Wise MCP Server

Exchange rate

get_rate

Read-onlyIdempotent

Retrieve Wise's mid-market exchange rate between two currencies for now, a past moment, or a grouped history to price conversions before fees.

Instructions

Wise's mid-market rate between two currencies: now, at a moment in the past, or as a history over a period grouped by day, hour or minute. The rate Wise converts at, before its fee.

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": {
      "source": "<source>",
      "target": "<target>"
    },
    "name": "get_rate"
  }
}

Input Schema

Name	Required	Description
`at`	No	A past moment, such as 2026-10-01T12:00:00.
`to`	No	History end.
`from`	No	History start, such as 2026-10-01.
`group`	No	History interval. Defaults to day when from is given.
`source`	Yes	From, such as EUR.
`target`	Yes	To, such as SEK.

Schema Changelog

Changes observed during successful MCP inspections.

First observedv1.2.0Nov 7, 2026

TDQS

A4.1/5.0

Behavior4/5

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

Annotations already establish that this is a read-only, idempotent, non-destructive, open-world operation. The description adds important behavioral meaning by clarifying that the returned rate is Wise's mid-market rate before fees and that historical grouping is supported, though it does not discuss freshness, caching, or response shape.

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

Conciseness5/5

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

The description is two tight sentences with the core resource front-loaded, followed by the fee clarification. There is no redundant restatement of the title or annotations.

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

Completeness4/5

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

For a moderately complex rate tool with six parameters and no output schema, the description covers the important modes and rate meaning well. It could be more complete by explicitly saying what a history response looks like, but the schema and annotations carry most remaining weight.

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 meaningfully maps the parameters to three modes: 'now,' 'at a moment in the past' via at, and history via from/to/group. It still leaves some implicit details, such as exactly how to omit history parameters for a current-rate request.

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

Purpose4/5

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

The description clearly states that this tool returns Wise's mid-market exchange rate between two currencies, including current, historical, and time-series forms. It distinguishes the rate conceptually as 'the rate Wise converts at, before its fee,' but does not explicitly name alternative sibling tools such as compare_prices or create_quote.

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?

It gives clear usage contexts: getting a rate now, at a past moment, or as a history grouped by day, hour, or minute. It does not explicitly state when not to use it or name alternative tools for related tasks, so it stops short of full alternative guidance.

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