Google Search Console integration for Model Context Protocol (MCP)
Nothing to run from here
Coupon Center 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.
96/100
trust score
194
downloads a day
local
runs on your machine
13
tools declared
What it does
It connects AI agents to the Coupon Center REST API with secure coupon flows.
Quickstart
# 1 — add it to Claude Code
claude mcp add --scope user --env 'CUPOM_API_KEY=${CUPOM_API_KEY}' --transport stdio coupon-center-mcp '--' npx -y @cupom_center/mcp
# 2 — ask your agent for something these tools do
# recommend_integration_flow, find_eligible_coupons, quote_single_coupon and 10 more
It needs CUPOM_API_KEY: this reads it from your environment, so export it first.
Coupon Center costs nothing on mcprush: there is no plan to choose here, no cap to set and nothing mcprush can bill you for.
Publishernot claimed
EXAll 1 server
experiens1 server
1 category
Collected from a public index. Nobody has claimed this account, so nothing here was written by its author — claim it if it is yours.
Installation
Where are you running it?
Every route below installs the same thing and ends at the same approval screen. This one runs on your machine: your client starts Coupon Center as a process under your own user, with your files and your network, so the tool surface below is what it can do to your computer rather than to a server somewhere else. Its scan result is on the Security tab — read the surface before you approve it.
Claude Codedeclared by this listing
This is a public server: you run it yourself and this marketplace is not in the path. You need Node.js — the current LTS (24) is the safe choice; npx comes with it. Claude Code registers it in one command; --scope user makes it available in every project. Claude Code reads CUPOM_API_KEY (API key do projeto e ambiente no Cupom Center) from your environment each time it starts the server, so the value stays out of its config: export it in your shell profile (macOS, Linux), or run setx CUPOM_API_KEY … and open a new terminal (Windows). The '--' is in quotes so that PowerShell passes it on.
claude mcp add --scope user --env 'CUPOM_API_KEY=${CUPOM_API_KEY}' --transport stdio coupon-center-mcp '--' npx -y @cupom_center/mcpReconnect, or start a new session, and the tools appear in the model’s tool list.
Free on mcprush, and it runs from its publisher’s own package: this marketplace is not in the path, so there is no key of ours to hold and no card to add.
What it asks of you
It reaches a system of yours, so it needs your own credential rather than the publisher’s: CUPOM_API_KEY — API key do projeto e ambiente no Cupom Center.. You set it in your own client’s config, on your machine — this marketplace never holds it.
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
13 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.
Choose the correct Cupom Center workflow before making API calls. This tool is local, has no commercial effect, and consumes no Cupom Center API allowance. Use it whenever it is unclear whether to discover, quote, issue, redeem, record payment, inspect, or reverse.
No parameter schema on file.
Discover coupons whose configured rules match the known customer/cart context. This does not calculate final totals, reserve budget, or consume a coupon. Missing context intentionally excludes coupons that require that fact. public defaults to true.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| context | no | — | |
| pagination | object | no | — |
Validate a known coupon code against the current cart, calculate authoritative totals, and create a temporary quote reservation. Use before redeeming or displaying a final discount. Do not use for catalog discovery.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| cart_id | string | no | — |
| coupon_code | yes | — | |
| context | yes | — |
Validate and calculate 2–10 known coupon codes. code_order stacks sequentially in supplied order; highest_discount_per_product applies only the best coupon to each product. Every supplied code must be eligible and applied.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| cart_id | string | no | — |
| coupon_codes | yes | — | |
| selection | object | yes | — |
| context | yes | — |
Automatically select public coupons for 1–20 marketplace/store units. Use only when a cart is partitioned into units and the integration wants Cupom Center to choose by coverage or total discount. This is not for validating a known code.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| mode | string | yes | — |
| context | object | no | — |
| priority | string | no | — |
| max_coupons_per_unit | integer | no | — |
| units | yes | — |
Create an individual code from an existing coupon configured with ISSUED distribution, typically for cart recovery, CRM, or individualized delivery. This never creates discount rules. Requires COUPON_ISSUE and a stable idempotency key.
No parameter schema on file.
