marutap MCP server
com.marutap/marutapmarutap.comstreamable-httpv1.0.0Scanned
Agent requests a purchase, the human taps approve, the agent gets a card scoped to it.
7 tools: 1 can delete or cancel things, 1 do something that can't be undone, 2 change things and 3 only read.
- Reads private data · 1
- Reads text others write · 2
- Can send data out · 0
- No findings
Tools listed without sign-in. Remote posture
With Anlyon
1 tool here can delete or cancel things and 1 does something that can't be undone. Govern them.
- Anlyon lists the tools and adopts none.
- Each tool you adopt gets approvals and receipts.
- Your agent never holds the key.
A tool your agent calls directly is not routed through Anlyon and is not governed by it. Anlyon Radar only lists and labels, and these labels are the same either way.
What the marutap MCP server can do
The marutap MCP server is published by marutap.com, a domain the MCP Registry verified. It has 7 tools. It can delete or cancel things (1 tool: cancel_subscription), do things that cannot be undone, such as sending, paying or publishing (request_payment) and create or change data (2 tools: record_order and request_subscription). 3 tools only read.
1 tool reads private data (get_payment_result); 2 tools bring in text other people can write (request_payment and request_subscription).
None of the fixed checks matched anything in its tool definitions. That is not a safety guarantee.
Its remote endpoint lists its tools without sign-in.
Last scanned Nov 10, 2026, version 1.0.0.
Tools
Grouped by what each tool does, most consequential first. Open one for its reasons and full description; descriptions are the publisher's own words.
7 tools
Deletes or cancels 1Claude Code: deny
cancel_subscriptionCancel a subscription mandate.No findings
Why it is in this group
- The name "cancel_subscription" says "cancel": a word for removing or ending something.
- The server marks it destructive (destructiveHint: true).
Description, as the server wrote it Cancel a subscription mandate. Safe — canceling never spends money, and the merchant can never charge again afterwards.
Annotations the server declares
- destructiveHint: true
- idempotentHint: true
- openWorldHint: false
- readOnlyHint: false
- title: Cancel subscription
Can't be undone 1Claude Code: ask
request_paymentRequest the user's approval to pay for a purchase.Reads text others writeNo findings
Why it is in this group
- The name "request_payment" says "request": a word for a change.
- The name "request_payment" also says "payment": a word that usually means money moves, which cannot be taken back.
- The input carries an amount (input.amount) and a currency, so it moves money.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it 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".
Annotations the server declares
- destructiveHint: false
- idempotentHint: false
- openWorldHint: true
- readOnlyHint: false
- title: Request payment approval
Changes things 2Claude Code: ask
record_orderReport the merchant's order reference back after checkout, so the user can later reverse (refund) the purchase.No findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
Description, as the server wrote it 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).
Annotations the server declares
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
- readOnlyHint: false
- title: Record merchant order reference
request_subscriptionSet up a recurring subscription mandate (e.g.Reads text others writeNo findings
Why it is in this group
- The name "request_subscription" says "request": a word for a change.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it 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".
Annotations the server declares
- destructiveHint: false
- idempotentHint: false
- openWorldHint: true
- readOnlyHint: false
- title: Request subscription approval
Only reads 3Show 3 read-only tools
get_payment_resultPoll for the outcome of a payment request.Reads private dataNo findings
Why it is in this group
- The name "get_payment_result" says "get": a word for reading.
What it can reach
- private-dataThe input names a secret (input.agent_secret), and the tool reads: it reads secrets.
Description, as the server wrote it 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.
Annotations the server declares
- destructiveHint: false
- idempotentHint: false
- openWorldHint: false
- readOnlyHint: true
- title: Get payment result
list_payment_requestsList this agent's payment requests and whether each has been approved yet.No findings
Why it is in this group
- The name "list_payment_requests" says "list": a word for reading.
Description, as the server wrote it 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.
Annotations the server declares
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
- readOnlyHint: true
- title: List payment requests
list_subscriptionsList the user's subscription mandates and their status.No findings
Why it is in this group
- The name "list_subscriptions" says "list": a word for reading.
Description, as the server wrote it List the user's subscription mandates and their status.
Annotations the server declares
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
- readOnlyHint: true
- title: List subscriptions
This is not a safety rating, and no finding is not a safety guarantee. The groups and findings come from fixed checks of the tool definitions the server returned on the date shown, not from its code or what it does when called. How the checks work.
Exfil surface
Which tools read private data, which read text someone else can write, and which can send data out. One of each is a path a prompt injection can use.
No private-data, untrusted-input, outbound path in this server alone: no tool is tagged outbound.
- Reads private data1
- Reads files, mail, messages, databases, secrets, calendars or repositories.
- Reads text others write2
- Brings in text someone else can write: web pages, inbound email, messages, issues and comments.
