ApparelHub MCP server: workflow-level tools that let an AI agent design apparel, build products, and sync them to sales channels through
Free
Nothing to run from here
Nanocart is installed from its publisher's own source and answers where it runs, so this marketplace is not in the path of a single call. There is no address here to send one to, and a panel that pretended otherwise would be showing you an answer we made up. Install it and call it from your own client — the Installation tab has the entry for each one.
Open Installation—
p95 latency
—
call success
local
runs on your machine
—
calls last 7d
What it does
Official NanoCart MCP server — manage your NanoCart store (products, orders, coupons, reports, settings) from any MCP-capable AI agent.
Quickstart
# 1 — run it from where its publisher ships it
npx -y nanocart-mcp
# 2 — ask your agent something
> Official NanoCart MCP server — manage your NanoCart store (products, orders, coupons, reports, settings) from any MCP-capable AI agent.
Nanocart is free: there is no plan to choose, no cap to set and nothing that can bill you.
Publishernot claimed
BYAll 1 server
bytebunny-io1 server
1 category
Collected from a public index. Nobody has claimed this account, so nothing here was written by its author — claim it if it is yours.
Installation
Where are you running it?
Every route below installs the same thing and ends at the same approval screen. This one runs on your machine: your client starts Nanocart as a process under your own user, with your files and your network, so the tool surface below is what it can do to your computer rather than to a server somewhere else. It is scanned, signed and pinned to the version you choose — read the surface before you approve it.
Claude Codedeclared by this listing
This is a public server: you run it yourself and this marketplace is not in the path. Claude Code registers it in one command.
claude mcp add nanocart-mcp -- npx -y nanocart-mcpReconnect, or start a new session, and the tools appear in the model’s tool list.
Free to install, and it runs from its publisher’s own package: no account, no key, no card.
What it asks of you
It reaches a system of yours, so it needs your own credential rather than the publisher’s: NANOCART_API_KEY, NANOCART_STORE_ID. You set them after installing; the value is sealed here and sent to the server on each call.
What it writes
One config entry your client uses to start the process locally. A local server runs with your file system and your network, which is why it is priced without metering.
What you approve
39 tools, with what each one reads, writes and reaches shown before you agree — the same list on every route above. Read the tool surface.
Tool surface
What the model actually sees. Descriptions are diffed on every release — see version history.
Get the store bound to this API key: name, slug (storeId), tier, domain, currency, configured payment processors, allowed domains. Secrets are never included.
Takes no parameters.
Example callreturns →
Current plan tier, its limits, and live usage (active products, coupons, monthly orders). Check this before bulk-creating products.
Takes no parameters.
Example callreturns →
List ALL products including drafts and archived. Optionally filter by status or search by name/slug substring (filtering happens client-side).
Takes no parameters.
Example callreturns →
List the store’s categories (via the public API).
Takes no parameters.
Example callreturns →
List orders, newest first. Filter by status and/or ISO date range; paginate with limit/lastKey.
Takes no parameters.
Example callreturns →
List all coupons with usage counts.
Takes no parameters.
Example callreturns →
List email subscribers (Product Alerts). Paginate with limit/lastKey.
Takes no parameters.
Example callreturns →
Get store settings: shipping_config, tax_config, email_config, order_config.
Takes no parameters.
Example callreturns →
Get hosted-storefront configuration (template, hero, sections). Only meaningful on hosted plans.
Takes no parameters.
Example callreturns →
Sales report for a date range: revenue, orders, AOV, tax collected (total + by state), shipping, discounts, top products.
Takes no parameters.
Example callreturns →
Cart funnel analytics for a date range: sessions that viewed, added to cart, reached checkout, purchased; abandoned value.
Takes no parameters.
Example callreturns →
Recent signed-webhook delivery attempts and results.
Takes no parameters.
Example callreturns →
Create a product. Defaults to DRAFT (invisible to shoppers) unless status
Takes no parameters.
Example callreturns →
Update any fields of an existing product by productId (partial update). Prices in integer cents.
Takes no parameters.
Example callreturns →
Archive (soft-delete) a product — it disappears from the store but stays in the database. CONFIRM WITH THE USER before calling; name the product, not just the id.
Takes no parameters.
Example callreturns →
Create a category. parentId makes it a subcategory.
