Comprehensive Model Context Protocol server for managing Home Assistant through AI assistants.
Topup 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
Travel eSIMs and mobile top-ups paid in USDC via x402. A technology demonstration, limited pilot.
Quickstart
# 1 — add it to Claude Code
claude mcp add --scope user --transport http topup-mcp https://iomarkets.app/mcp
# 2 — ask your agent for something these tools do
# lookup_phone, list_offers, quote and 6 more
Topup 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. Nothing here runs on your machine and nothing runs on ours: this server answers at its publisher’s own address, and what you install is the connection straight to it.
This is a public server: it answers at its publisher’s own address and this marketplace is not in the path. Claude Code registers it in one command; --scope user makes it available in every project. The transport below is http, as the publisher's own manifest declares it.
claude mcp add --scope user --transport http topup-mcp https://iomarkets.app/mcpReconnect, or start a new session, and the tools appear in the model’s tool list.
One config entry pointing straight at the publisher’s own address — this marketplace is not in the path, and nothing from this listing executes on your machine.
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.
Identify the country and mobile operator of a phone number and list the top-up offers available for it. Free. The operator is DETECTED from the number range and is a guess: MVNOs (Tesco Mobile, Giff Gaff, Lebara, Voxi, Sky…) resolve to the host network they ride on. Read the detected brand back to the human and have them confirm it before buying, and use other_brands to correct it — a voucher bo
| Parameter | Type | Required | Notes |
|---|---|---|---|
| phone | string | yes | E.164, e.g. +919876543210 |
Browse purchasable offers: mobile top-ups, travel eSIMs, prepaid bills, or international payment corridors (bank / mobile money / UPI) for a country. Free. Prices shown are indicative; the quote fixes them.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| type | string | yes | payout = international payment (bank / mobile money / UPI) |
| country | string | no | ISO-3166 alpha-2, e.g. IN |
| brand | string | no | — |
| limit | integer | no | page size, default 100; 0 means all |
| offset | integer | no | use next_offset from the previous page |
Lock a price (10 minutes) for one purchase. Returns quoteId, exact USDC price and what will be delivered. Free. ALWAYS show the human the price and the recipient before buying.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| type | string | yes | — |
| offerId | string | yes | — |
| phone | string | no | recipient phone for topup/bill (E.164) |
| amount | number | no | for range offers: amount in the recipient's local currency |
| iccid | string | no | existing eSIM to top up (optional) |
| fields | object | no | bill-pay / payout recipient fields the offer lists in requiredFields (account_number, bank_code, full_name, vpa, iban…) |
| sender | object | no | payouts only: the principal (legal name + country); reference = partner KYC id, required above $100/day |
| payer | string | no | the Algorand address you will pay from (required for payout compliance when this server holds no wallet) |
| ref | string | no | referrer's Algorand address — earns a share of margin if the order is delivered (GET /v1/referrals) |
Create a checkout link a HUMAN pays from their own Algorand wallet (Pera). Use this when you have no wallet, or when the person should approve and pay themselves: they open the link, see the exact price, sign in their wallet, and the result (the eSIM QR code, or the top-up confirmation) appears on the page. You never hold a key. A top-up link can be paid by anyone — send it to family as 'top up my
| Parameter | Type | Required | Notes |
|---|---|---|---|
| type | string | yes | — |
| offerId | string | yes | — |
| phone | string | no | topup only: recipient phone, E.164 |
| amount | number | no | for range top-up offers: amount in local currency |
| note | string | no | shown on the link page, e.g. 'Your Tokyo trip data' |
| ref | string | no | your Algorand address, to earn referral share |
| max_uses | integer | no | 0 = reusable until expiry; default 1 for topup, 0 for esim |
| ttl_hours | integer | no | default 168 (7 days) |
Get the x402 payment challenge for a quote. This hosted server holds no wallet, so it does NOT spend your money: it returns the exact amount, asset, payTo address and facilitator for you to pay from your own Algorand wallet, then you POST the quote again with your payment signature. Requires prior human confirmation of the quote.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| quoteId | string | yes | — |
Check an order. Poll every ~3 s until terminal is true: delivered (confirmation + signed receipt), refunded (refund txid + signed receipt) or refund_failed.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| orderId | string | yes | — |
Verify an ed25519-signed receipt: the signature, and — unless you pass onChain:false — both txids against an Algorand indexer. Give it an orderId to check one of this service's own orders, or a receipt object to check ANY receipt in this format, including one issued by another server.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| orderId | string | no | an order on this service |
| receipt | no | a receipt {payload, signature}, or an order response containing one | |
| onChain | boolean | no | confirm the txids on chain; default true |
Indicative USDC → local-currency rate at our sale price, with an estimate for an amount. The quote is the binding price.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| to | string | yes | ISO-4217, e.g. INR |
| amount | number | no | — |
| type | string | no | what the rate is for; default payout |
Public delivery ledger: totals, delivered-or-refunded %, volume, countries, recent orders.
No parameter schema on file.
- Every tool — any call limit is its publisher’s, not ours
- No card, and mcprush charges nothing for it
- Runs at its publisher’s own address — this marketplace is not in the path
- 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 Topup 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 | minimal | capability blast radius (minimal) — client exposure if the model is manipulated | −0 |
| coverage-honesty | manifest | inspection depth (manifest) — how much of the target the scan could see | −4 |
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.
The scan read each tool’s name, description, input schema and annotations exactly as the server listed them the last time it answered us; no code was reviewed. We ask the server again about once a month, and a list that changed is graded again.
The implementation source was not read — this reflects the declared tool metadata only.
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. minimal is the level these add up to.
| Tool | Capability tags | Why the tag was assigned |
|---|---|---|
| lookup_phone | no tags | |
| list_offers | untrusted-input | untrusted-input: keyword "browse" |
| quote | no tags | |
| create_pay_link | no tags | |
| buy | no tags | |
| order_status | no tags | |
| verify_receipt | no tags | |
| fx | no tags | |
| ledger | 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.
The public result for this release does not print the flow graph, so there is nothing to show here. That is not the same as "no paths were found": what the scan did read is above, under coverage.
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
This is an address its publisher runs: which release it serves is theirs to choose, so there is nothing here to pin. The history below is for reading; the current release on file is 0.2.8.
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 Topup 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.