# com.marutap/marutap

> Agent requests a purchase, the human taps approve, the agent gets a card scoped to it.

- name: com.marutap/marutap
- version: 1.0.0
- connection class: R0 (autonomous)
- trust: 93/100
- quality: 96/100 (strong)
- owner: not claimed
- descriptor: https://api.protogrid.dev/v1/servers/com.marutap%2Fmarutap
- tools: https://api.protogrid.dev/v1/servers/com.marutap%2Fmarutap/tools

**An agent can connect right now, no human step.** Remote endpoint, no authentication, reachable on the last probe.

## Connection (mcpServers)

```json
{
  "mcpServers": {
    "marutap": {
      "type": "http",
      "url": "https://mcp.marutap.com/mcp",
      "headers": {
        "Authorization": "Bearer ${MARUTAP_TOKEN}"
      }
    }
  }
}
```

Placeholders to fill: `${MARUTAP_TOKEN}`.

## Trust

- hygiene: 100
- liveness: 100
- freshness: 85
- provenance: 85
- drivers: +repository +dns-namespace +website +reachable +uptime-100% ~updated-39d-ago
- Derived from observable signals (official registry feed and our own credential-free probes); no code audit performed.

## Quality 96/100 (strong)

### protocol: 88 (weight 25)

- pass `protocol.modern`: supports 2026-07-28 (server/discover)
- pass `protocol.stateless`: answers without a session
- pass `protocol.transport`: streamable HTTP
- warn `protocol.list_ttl`: tools/list declares ttlMs 0, so clients re-fetch it on every use

### authorization: n/a (weight 15)

- n/a `auth.prm`, `auth.as_metadata`, `auth.cimd`: no remote uses OAuth
- n/a `auth.secret_in_url`: no templated URL

### tool hygiene: 100 (weight 30)

- pass `tools.descriptions`: every tool has a description
- pass `tools.description_length`: descriptions are concise
- pass `tools.schemas`: every tool has an object input schema
- pass `tools.annotations`: 7 of 7 tools declare readOnlyHint or destructiveHint
- pass `tools.directory_hints`: every tool declares readOnlyHint, destructiveHint, idempotentHint and openWorldHint
- pass `tools.token_cost`: about 1,374 tokens to load every tool
- pass `tools.api_dump`: tools are not a one-to-one API dump

### stability: 100 (weight 15)

- pass `stability.changes`: no tool changes in 30 days
- pass `stability.rug_pull`: no tool changed its meaning under the same name

### dependencies: n/a (weight 15)

- n/a `deps.known_vulns`, `deps.mcp_sdk_version`, `deps.resolvable`: no npm or PyPI package

- tools: 7, about 1,374 tokens to load them all
- tool set hash: 6745b6278a8099ed35eae6d543261149
- badge: [![protogrid quality](https://protogrid.dev/badge/com.marutap/marutap.svg)](https://protogrid.dev/servers/com.marutap/marutap)
- Checks run on what our credential-free, read-only probes observe; tools are never called and no code audit is performed.

### Tool changes

_No tool definition changes recorded._

## Remotes

- https://mcp.marutap.com/mcp (streamable-http, auth none, reachable true, uptime30d 1)

## Packages

_none_

## Tools (7)

- `cancel_subscription`: Cancel a subscription mandate. Safe — canceling never spends money, and the merchant can
    never charge again afterwards.
- `get_payment_result`: Poll for the outcome of a payment request.

    Long-polls up to wait_seconds. Returns status one of: pending, approved, settled,
    declined, expired, not_found, claim_pending. When approved, includes a single-use
    `card` (number, cvc, exp) locked to this purchase — use it to complete checkout at
    the merchant. If still "pending"/"claim_pending", call again.

    For a claim (charge_id = the "clm_…" poll_id from request_payment): pass the
    agent_secret you received. The first approved result also contains `connect_token` —
    persist it and send it as the Authorization bearer on all future calls.
    
- `list_payment_requests`: List this agent's payment requests and whether each has been approved yet.

    Use this to see the state of every request you've made — not just poll one saved
    charge_id. Each item includes its `status` (pending, approved, settled, declined,
    expired) so you can tell which are still waiting and which the user has acted on.
    For a pending request it also returns the `approval_url` (re-surface it to the user);
    once a request is approved, call get_payment_result(charge_id) to fetch the card.

    Args:
        status: which to return — "open" (default, still-pending only) or "all".
        limit: max requests to return (default 20, capped at 100), newest first.
    
- `list_subscriptions`: List the user's subscription mandates and their status.
- `record_order`: Report the merchant's order reference back after checkout, so the user can later reverse
    (refund) the purchase. `order_ref` is the merchant's payment id (e.g. a Stripe PaymentIntent).
    
- `request_payment`: Request the user's approval to pay for a purchase.

    Usually returns `{auto_approved: false, approval_url}` — show the approval_url to the user
    so they can review the total and approve with one tap, then call get_payment_result.

    If the user's spending policy auto-approves this purchase (e.g. under their cap at an
    allowlisted merchant), it returns `{auto_approved: true, status: "approved", card}` immediately
    — no approval needed, just use the card.

    Args:
        amount: Total to charge, in major units (e.g. 18.50 dollars).
        merchant: Human-readable merchant / store name shown on the approval screen.
        line_items: Optional list of {"name": str, "quantity": int, "amount_cents": int}.
        currency: ISO currency code, default "usd".
    
- `request_subscription`: Set up a recurring subscription mandate (e.g. Netflix at up to $16/month).

    Requires the user's explicit one-time approval — returns an approval_url. The mandate is
    merchant-locked and capped: the merchant can never charge more than `cap` per period, and the
    user can cancel anytime (after which the merchant can never charge again).

    Args:
        merchant: merchant to authorize (e.g. "Netflix").
        cap: max amount per period in major units (e.g. 16.00).
        interval: "weekly" | "monthly" | "yearly".