Takes no parameters.
Example callreturns →
Update a category by categoryId (partial).
Takes no parameters.
Example callreturns →
Create a coupon. value = 1-100 for percent_off, integer cents for fixed_amount, ignored for free_shipping.
Takes no parameters.
Example callreturns →
Delete a coupon by code. CONFIRM WITH THE USER before calling.
Takes no parameters.
Example callreturns →
Update an order’s status, tracking number, or notes. Status transitions to
Takes no parameters.
Example callreturns →
Resend the order confirmation email to the customer for an order.
Takes no parameters.
Example callreturns →
Upload an image (or digital file) to the store’s storage and get back a public fileUrl for product/category images. Provide EITHER file_path (local server only) OR source_url (fetched server-side).
Takes no parameters.
Example callreturns →
Update ONE settings key: shipping_config, tax_config, email_config, or order_config. Read get_settings first and send the full desired value for that key. Tier limits apply to shipping methods.
Takes no parameters.
Example callreturns →
Update store display config: name, domain, brandColor, currency, allowedDomains. Payment credentials can NOT be changed here (dashboard only). Changing allowedDomains affects which sites the widget works on — confirm with the user.
Takes no parameters.
Example callreturns →
List the store\
Takes no parameters.
Example callreturns →
Fetch one fulfillment vendor including its order-sheet templateHtml.
Takes no parameters.
Example callreturns →
Create a fulfillment vendor. Requires name and at least one
Takes no parameters.
Example callreturns →
Update a fulfillment vendor (partial — provide only the fields to change; the rest are preserved, including the saved template). Use status
Takes no parameters.
Example callreturns →
Delete a fulfillment vendor — its routed products keep selling but orders stop being forwarded. CONFIRM WITH THE USER before calling; name the vendor, not just the id.
Takes no parameters.
Example callreturns →
Email the MERCHANT (never the vendor) a test order sheet rendered with sample data, so they can see exactly what the vendor will receive.
Takes no parameters.
Example callreturns →
Manually email an existing order to a vendor — for orders placed before the vendor was set up (items match by the products\
Takes no parameters.
Example callreturns →
List the store\
Takes no parameters.
Example callreturns →
Fetch one donation campaign by its slug (campaignId).
Takes no parameters.
Example callreturns →
Create a donation campaign. campaignId is the PUBLIC slug used in data-nanocart-donate=
Takes no parameters.
Example callreturns →
Update a donation campaign (partial — provide only the fields to change; everything else, including live counters, is preserved). Use status
Takes no parameters.
Example callreturns →
Delete a donation campaign — the donate button and stats widget stop rendering immediately. Donation records are kept and active Stripe subscriptions are NOT canceled (that happens in the Stripe dashboard). CONFIRM WITH THE USER before calling; name the campaign, not just the slug.
Takes no parameters.
Example callreturns →
List donation records, newest first. kind filters to
Takes no parameters.
Example callreturns →
List monthly supporters: amount, status (active/past_due/canceled), consecutive months, lifetime giving, start date.
Takes no parameters.
Example callreturns →
Donations report: range totals (raised, gift counts, one-time vs recurring split, new/canceled supporters, average/largest gift) plus live stats (all-time raised, active supporters, MRR) and per-campaign breakdowns. Dates are YYYY-MM-DD.
Takes no parameters.
Example callreturns →
Freeyour plan
$0 forever
- Every tool, no call limit
- No card, no account needed
- Source published under a licence you can read
- Runs on your machine — nothing of it reaches our gateway
- Nothing to cap, because nothing bills
What counts against your monthly calls
| Tool | Unit | Calls used | Out of the allowance |
|---|
Nothing here is billable. Nanocart costs nothing to install and nothing to call, at any volume.
Call allowance · this installenforced at the gateway
Monthly allowance, in calls
—
—
Alert at 80% · then the tool returns a normal MCP error
Used this month: $8.42
$16.58 left
ATrust score 96 / 100
Release 1.2.0 · scanned 25 Aug 2026
Two independent axes, because powerful and malicious are different questions. The grade is threat only. The capability level is blast radius, and it is never a penalty on the grade — it is priced as one subtract-only term in the score, where you can see it.
