MCP server for minia2a.uk — discover and call 1,600+ x402 pay-per-call APIs with USDC payments.
Qut Pay (Kaspi QR payments) 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.
What it does
Kaspi QR payments (Kazakhstan) via Qut Pay: create invoices, check status, refund, sandbox tests.
Quickstart
# 1 — add it to Claude Code
claude mcp add --scope user --env 'QUTPAY_API_KEY=${QUTPAY_API_KEY}' --transport stdio qut-pay-kaspi-qr-payments-mcp '--' npx -y @qutpay/mcp
# 2 — ask your agent for something these tools do
# qutpay_account, qutpay_create_invoice, qutpay_get_invoice and 6 more
It needs QUTPAY_API_KEY: this reads it from your environment, so export it first. Remote: no sign-in · Package: API key.
Qut Pay (Kaspi QR payments) costs nothing on mcprush: there is no plan to choose here, no cap to set and nothing mcprush can bill you for.
Collected from a public index. Nobody has claimed this account, so nothing here was written by its author — claim it if it is yours.
Where are you running it?
Every route below installs the same thing and ends at the same approval screen. This one can run either way — at an address its publisher runs, or as a process under your own user, with your files and your network — and this marketplace is in the path of neither.
This is a public server: you run it yourself and this marketplace is not in the path. You need Node.js — the current LTS (24) is the safe choice; npx comes with it. Claude Code registers it in one command; --scope user makes it available in every project. Claude Code reads QUTPAY_API_KEY (Qut Pay API key (qp_test_… sandbox or qp_live_…), from the cabinet → Integrations → API keys) from your environment each time it starts the server, so the value stays out of its config: export it in your shell profile (macOS, Linux), or run setx QUTPAY_API_KEY … and open a new terminal (Windows). The '--' is in quotes so that PowerShell passes it on.
claude mcp add --scope user --env 'QUTPAY_API_KEY=${QUTPAY_API_KEY}' --transport stdio qut-pay-kaspi-qr-payments-mcp '--' npx -y @qutpay/mcpReconnect, or start a new session, and the tools appear in the model’s tool list.
Its publisher also runs it at https://api.qut.kz/mcp: nothing to start on your machine, and this marketplace is not in the path.
claude mcp add --scope user --transport http qut-pay-kaspi-qr-payments-mcp https://api.qut.kz/mcpIt reaches a system of yours, so it needs your own credential rather than the publisher’s: QUTPAY_API_KEY — Qut Pay API key (qp_test_… sandbox or qp_live_…), from the cabinet → Integrations → API keys. You set it in your own client’s config, on your machine — this marketplace never holds it.
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.
9 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.
Read from its source code. A server that builds its tool list when it starts can list more tools than this.
Returns the organization behind the API key: mode (sandbox or live), tariff and limits, connected Kaspi cashiers, provider status. Call this first.
No parameter schema on file.
Creates an invoice (QR by default, or pushed to the customer's Kaspi.kz app with kind="phone"). Returns payUrl (hosted pay page), qrImageUrl, deepLink, expiresAt (~3 min). Always pass idempotencyKey (e.g. "order-1001") so a retry never creates a second invoice. Amount in KZT, ≤ 2 decimals; whole…
| Parameter | Type | Required | Notes |
|---|---|---|---|
| amount | number | yes | Amount in KZT, e.g. 2500 or 1500.5 |
| description | string | no | Shown to the customer, e.g. "Order #1001" |
| externalOrderId | string | no | Your order id; later GET /invoices?externalOrderId finds it |
| idempotencyKey | string | no | Unique per order; same key → same invoice |
| kind | string | no | "qr" (default) or "phone" (invoice pushed into the customer's Kaspi.kz app; needs customer.phone) |
| customer | object | no | — |
| successUrl | string | no | — |
| failUrl | string | no | — |
| metadata | object | no | Returned unchanged in webhooks |
Reads one invoice by id (inv_…). live=true asks Kaspi right now instead of the cached status. Status flow: new → pending → paid | failed | expired | cancelled; paid → partially_refunded → refunded.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| id | string | yes | — |
| live | boolean | no | — |
Lists invoices of the organization, newest first. Filter by status, externalOrderId, date range (ISO), limit ≤ 50, offset for paging.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| status | string | no | — |
| externalOrderId | string | no | — |
| from | string | no | ISO date/time, inclusive |
| to | string | no | ISO date/time, exclusive |
| limit | integer | no | — |
| offset | integer | no | — |
Closes a pending invoice. A QR may still be paid until expiresAt — then invoice.paid arrives anyway; handle it.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| id | string | yes | — |
Full refund (omit amount) or partial refund of a paid invoice. Needs the refunds:write scope. With a LIVE key real money is returned to the customer, so confirm=true is required and the merchant must have asked for this refund explicitly.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| id | string | yes | — |
| amount | number | no | Omit for a full refund |
| reason | string | no | — |
| confirm | boolean | no | Required (true) with a live key |
Completes a sandbox invoice as paid / failed / expired without Kaspi, so the whole flow including the merchant's webhook can be tested. Refuses to run with a live key.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| id | string | yes | — |
| status | string | no | Default "paid" |
Read-only list of recurring invoice schedules. Needs the subscriptions:manage scope on the key.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| status | string | no | — |
| limit | integer | no | — |
Reads a recurring invoice schedule by id (sub_…). Needs the subscriptions:manage scope.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| id | string | yes | — |
- Every tool, no call limit
- No card, and mcprush charges nothing for it
- Source published under MIT
- Runs on your machine — nothing of it reaches our gateway
- Nothing to cap, because mcprush bills nothing
What counts against your monthly calls
| Tool | Unit | Calls used | Out of the allowance |
|---|
Nothing here is billable: mcprush charges nothing to install Qut Pay (Kaspi QR payments) or to call it, at any volume.
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.
| 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 |
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.
Tools were statically extracted from the published source (9 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 |
|---|---|---|
| qutpay_account | untrusted-input | untrusted-input: declares openWorldHint: true (interacts with entities outside the server) |
| qutpay_create_invoice | external-sink | external-sink: declares readOnlyHint: false, openWorldHint: true |
| qutpay_get_invoice | untrusted-input | untrusted-input: declares openWorldHint: true (interacts with entities outside the server) |
| qutpay_list_invoices | untrusted-input | untrusted-input: declares openWorldHint: true (interacts with entities outside the server) |
| qutpay_cancel_invoice | external-sink | external-sink: declares readOnlyHint: false, openWorldHint: true |
| qutpay_refund_invoice | external-sink | external-sink: declares readOnlyHint: false, destructiveHint: true, openWorldHint: true |
| qutpay_simulate_payment | external-sink | external-sink: keyword "webhook", declares readOnlyHint: false, openWorldHint: true |
| qutpay_list_subscriptions | untrusted-input | untrusted-input: declares openWorldHint: true (interacts with entities outside the server) |
| qutpay_get_subscription | untrusted-input | untrusted-input: declares openWorldHint: true (interacts with entities outside the server) |
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.
Supply chain and provenance
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
Always latest — the install command names no version, so it installs the newest release when it runs; the current release on file is 0.1.2. Pin a release below and the command asks for exactly that one.
No release note was published with this version.
One review per account, from a signed-in account that does not publish this listing. Nothing else is asked — you can say what you think before you install it. Publishers can reply once per review, and a review can be edited or deleted by whoever wrote it.
Any signed-in account that does not publish Qut Pay (Kaspi QR payments) can review it, once — before installing it or after. A review from an account that has installed it is marked as one.
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 a signed-in account that does not publish it, and nothing else.