Comprehensive Model Context Protocol server for managing Home Assistant through AI assistants.
Nothing to run from here
Mono eSIM — Travel Connectivity for AI Agents 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.
93/100
tool-list score
21
tools declared
remote
at its publisher
—
calls last 7d
What it does
Search travel eSIM plans, check devices, and create secure customer-paid checkout links.
Quickstart
# 1 — add it to Claude Code
claude mcp add --scope user --transport http mono-esim-travel-connectivity-for-ai-agents-mcp https://www.monoesim.app/mcp
# 2 — ask your agent for something these tools do
# card_payment_terms, create_card_authorization, sync_card_authorization and 18 more
Mono eSIM — Travel Connectivity for AI Agents costs nothing on mcprush: there is no plan to choose here, no cap to set and nothing mcprush can bill you for.
Publishernot claimed
ATAll 1 server
andrii-tiurin1 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. 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.
Claude Codedeclared by this listing
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 mono-esim-travel-connectivity-for-ai-agents-mcp https://www.monoesim.app/mcpReconnect, or start a new session, and the tools appear in the model’s tool list.
Free on mcprush, and it answers at its publisher’s own address: this marketplace is not in the path, so there is no key of ours to hold and no card to add.
What it writes
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.
What you approve
21 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 the currently required consent version and conditions before create_card_authorization. Use this to explain future off-session card charges and spending authority; it never creates a card setup or charges money.
No parameter schema on file.
Create an offline-sandbox Stripe SetupIntent tied to this authenticated machine after explicit saved-card consent. Call card_payment_terms first, then complete the returned client_secret with Stripe.js and call sync_card_authorization; this call stores consent and limits but does not charge the card. Reuse idempotency_key on retries and never send PAN/CVC to this tool.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| payment_authorized | boolean | yes | — |
| consent_version | string | yes | — |
| per_purchase_cents | integer | yes | — |
| per_day_cents | integer | yes | — |
| valid_days | integer | no | — |
| idempotency_key | string | no | — |
After completing a Stripe SetupIntent with Stripe.js, reconcile the authenticated machine's saved-card authorization with Stripe. Use the authorization_id returned by create_card_authorization; this may activate the permission only after successful setup and ownership checks, and never charges a card. Do not use it to initiate setup (create_card_authorization) or reconcile an order payment (sync_c
| Parameter | Type | Required | Notes |
|---|---|---|---|
| authorization_id | string | yes | Saved-card permission ID from create_card_authorization for this machine. |
Revoke an authenticated machine's own saved-card spending permission by authorization_id. This blocks NEW purchases against that permission, but already reserved or in-flight payments may still settle and need reconciliation. This action does not delete the Stripe customer or refund prior charges.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| authorization_id | string | yes | — |
Reconcile a saved-card purchase by the order_id returned from purchase with payment_method=stripe_off_session. For this machine's order, check Stripe PaymentIntent ownership and status; the operation can resume an idempotent pending charge, complete verified fulfilment, or return a required Stripe.js/3-D Secure action. Do not retry with a new order or bypass bank authentication; use get_order to r
| Parameter | Type | Required | Notes |
|---|---|---|---|
| order_id | string | yes | Order ID returned by the machine's stripe_off_session purchase. |
Create a NEW offline-sandbox machine identity with a zero-EUR test wallet and one-time API key; no email or human account is required. Use before get_wallet, fund_wallet, set_wallet_limits, or sandbox purchases; securely store the returned mak_test_ key, which cannot be retrieved again. This does not create a live payment account.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| name | string | yes | Non-secret machine label used for audit trails (1–80 characters). |
Read the authenticated sandbox machine's own EUR-cent balance, spending limits, and latest ledger entries. Returns at most 100 ledger entries per call; pass offset=100, 200, ... to paginate when next_offset is present. Use fund_wallet to create a test funding checkout and set_wallet_limits to change limits; this read does neither.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| offset | integer | no | Zero-based ledger offset; use next_offset to fetch the next 100 entries. |
Change this authenticated sandbox machine's gross spending limits in integer EUR cents per purchase and per UTC day. Zero blocks future spending; refunds do not restore the consumed daily limit. Use get_wallet to inspect current limits first; this does not authorize another person's card or make a purchase.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| per_purchase_cents | integer | yes | — |
| per_day_cents | integer | yes | — |
Create or retrieve an offline-sandbox Stripe TEST Checkout session for funding this authenticated machine's test wallet. amount_cents is integer EUR cents (100 = EUR 1.00); the balance changes only after verified test payment, not after opening the checkout link. Reuse idempotency_key for retries; no real money is accepted.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| amount_cents | integer | yes | — |
| idempotency_key | string | no | — |
Permanently disable the authenticated sandbox machine's current API key, preventing subsequent wallet and purchase requests with that key. The transaction and ledger history remain; this does not cash out, refund, or transfer wallet funds. Use only when decommissioning or securing the machine, not when merely changing spending limits.