Threat score100
Client score96
Findings1 threat · 0 capability
Capabilitymoderate
Coveragesource
Verificationrepo
Surface digestfd7a7a2a191acc6fe818b3d6057b9db47bfdf223b71dd7ea09b0b8c80083d6e5
Score vectorthreat 100 → client 96
| Term | Level | What it prices | Points |
|---|---|---|---|
| capability-exposure | moderate | capability blast radius (moderate) — client exposure if the model is manipulated | −3 |
| verification-discount | repo | publisher verification (public source) — no provenance, but the source is public and inspectable | −1 |
| coverage-honesty | source | inspection depth (source) — how much of the target the scan could see | −0 |
score = clamp(round(threatScore − E_cap − E_ver − E_cov), 0, 100). No model, no opinion, no network call at scoring time: the same methodology version against the same bytes always produces this number, and every line above is a field of the report rather than a summary of it.
What the scan could actually read
A grade is only as meaningful as its coverage, so the scanner publishes its own depth before it publishes its result.
Tool surfaceread
Implementation sourceread
Package metadataread
Live transportnot available
Tools were statically extracted from the published source (39 recovered), not enumerated from a running server. Tool-poisoning, Unicode-smuggling, capability and toxic-flow analysis ran on this inferred surface, but a mis-parsed registration could be missed or mis-attributed, so tool-derived findings are capped below “confirmed”. To grade the real runtime surface, scan the running server: --command "npx -y <package>".
Capability — what it could do if the model were manipulated
Tags derived from each tool’s schema and the implementation, not from what the tool calls itself. moderate is the level these add up to.
| Tool | Capability tags | Why the tag was assigned |
|---|---|---|
| get_store_info | no tags | |
| get_tier_usage | no tags | |
| list_products | no tags | |
| list_categories | no tags | |
| list_orders | no tags | |
| list_coupons | no tags | |
| list_subscribers | no tags | |
| get_settings | no tags | |
| get_storefront | no tags | |
| sales_report | no tags | |
| analytics_funnel | no tags | |
| list_webhook_deliveries | no tags | |
| create_product | no tags | |
| update_product | no tags | |
| archive_product | no tags | |
| create_category | no tags | |
| update_category | no tags | |
| create_coupon | no tags | |
| delete_coupon | no tags | |
| update_order | external-sink | |
| resend_order_confirmation | no tags | |
| upload_image | no tags | |
| update_settings | no tags | |
| update_store_config | no tags | |
| list_vendors | no tags | |
| get_vendor | untrusted-input | |
| create_vendor | no tags | |
| update_vendor | no tags | |
| delete_vendor | no tags | |
| send_vendor_test | no tags | |
| send_order_to_vendor | no tags | |
| list_donation_campaigns | no tags | |
| get_donation_campaign | untrusted-input | |
| create_donation_campaign | no tags | |
| update_donation_campaign | no tags | |
| delete_donation_campaign | no tags | |
| list_donations | no tags | |
| list_donation_supporters | no tags | |
| donations_report | no tags |
Toxic-flow graph
The lethal trifecta, checked as a graph rather than as a checklist: untrusted input, a sensitive source and an external sink have to meet before there is a path worth worrying about.
Untrusted input can drive an external action even though no sensitive source is exposed.
Supply chain and provenance
Integrityfirst-seen
Surface digestfd7a7a2a191acc6f
Scanned2026-08-25
This is the first scan of this surface here, so there is nothing yet to compare it against.
Every result on this tab comes from one deterministic pass over the published package — offline, rule by rule, and auditable line by line above. Same methodology version, same bytes, same score.
Release history
Pinned to 1.2.0 — the install command below asks for that release. A pin is part of an install, so it is kept for this visit and written down when you install.
1.2.0
undated
installedNo release note was published with this version.
—
no reviews yet
Reviews are earned
Only accounts with at least 50 real tool calls against this server in the last 90 days can post. Ratings are weighted by how much the reviewer actually uses it, and publishers can reply once per review.
Reviews are earned
Writing one takes an account with at least 50 real tool calls against Nanocart in the last 90 days. That is the whole gate — there is no other way to post, which is why the counts beside each review are worth reading.
No reviews yet
Nobody has reviewed this listing. The rating on the card is the mean of the reviews written here and nothing else, so there is no rating until somebody writes the first — which takes an account with 50 real tool calls against it.