_catalog

Batch-retrieve full product objects by ID in ONE call. This is the UCP/Shopify-canonical batch product-lookup primitive (Shopify Catalog MCP's `lookup

get_product_details

Deprecated alias of `get_product` — prefer `get_product` (the UCP-canonical product-detail tool). `get_product_details` is also a real Shopify Storefr

get_cart

Read a shopper's current cart by id. Returns line items, totals, discount info, and checkout URL. Passthrough to Shopify Storefront MCP's get_cart for

update_cart

Modify a Shopify cart — add line items, update quantities, remove lines. Pass cart_id=null to create a new cart. Returns the updated cart with checkou

create_cart

Create a new Shopify cart for the target shop, optionally pre-loaded with line items. UCP-canonical dev.ucp.shopping.cart.create_cart. Returns the new

cancel_cart

Cancel an existing Shopify cart. UCP-canonical dev.ucp.shopping.cart.cancel_cart. Idempotent — re-cancelling a cancelled cart returns success. Passthr

get_checkout

Read a Shopify checkout session's current state by id. Returns status, line items, shipping address, totals, brand voice. UCP-canonical dev.ucp.shoppi

update_checkout

Update fields on a Shopify checkout session. UCP-canonical dev.ucp.shopping.checkout.update_checkout — Curie's wrapper performs a PUT-semantics-safe d

+17 more tools

Spec conformance20%100

✓ initialize → protocolVersion 2025-06-18
✓ initialize HTTP 200
✓ unknown method → -32601
✓ tools/list → 35 tools
✓ every tool has name + inputSchema

Security (OWASP MCP)30%100

35 tools scanned
no injection markup
no secret-path refs

Reliability / performance20%92

single-probe latency 389ms (PRELIMINARY — continuous uptime/p95 from proxy telemetry lands in v2)

Tool hygiene15%81

97% of tools have typed inputSchema
22/35 declare outputSchema
2 destructive-by-name tools lack safety annotations

Transparency / provenance15%90

HTTPS ✓
RFC 9728 oauth-protected-resource metadata ✓
advertises protocol 2025-06-18

Observed behavior

No proxied traffic observed for this host yet. Connect it at /connect and its grade gains a measured Reliability score + per-tool behavioral evidence — the half a static scan can't produce.

Findings

No blocking issues found in the static + spec checks.

Grade another server

We re-grade chat.curie.app on a schedule and alert your Slack/webhook the moment its tools change or its grade drops — rug-pull insurance for the connection.

Share this report card

A 1200×630 card with the grade + audit — drop it in a post, Slack, or your repo.

MCP Trust report card — chat.curie.app grade A

Share on X Open card image

https://wmcp.sh/mcp/grade/chat.curie.app

Embed this grade

A live badge — it re-verifies itself and shows current stability. Static scorecards can't. Paste it in your README or site to show users you're independently audited.

Markdown (for your README)

[![MCP Trust Grade A](https://wmcp.sh/mcp/grade/chat.curie.app/badge.svg)](https://wmcp.sh/mcp/grade/chat.curie.app)

HTML

<a href="https://wmcp.sh/mcp/grade/chat.curie.app"><img src="https://wmcp.sh/mcp/grade/chat.curie.app/badge.svg" alt="MCP Trust Grade A · wmcp.sh"></a>

Agents: check this before connecting

Add the wmcp.sh trust oracle as an MCP server and call grade_mcp_server / check_mcp_drift in your agent's pre-connection gate:

https://wmcp.sh/mcp/trust

How this grade is computed. An open, independent rubric — Spec conformance (20%), Security mapped to the OWASP MCP Top 10 (30%), Reliability (20%), Tool hygiene (15%), Transparency (15%) — run by connecting to the server and inspecting its real MCP surface. The grade is free and identical whether or not the operator pays. v1 uses static + spec signals from a single connection; continuous uptime, real latency, and annotation-truthing (declared readOnly vs observed behavior) layer on via the wmcp.sh proxy.