No parameter schema on file.
Read the payment-method capability matrix BEFORE invoking purchase. Each method reports enabled versus planned status, environment (live/sandbox/offline_sandbox), required customer interaction, supported buyer modes, and any unavailable reason. This is discovery only: listing a planned method does not mean it can charge, and autonomous payments must not fall back silently to human Stripe Checkout.
No parameter schema on file.
Attempt a purchase for a quote_id from prepare_order using an explicitly selected buyer_mode and payment_method supported by payment_capabilities. stripe_checkout requires human/delegated confirmation, accepted terms, customer email and a customer-paid Stripe link; agent_wallet and stripe_off_session are available only when their offline-sandbox capabilities are enabled and the machine has the nec
| Parameter | Type | Required | Notes |
|---|---|---|---|
| authorization_id | string | no | Required for stripe_off_session; from create_card_authorization. |
| quote_id | string | yes | — |
| buyer_mode | string | yes | — |
| payment_method | string | yes | — |
| string | no | — | |
| customer_confirmed | boolean | no | — |
| terms_accepted | boolean | no | — |
| idempotency_key | string | no | — |
| lang | string | no | Language for names and texts (default en). |
List currently offered travel eSIM destinations (countries and multi-country regions) with their localized names, identifiers and starting EUR prices. Use when the travel destination is unknown or to discover valid destinations before search_plans; filter type=country or type=region, or omit it for both. Results are informational only and do not reserve inventory or prices.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| type | string | no | Filter by type. |
| lang | string | no | Language for names and texts (default en). |
Find available travel data eSIM plans for a country, city, region, or ISO-2 destination such as 'Japan', 'Tokyo', 'Europe', or 'TR'. Filter by minimum validity (days), minimum data (data_gb), unlimited-only, maximum EUR budget and sort order; returns matching plans, price/validity details and a cheapest-match recommendation, without reserving stock. Use get_plan to validate a selected plan before
| Parameter | Type | Required | Notes |
|---|---|---|---|
| destination | string | yes | Country, city, region or ISO-2 code. |
| days | integer | no | Minimum validity in days (trip length). |
| data_gb | number | no | Minimum data in GB. |
| unlimited | boolean | no | Only unlimited (true) or only fixed-data (false) plans. |
| max_price_eur | number | no | Maximum price in EUR. |
| sort | string | no | — |
| limit | integer | no | — |
| lang | string | no | Language for names and texts (default en). |
Retrieve one current eSIM plan by plan_id (from search_plans), including EUR price, coverage destination, data allowance, validity, availability, and purchase terms. Use this to confirm an offer before prepare_order; optional destination must be the exact destination slug to narrow lookup, not a free-text city. A missing or withdrawn plan returns not_found; search_plans again instead of relying on
| Parameter | Type | Required | Notes |
|---|---|---|---|
| plan_id | string | yes | Exact current plan ID from search_plans, not a plan name. |
| destination | string | no | Optional destination slug (faster). |
| lang | string | no | Language for names and texts (default en). |
Compare 2–10 existing eSIM plan IDs returned by search_plans or get_plan. Returns each matching plan plus the IDs of the cheapest plan, lowest EUR price per GB where calculable, and longest validity; an unknown plan ID is flagged not_found rather than silently replaced. Use for an explicit shortlist, not as the initial destination search; this makes no reservation or purchase.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| plan_ids | array | yes | Two to ten exact plan IDs from search_plans; unknown IDs are reported as not_found. |
| lang | string | no | Language for names and texts (default en). |
Look up a phone model's probable eSIM compatibility by model name (for example 'iPhone 12 mini' or 'Galaxy S21'), using a device list and optional supplier check. Returns supported=true/false/null, close model matches and caveats; null means unknown, not incompatible. Always advise users to confirm an EID and carrier unlock status, especially for regional variants; this is not a purchase approval.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| model | string | yes | Full commercial phone model such as iPhone 13 or Galaxy S23; include region variant when known. |
Retrieve the latest displayed eSIM purchase terms and legal links in the requested language (en/de/ru/uk), including delivery, validity, refund/withdrawal conditions and payment. Show these to the customer before confirmation and checkout. This is read-only; it neither records agreement nor grants payment authorization.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| lang | string | no | Language for names and texts (default en). |