Read the current state and immutable commercial details of an individual issued code.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| issuance_id | yes | — |
Revoke one active individual issuance. This is idempotent but cannot reactivate a consumed or expired code. Use only when the individual code must no longer be accepted.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| issuance_id | yes | — |
Confirm one coupon as a commercial operation. Normally call after quote_single_coupon and send the same cart/context. Provide cart_id, context.user.id, or quote_id for correlation. Include payment only after external confirmation; Cupom Center does not charge money.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| cart_id | string | no | — |
| order_id | string | no | — |
| coupon_code | yes | — | |
| context | yes | — | |
| quote_id | string | no | — |
| payment | no | — |
Atomically confirm 2–10 coupons previously calculated together. Preserve code order and selection strategy from the quote. Either all applicable uses/budgets confirm or none do.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| cart_id | string | no | — |
| order_id | string | no | — |
| coupon_codes | yes | — | |
| selection | object | yes | — |
| context | yes | — | |
| quote_id | string | no | — |
| payment | no | — |
Inspect a redemption operation, immutable receipts, current payment, and reversals. Use for reconciliation and as the first recovery step after a timeout when operation_id is known.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| operation_id | yes | — |
Record an integral payment that an external payment provider has already confirmed. This does not charge or capture money and does not consume coupons again. Requires PAYMENT_WRITE.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| operation_id | yes | — | |
| payment | yes | — |
Fully reverse one coupon operation and release its usage counters and budgets. The backend classifies it as cancellation without payment or refund with confirmed payment. This does not move money at the payment provider and accepts no reason or partial amount.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| operation_id | yes | — |
Free
$0 forever
- 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 Coupon Center or to call it, 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: —
ATrust score 96 / 100
Release 0.1.0 · scanned 5 Nov 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
Findings0 threat · 1 capability
Capabilitymoderate
Coveragesource
Verificationrepo
Surface digestfb9c8ca090e4173b756eebccaa58d7ee1789f96865e2bfe440b6b7fe42f837df
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 (13 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 |
|---|---|---|
| recommend_integration_flow | no tags | |
| find_eligible_coupons | untrusted-input | untrusted-input: declares openWorldHint: true (interacts with entities outside the server) |
| quote_single_coupon | external-sink | external-sink: declares readOnlyHint: false, openWorldHint: true, handler sends an HTTP POST (request("POST", …)) at dist/server.js:95 |
| quote_multiple_coupons | external-sink | external-sink: declares readOnlyHint: false, openWorldHint: true, handler sends an HTTP POST (request("POST", …)) at dist/server.js:110 |
| select_coupons_for_units | external-sink | external-sink: declares readOnlyHint: false, openWorldHint: true |
| create_coupon_issuance | external-sink | external-sink: declares readOnlyHint: false, openWorldHint: true, handler sends an HTTP POST (request("POST", …)) at dist/server.js:146 |
| get_coupon_issuance | untrusted-input | untrusted-input: declares openWorldHint: true (interacts with entities outside the server) |
| revoke_coupon_issuance | external-sink | external-sink: declares readOnlyHint: false, destructiveHint: true, openWorldHint: true, handler sends an HTTP POST (request("POST", …)) at dist/server.js:158 |
| redeem_single_coupon | external-sink | external-sink: declares readOnlyHint: false, destructiveHint: true, openWorldHint: true, handler sends an HTTP POST (request("POST", …)) at dist/server.js:176 |
| redeem_multiple_coupons | external-sink | external-sink: declares readOnlyHint: false, destructiveHint: true, openWorldHint: true, handler sends an HTTP POST (request("POST", …)) at dist/server.js:197 |
| get_coupon_operation | untrusted-input | untrusted-input: declares openWorldHint: true (interacts with entities outside the server) |
| record_operation_payment | external-sink | external-sink: declares readOnlyHint: false, openWorldHint: true, handler sends an HTTP POST (request("POST", …)) at dist/server.js:209 |
| reverse_operation | external-sink | external-sink: declares readOnlyHint: false, destructiveHint: true, openWorldHint: true, handler sends an HTTP POST (request("POST", …)) at dist/server.js:215 |
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.
flow-1
Untrusted input can drive an external action even though no sensitive source is exposed.
Supply chain and provenance
Integrityfirst-seen
Surface digestfb9c8ca090e4173b
Scanned2026-11-05
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 0.1.0. Pin a release below and the command asks for exactly that one.
0.1.0
undated
latestNo release note was published with this version.
—
no reviews yet
Who can review
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.
Sign in to write one
Any signed-in account that does not publish Coupon Center can review it, once — before installing it or after. A review from an account that has installed it is marked as one.
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 a signed-in account that does not publish it, and nothing else.