Fee Optimizer MCP

get_fiat_cost

Read-only

Calculate fiat on/off-ramp costs across crypto exchanges, comparing card, bank transfer, and wire fees to identify a cost-effective deposit or withdrawal rail.

Instructions

当用户询问法币入金/出金成本、刷卡买币手续费、银行卡/信用卡充值费用、银行转账(SEPA/ACH/FPS/PIX/电汇 SWIFT/wire)哪个便宜、提现到银行卡实际到账多少时使用。Use when the user asks how much it costs to move fiat money INTO an exchange (deposit/buy crypto with card or bank transfer) or OUT to a bank account (cash out / withdraw fiat). Prices the direct, exchange-operated rails across venues: credit/debit cards (about 1.1% EU at Bybit to 4.5% at KuCoin; most venues have no card cash-out), US ACH (free at OKX and Kraken), EU SEPA (free deposits at OKX/Kraken/Bitget, about EUR 1 withdrawals; Gate charges 0.5%/1%), UK Faster Payments, Brazil PIX, and SWIFT/domestic wire (fixed USD 4-35 withdrawals). For every venue returns each available rail with fee in fiat AND USD, effective percentage, net amount that arrives, ETA and caveats, plus cheapest overall pick and saving vs the most expensive supported venue. Region/residency-aware: pass country so non-resident rails are filtered (SEPA is EU-only, ACH/wire US-only, FPS GB-only, PIX BR-only). Covers ONLY direct rails — third-party gateway quotes (Banxa/Simplex/MoonPay: 1.99%-5.5% at checkout) and zero-fee P2P (cost embedded in the quote spread) are excluded and called out in notes/advice.

Input Schema

TableJSON Schema

Name	Required	Description
`amount`	No	法币金额(按 currency 单位，如 1000 欧元)，默认 1000；与 amountUsd 二选一
`method`	No	只看指定渠道：card=信用卡/借记卡，ach=美国 ACH，sepa=欧洲银行转账，fps=英国快速转账，wire=美国国内电汇，swift=国际电汇，pix=巴西即时支付
`country`	No	ISO 3166-1 alpha-2 居住国(如 US/DE/GB/BR/JP)；同时用于通道地区过滤与交易所合规过滤
`currency`	No	法币种类，默认 USD。EUR→SEPA 通道，GBP→FPS，BRL→PIX，USD→ACH/wire/卡
`language`	No	输出语言：en=英文(默认)，zh=中文。仅影响 advice/warnings/tradeoffs/reasons 等叙述性文字，数值、字段名与错误码不受影响
`amountUsd`	No	以美元计的金额，工具按内置展示汇率换算成所选法币；与 amount 二选一
`direction`	No	资金方向：deposit=入金买币(默认)，withdraw=卖出提现到银行账户
`exchanges`	No	只查询指定交易所(如 ['kraken','okx'])；默认返回全部 9 家(合约比较不含 Coinbase)

Schema Changelog

Changes observed during successful MCP inspections.

First observedv0.47.1Sep 13, 2026

TDQS

A4.7/5.0

Behavior5/5

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

Annotations only mark it read-only/non-open-world; the description goes well beyond by disclosing the per-venue output shape (fee in fiat AND USD, effective %, net amount, ETA, caveats, cheapest pick, savings vs. priciest venue) and the region/residency filtering behavior driven by country. That is real behavioral context an agent cannot get from the annotations.

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

Conciseness3/5

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

Every sentence carries substantive information, but the definition is very long and duplicates its trigger phrasing bilingually (Chinese then English), which adds bulk without new meaning for an English-reading agent. It is front-loaded on usage, so it is adequate rather than efficient.

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?

With no output schema, the description carries the return-value burden and does so fully: it enumerates the fields returned per rail, the comparative picks (cheapest overall, savings vs. most expensive), and the region-awareness behavior. Nothing an agent needs to invoke or interpret it 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 baseline is 3, but the description adds meaning the schema does not: country is not just a locale but a filter that removes non-resident rails (SEPA EU-only, ACH/wire US-only, FPS GB-only, PIX BR-only), and currency determines which rail family applies. Rate detail (1.1%–4.5% cards, free ACH/SEPA deposits, fixed USD 4–35 wires) further grounds expected values.

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?

States a precise verb+resource (price fiat on/off-ramp costs across exchanges) and explicitly delimits scope: only direct, exchange-operated rails, with third-party gateways and P2P called out as excluded. An agent can distinguish it from siblings like get_withdrawal_fees or get_execution_cost without opening the schema.

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

Usage Guidelines5/5

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

Opens with concrete trigger phrases (deposit/buy with card or bank, cash out/withdraw) and names the conditions that select alternatives by explicitly excluding Banxa/Simplex/MoonPay and P2P routes. When-to-use and when-not-to-use are both stated.

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

get_fiat_cost

Instructions

Input Schema

Schema Changelog

TDQS

Other Tools