Prepare a time-limited signed quote for a plan_id selected using search_plans or get_plan. Returns quote_id, current price and customer-confirmation requirements; the quoted price is locked for 30 minutes, but no order, payment, or eSIM is created. Next call create_checkout for customer-paid Stripe Checkout or purchase for an enabled alternate method.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| plan_id | string | yes | — |
| destination | string | no | — |
| lang | string | no | Language for names and texts (default en). |
Create a pending customer-paid Stripe Checkout from a quote_id returned by prepare_order, only after the customer explicitly approved the displayed plan and price and accepted the terms. Requires the customer's email and customer_confirmed=true, terms_accepted=true; returns a checkout URL, NOT a paid eSIM, and fulfilment starts only after verified payment. Reuse one idempotency_key per intended pu
| Parameter | Type | Required | Notes |
|---|---|---|---|
| quote_id | string | yes | From prepare_order. |
| string | yes | Customer email; the eSIM and receipt are sent there. | |
| customer_confirmed | boolean | yes | true only if the customer explicitly confirmed this purchase. |
| terms_accepted | boolean | yes | true only if the customer accepted immediate delivery and the loss of the withdrawal right. |
| idempotency_key | string | no | Unique per purchase (MCP). REST: send the Idempotency-Key header instead. |
| lang | string | no | Language for names and texts (default en). |
Retrieve payment/fulfilment status for exactly one order using its order_id AND private order_token returned during checkout or purchase. After confirmed delivery, the response may include activation code (LPA), QR/install links and available usage data; treat the token and activation information as secrets. This is read-only and never confirms payment by itself; do not share the output publicly.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| order_id | string | yes | — |
| order_token | string | yes | — |
| include_usage | boolean | no | — |
Free
$0 forever
- 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 Mono eSIM — Travel Connectivity for AI Agents 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: —
ATool-list grade · score 93 / 100
Release 0.1.0 · scanned 3 Nov 2026
Graded from the tools this server lists, not from its source code.
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 score93
Findings0 threat · 0 capability
Capabilitymoderate
Coveragemanifest
Verificationnot in this report
Surface digeste352560cd51d286960101f9b29ec22d8f8fb0ab426a6e7e777f193b1cbd5bd85
Score vectorthreat 100 → client 93
| Term | Level | What it prices | Points |
|---|---|---|---|
| capability-exposure | moderate | capability blast radius (moderate) — client exposure if the model is manipulated | −3 |
| coverage-honesty | manifest | inspection depth (manifest) — how much of the target the scan could see | −4 |
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.
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.
Tool surfaceread
Implementation sourcenot available
Package metadatanot available
Live transportnot available
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. moderate is the level these add up to.
| Tool | Capability tags | Why the tag was assigned |
|---|---|---|
| card_payment_terms | no tags | |
| create_card_authorization | external-sink | external-sink: declares readOnlyHint: false, openWorldHint: true |
| sync_card_authorization | external-sink | external-sink: declares readOnlyHint: false, openWorldHint: true |
| revoke_card_authorization | external-sink | external-sink: declares readOnlyHint: false, destructiveHint: true, openWorldHint: true |
| sync_card_payment | external-sink | external-sink: declares readOnlyHint: false, openWorldHint: true |
| register_machine | external-sink | external-sink: declares readOnlyHint: false, openWorldHint: true |
| get_wallet | no tags | |
| set_wallet_limits | external-sink | external-sink: declares readOnlyHint: false, openWorldHint: true |
| fund_wallet | external-sink | external-sink: declares readOnlyHint: false, openWorldHint: true |
| revoke_machine | external-sink | external-sink: declares readOnlyHint: false, destructiveHint: true, openWorldHint: true |
| payment_capabilities | no tags | |
| purchase | external-sink | external-sink: declares readOnlyHint: false, openWorldHint: true |
| list_destinations | no tags | |
| search_plans | no tags | |
| get_plan | no tags | |
| compare_plans | no tags | |
| check_device | no tags | |
| get_terms | no tags | |
| prepare_order | no tags | |
| create_checkout | external-sink | external-sink: declares readOnlyHint: false, openWorldHint: true |
| get_order | 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
Integrityfirst-seen
Surface digeste352560cd51d2869
Scanned2026-11-03
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 0.1.0.
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 Mono eSIM — Travel Connectivity for AI Agents 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.