A-

mcp.packrift.com

https://mcp.packrift.com/mcp
91/100 · MCP Trust Grade · checked 3h ago · MCP 2025-06-18
Rug-pull watch: this server's tool surface has changed since baseline — last 5h ago. Continuously watched by wmcp.sh for drift & rug-pulls.

What it offers — 15 tools · Developer Tools

search_products

Use when the user names a category by keyword (e.g. 'kraft tape', 'bubble mailer', 'starter kit') with no dimensions. For dimension-based fit, prefer

get_product

Use after find_packaging_for_item or search_products to pull full detail for a handle: all variants, SKUs, dimensions, weight, stock. Input: handle. C

get_pricing

Use to confirm live unit price and line total before cart handoff. Required argument: variant_ids as an array of numeric Shopify variant IDs encoded a

check_inventory

Use to confirm stock before recommending a SKU or building a cart. Required argument: variant_ids as an array of numeric Shopify variant IDs encoded a

find_packaging_for_item

Use when the buyer has item dimensions and needs a fitting box or mailer. Required arguments are item_length_in, item_width_in, item_depth_in, item_we

get_shipping_estimate

Use when the buyer asks shipping cost for selected AI_APPROVE variants. Required arguments: destination_postal_code, country (US|CA), and items with v

get_cart_handoff_candidates

Returns priority AI-approved Packrift SKUs that are ready for MCP cart handoff exploration, including create_cart_url arguments, SKU records, measured

create_cart_url

Final checkout handoff after live product, price, inventory, and buyer confirmation. For most agents, use exact AI_APPROVE sku plus quantity. Use item

prepare_purchase_handoff

Preferred exact-SKU purchase prep for agents. Call first with sku, quantity, and buyer_confirmed=false to confirm AI_APPROVE product, live price, and

compare_alternatives

Exploration tool for buyers comparing a packaging spec, competitor-style item, or Uline-style request against Packrift AI_APPROVE products. Returns ra

pack_calculator

Exploration tool for item dimensions and weight. Calculates required inside dimensions, ranks Packrift box/mailer candidates, and gives void-fill guid

inventory_status

Live inventory exploration for one or more AI_APPROVE variants. Returns Shopify total quantity, available-for-sale state, location-level BOX warehouse

get_reorder_link

Return the Packrift reorder URL, product URL, and copy-procurement-spec text for one AI_APPROVE SKU or handle. Use for repeat-buy and procurement hand

get_bulk_quote_link

Return a tracked Packrift bulk quote URL for an exact requested packaging spec or SKU. Use when there is no exact match or the buyer needs bulk/procur

explain_no_exact_match

Explain why Packrift should not present a nearby product as an exact match, then return safe next actions and a tracked bulk quote URL.

Spec conformance20%100
Security (OWASP MCP)30%100
Reliability / performance20%92
Tool hygiene15%80
Transparency / provenance15%70

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 mcp.packrift.com 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 — mcp.packrift.com grade A-
Share on X Open card image

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.

MCP Trust Grade A- · wmcp.sh
[![MCP Trust Grade A-](https://wmcp.sh/mcp/grade/mcp.packrift.com/badge.svg)](https://wmcp.sh/mcp/grade/mcp.packrift.com)
<a href="https://wmcp.sh/mcp/grade/mcp.packrift.com"><img src="https://wmcp.sh/mcp/grade/mcp.packrift.com/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.