com.marutap/marutap
Description
Agent requests a purchase, the human taps approve, the agent gets a card scoped to it.
What our measurements say
com.marutap/marutap is a remote MCP server published at mcp.marutap.com. It has been probed 6 times since 9/12/2026. It answered in 6 of them (100.0%), a near-uninterrupted record. Median response time is 619 ms, a delay an agent will notice. It offers a narrow, focused set of 6 tools. On the protocol side it speaks the 2026-07-28 stateless spec.
Agent readability score
Can an LLM agent pick the right tool here — names, descriptions and parameter clarity are assessed.
Agent readability score
Strengths
- Tool names like 'request_payment' and 'get_payment_result' clearly indicate their purpose.
- Descriptions for 'request_payment' and 'get_payment_result' provide actionable context for usage.
Weaknesses
- Parameter 'line_items' in 'request_payment' has a null type with no clarification on expected format.
- Descriptions for 'list_subscriptions' and 'record_order' are vague about specific use cases.
- Optional parameters (e.g., 'wait_seconds') are not explicitly marked as optional in the schema.
request_payment— Parameter 'line_items' has a null type with no format clarification.request_subscription— Parameter 'interval' lacks constraints on valid values (e.g., 'monthly' vs. 'yearly').list_subscriptions— Description does not explain when or why this tool should be used.
Verdict
Event narrative
Risk: low
Advice
Schema compliance
tools/list structure, inputSchema validity, and a functional smoke test — the components of the 0-100 score.
- tools/list schema valid
- inputSchema is valid JSON Schema
- Smoke test not run this round
- Cold-start: cold 203ms → warm 196ms (penalty 7ms)
Tools
Tools the server advertised in the latest measurement — measured, not catalog-claimed.
request_paymentRequest 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".
amountnumberrequiredmerchantstringrequiredline_itemscurrencystring
get_payment_resultPoll 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.
charge_idstringrequiredwait_secondsintegeragent_secretstring
record_orderReport 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).
charge_idstringrequiredorder_refstringrequired
request_subscriptionSet 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".
merchantstringrequiredcapnumberrequiredintervalstring
list_subscriptionsList the user's subscription mandates and their status.
cancel_subscriptionCancel a subscription mandate. Safe — canceling never spends money, and the merchant can never charge again afterwards.
mandate_idstringrequired
Availability history
Event log
Derived by comparing consecutive probes — changes in era, protocol version, build and reachability.
- Added to watch — era: Dual-era
Get your badge
Add this badge to your README — it updates automatically as measurements change.
[](https://mcpmetrics.io/servers/com-marutap-marutap)<a href="https://mcpmetrics.io/servers/com-marutap-marutap"><img src="https://mcpmetrics.io/badge/com.marutap/marutap/era.svg" alt="mcpmetrics"></a>You are seeing the last 7 days. Sign up for the full history. Which check failed and why is in the dashboard.
Sign up free to seeSimilar MCP servers
The catalog entries whose name and description are closest to this one, found with the same index the search box uses.
- Agent Discovery Doctor - llms.txt, agent card, mcp.jsonwww.pathwren.workers.dev
{"jsonrpc":"2.0","id":1,"method":"tools/call","params":{"name":"whoami","arguments":{}}} free no key
- Invoke — hire a human from your AI agent (first post free)invoke.nanocorp.app
Let your AI agent hire a human for tasks it can't do — first post free.
- No-Shell Agent Architect MCPai-automation-operating-pack.vercel.app
Turns vague automation requests into tool stacks, prompts, QA checks, and human boundaries.
- agent-2-agent-mcpagent-2-agent.com
Model Context Protocol (MCP) server for the Agent-2-Agent Commerce Network (A2A), enabling autonomous trading agents to query product directories and submit buying requests.
- Rooster Agent Switchboardroosteragents.ai
Register as an AI agent, read signed human bulletins, and message a real human.
- agent-cold-emailapi.coldrig.dev
Agent-operated cold email infrastructure: domains, mailboxes, warmup, campaigns, replies over MCP. 17 tenant-scoped tools.
Comments
Sign in to write a comment
No comments yet. Be the first.