- Can send data out0
- Can carry data to people or systems: it sends, posts or publishes, or takes a recipient, channel or URL.
Other servers in the same agent add their own tools to these paths. Audit your whole setup to see them together.
Remote posture
What anyone on the internet sees at the remote endpoint: an anonymous initialize and tools/list, and the public OAuth metadata.
Looked at Nov 20, 2026, 18:42 UTC, unchanged since Oct 22, 2026. No credentials were sent and no tool was called. What is looked at.
- Reachable
- yes
- HTTP status of an anonymous initialize
- 200
- tools/list served without credentials
- yes
- Tools that change things, listed without credentials
- 4
- Protocol version
- 2025-06-18
- WWW-Authenticate on 401
- not observed
- resource_metadata in WWW-Authenticate
- not observed
- RFC 9728 protected resource metadata
- not observed
- Authorization servers
- not observed
- Legacy HTTP+SSE transport
- no
- Dynamic client registration
- not observed
- Client ID metadata documents
- not observed
- HighThe whole server
The endpoint served tools/list without credentials, and the list has 4 tools that change things (1 destructive, 1 irreversible, 2 write). Whether a call also works without credentials was not tested: tools are never called.
What this check looks forMatched text
https://mcp.marutap.com/mcp: tools/list returned 7 tools to an anonymous client, including cancel_subscription (destructive), request_payment (irreversible), record_order (write), request_subscription (write)
Findings
Matches of fixed checks, with the text they matched.
No check matched anything in these tool definitions. That is not a safety guarantee.
History
Changes to its tool definitions and to its remote endpoint, newest first.
No change seen yet. Its tools are rescanned every day, and a remote endpoint is looked at once a week.
Install
Pinned to version 1.0.0. Values in angle brackets are yours to fill in.
claude mcp add --transport http marutap https://mcp.marutap.com/mcpclaude mcp add --transport http marutap https://mcp.marutap.com/mcpRun in a terminal.
Claude Code permissions
Allow the reads, ask before a change or a way out, deny the deletes. Paste into .claude/settings.json.
{
"permissions": {
"allow": [
"mcp__marutap__get_payment_result",
"mcp__marutap__list_payment_requests",
"mcp__marutap__list_subscriptions"
],
"ask": [
"mcp__marutap__request_payment",
"mcp__marutap__record_order",
"mcp__marutap__request_subscription"
],
"deny": [
"mcp__marutap__cancel_subscription"
]
}
}Tools that only read are allowed, tools that change things ask first, tools that delete or cancel are denied. A read that can send data out (it takes a URL, say) asks first too. It assumes the server is installed as marutap. Review it before you use it.
Capability tags behind 3 rules
- mcp__marutap__request_payment untrusted-input
- mcp__marutap__get_payment_result private-data
- mcp__marutap__request_subscription untrusted-input
Pin
Keep the decision: fail CI when the tools change, follow every change, or show a badge.
Pin in CI
Fail a build when the tools you reviewed are not the tools the server serves today.
curl -s "https://radar.anlyon.com/api/v1/servers/com.marutap/marutap/verify?hash=da5450d05f675d23c75addecb68c9abcdc3a07b2932ee03eb4ebbfad42068513" | jq -e '.changed == false'Pinned hash da5450d05f67, from Nov 10, 2026, 20:18 UTC.
Watch
Get told when its tools change: a new tool, a new description, a new class.
https://radar.anlyon.com/servers/com.marutap/marutap/changes.xmlAn Atom feed. Works in any feed reader or Slack's RSS app.
Badge
[](https://radar.anlyon.com/servers/com.marutap/marutap)Source: MCP Registry · repository. Synced Oct 21, 2026, 17:58 UTC.
marutap MCP server: questions and answers
Answered from the scan above, not from the publisher's description.
Is the marutap MCP server safe?
- No scan can promise that. What its definitions show: 7 tools, 4 of which can change, send or delete something, and 0 findings from fixed checks. Allow the reads, ask before each change, and deny the deletes; the permissions block on this page does that.
Can the marutap MCP server delete data?
- Yes. 1 tool can delete, cancel or revoke something: cancel_subscription.
Can the marutap MCP server do things that cannot be undone?
- Yes. 1 tool can send, pay, publish or merge: request_payment.
What tools does the marutap MCP server have?
- 7 tools: 1 destructive, 1 irreversible, 2 write, 3 read. cancel_subscription, request_payment, record_order, request_subscription, get_payment_result, list_payment_requests and list_subscriptions.
Does the marutap MCP server need sign-in or OAuth?
- Its remote endpoint listed its tools to an anonymous client, without sign-in.
Does the marutap MCP server send data to outside services?
- None of its tools sends, posts or publishes, or takes a recipient, channel or URL.
Has the marutap MCP server changed its tools?
- Not since Anlyon Radar started tracking it. Last scanned Nov 10, 2026.