Skip to main content
Glama
AllRatesToday MCP Server

AllRatesToday MCP Server

Commercial bank buy/sell board rates

get_bank_rates
Read-only

Retail buy and sell rates a commercial bank displays on its own website (e.g. SBI's TT buying rate, an Emirates NBD or HSBC Hong Kong board), read hourly.

Instructions

Retail buy and sell rates a commercial bank displays on its own website (e.g. SBI's TT buying rate, an Emirates NBD or HSBC Hong Kong board), read hourly. Use for 'what rate does bank X give for USD today?', remittance comparisons between banks in one country, or rules that name a bank's card rate (India Income-tax Rule 115 uses SBI's TT buying rate). These are bank prices, NOT official or mid-market rates: for those use get_official_rates or get_exchange_rate. Give country alone for every covered bank there, or add bank for one board; ccy narrows one bank to a currency and date returns the stored board for a past day. Covers 1,200+ commercial banks in 120+ countries (ae, lk, in, pk, bd, np, vn, id, ph, am, az, ge, kz, tw, jp, kr, hk, cn, au, cz, pl, hu, tr, eg, za, ke, us); codes are listed at https://allratestoday.com/bank-exchange-rate-api/. Requires ALLRATES_API_KEY (the free key works).

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "country": "<country>"
    },
    "name": "get_bank_rates"
  }
}

Input Schema

NameRequiredDescriptionDefault
ccyNoNarrow one bank's board to a single currency, e.g. 'USD'. Needs `bank`.
bankNoBank code within the country, e.g. 'sbi', 'fab', 'hsbchk'. Omit for every covered bank.
dateNoStored board for a past day, YYYY-MM-DD (kept about 400 days). Needs `bank`.
countryYesTwo-letter country code, e.g. 'in', 'ae', 'hk'.

Output Schema

NameRequiredDescriptionDefault
buyNoOne currency: what the bank pays per unit
ccyNo
bankNo
nameNo
sellNoOne currency: what the bank charges per unit
banksNoEvery covered bank (country call)
basisNoWhich board this is, e.g. Telegraphic transfer
ratesNoOne bank: its board
countryYes
quote_ccyYesHome currency every rate is quoted in
disclaimerNo
captured_atNo
snapshot_dateNo
bank_updated_atNoThe bank's own last-updated stamp

Schema Changelog

Changes observed during successful MCP inspections.

  1. Addedv0.8.1

TDQS

A4.4/5.0
Behavior3/5

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

Annotations already declare readOnlyHint and openWorldHint, so the read-only/open-world profile is covered. The description adds genuinely useful operational context the annotations cannot: hourly refresh, ~400 days of retained history, an auth requirement with a friendly note that the free key works, and a coverage list. It stops short of describing response shape or rate-field semantics, but an output schema exists to carry that.

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?

Front-loaded with purpose, then usage, then the tool's limits, then parameters, then coverage — a sensible priority order. The 27-country code list and the URL take a lot of space, though they are actionable (they tell the agent what inputs are valid) rather than pure padding.

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 read-only, open-world lookup with an output schema, everything an agent needs is present: what the numbers mean, how they differ from official rates, freshness, history depth, auth, coverage, and where the bank codes live. No material gap remains.

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; the description earns an extra point by spelling out the composition rules in one sentence ('country alone for every covered bank', 'add bank for one board', ccy narrows one bank, date returns a stored past board) and by giving an example rate type (SBI TT buying) that clarifies what a 'board' contains.

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?

Names a specific verb+resource (reads retail buy/sell board rates a commercial bank publishes) and immediately draws the boundary against siblings: 'These are bank prices, NOT official or mid-market rates: for those use get_official_rates or get_exchange_rate.' An agent can pick this tool without opening any 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?

Gives concrete trigger questions ('what rate does bank X give for USD today?'), two named use cases (remittance comparison, rules naming a bank card rate such as India Rule 115 / SBI TT buying), and explicit alternatives for the case it does not cover. It also states the parameter combinations that select each mode, which is guidance, not just description.

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