Skip to main content
Glama

FiatDock

by com.fiatdock

Create on-ramp session (fiat → USDC)

create_onramp_session

Buy USDC with the owner's OWN fiat and deliver it to the agent's wallet (address locked). Returns checkoutUrl + partnerOrderId. Paid endpoint ($0.01 USDC via x402) — without payment this returns the 402 challenge; use the fiatdock-mcp npm package with AGENT_PRIVATE_KEY for automatic payment. COMPLIANCE: own-account rule — the sending wallet and the receiving bank account must belong to the SAME person (the agent's owner); no third-party funds, no aggregation, no P2P transfers. 18+; served worldwide via our licensed provider across ~160 countries — EUR bank transfer in the SEPA zone (incl. Portugal), card/Apple Pay/Google Pay elsewhere — excluding US persons, sanctioned countries and the UK (NOT the UK). Crypto is volatile; not investment advice.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
refNoOptional referral code (1-64 chars: letters, digits, _ or -)
emailNoOwner's account email. If provided, the checkout link is ALSO emailed to this address automatically (you still receive it in checkoutUrl); the response echoes emailedTo to confirm
networkNoUSDC network, default base
paymentNoBase64 of a single x402 v2 PaymentPayload (EIP-3009 transferWithAuthorization on Base USDC). OMIT it on the first call: the 402 you get back carries `howToPay.payloadTemplate` — the exact envelope to fill in — plus the price and the EIP-712 domain. Send it on the second call to complete the purchase; it is forwarded as the PAYMENT-SIGNATURE header, never as body data. Nothing is charged for the 402 itself, and a call that fails after payment settles nothing.
providerNoLicensed fiat provider. `mtpelerin` is the only provider on this server and the default — omit this field. It settles by SEPA bank transfer across the SEPA zone (incl. Portugal); its order status is not push-updated. Any other value returns 400 (no other provider is configured on this server).
customerIdNoStable agent/customer id
fiatAmountYesFiat amount to spend
walletCodeNoOptional Mt Pelerin address lock, part 1: 4-digit code (1000-9999). Requires walletHash
walletHashNoOptional Mt Pelerin address lock, part 2: base64 signature of 'MtPelerin-<code>' by the agent's OWN wallet key (never shared with us). Locks the widget to walletAddress. Requires walletCode
callbackUrlNoOptional public https URL stored for a future provider with status webhooks — the current provider sends none, so no push will arrive and no callback secret is issued. Poll get_order_status instead
fiatCurrencyNoe.g. EUR, default EUR
walletAddressYesAgent wallet that receives USDC (0x…, EIP-55 checked)

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault
noteNoNext-step instructions
providerNoLicensed fiat provider handling this session (e.g. mtpelerin)
emailedToNoPresent when an `email` was supplied and email is configured: the checkout link was also emailed to this address (best-effort)
checkoutUrlYesBranded checkout URL (valid ~2 hours) — forward to the human owner
customerKeyNoReturned ONCE on the first session with a new customerId — store securely
partnerOrderIdYesOrder id — track it with get_order_status
customerKeyNoteNoHow to use customerKey

TDQS

A4.6/5.0
Behavior5/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

The description discloses far beyond what annotations provide: it explains the x402 payment mechanism (returns 402 challenge without payment, use npm package), the two-step completion, the fact that nothing is charged for the 402 itself, no callbacks are sent, order status is not push-updated, and the wallet-locking mechanism (walletCode + walletHash). Annotations only indicate non-read-only and non-idempotent; the description adds all the practical behavior an agent needs. No contradiction with annotations.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is long but every sentence carries unique, high-value information—payment flow, compliance, geography, settlement, locking, and error conditions. It is front-loaded with the core function and returns, then expands into operational details. It is not tautological or redundant; the density is appropriate for the tool's complexity. The length slightly exceeds minimal conciseness but is justified.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a tool with 12 parameters, a two-step payment flow, compliance restrictions, and provider-specific behavior, the description covers every critical aspect: the exact call sequence, the parameters' roles, the settlement method, the geography limits, the output expectations (checkoutUrl + partnerOrderId, echoed emailedTo), and the absence of callbacks. The output schema exists to document return values, so the description need not duplicate it. Nothing an agent needs to call this correctly is missing.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, so the baseline is 3, but the description adds significant meaning beyond the schema: it explains the payment parameter's exact role in the two-step flow ('OMIT it on the first call... Send it on the second call'), the provider parameter's constraint ('Any other value returns 400'), the callbackUrl's non-functionality for the current provider, and the walletCode/walletHash relationship. This goes beyond the schema's field-level descriptions, justifying a 4.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description states a specific action: 'Buy USDC with the owner's OWN fiat and deliver it to the agent's wallet (address locked)' and returns the exact outputs (checkoutUrl + partnerOrderId). It clearly distinguishes from the sibling create_offramp_session by naming the direction (fiat → USDC) and the ownership constraint, so an agent can tell them apart immediately.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description provides extensive usage context including the two-step payment flow (omit payment first, use payment on second call), compliance rules (own-account, 18+, geographies), and settlement details (SEPA, provider choice). It does not explicitly name the alternative tool for the reverse operation, but the purpose and conditions are concrete enough that an agent can infer when to use this vs create_offramp_session. The lack of an explicit 'use create_offramp_session instead' costs one point.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

All FiatDock toolsInspect
Try in Browser
RayrunBuild, deploy, and operate MCP servers without becoming an infrastructure team.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

TDQS

A4/5.0
Disambiguation4/5

Most tools are clearly separated by resource and action, but a few intentional bundles create mild selection overlap: token_report duplicates the data from token_price + token_safety, and address_intel overlaps eth_balance/usdc_balance plus safety. The descriptions explain the trade-offs well, so this is a minor rather than severe issue.

Naming Consistency4/5

Data-query tools follow a solid subject_metric pattern (token_price, usdc_balance, tx_status), while state-changing tools use verb_object (create_onramp_session, call_service). The pattern is readable and mostly consistent, but not a single uniform verb_noun convention throughout, so it falls just short of perfect.

Tool Count4/5

18 tools is above the typical 3-15 well-scoped range, but the server genuinely spans Base chain primitives, token intelligence, fiat ramps, and a marketplace. Each tool has a purpose, and the count is reasonable rather than bloated.

Completeness4/5

Core workflows are covered end-to-end: quote -> create on/off-ramp session -> order status; token price/safety/metadata/report; marketplace search/get/call; chain/tx primitives. Minor gaps exist, such as no order cancellation, no list-all-services endpoint, and no supported-country/method endpoint despite those details living in descriptions.

Resources