Wise MCP Server

Find a recipient

find_recipient

Read-onlyIdempotent

Find saved Wise recipients by name, currency, or account-ending digits to match a payment request to the right recipient. Searches all saved recipients and returns relevant matches first.

Instructions

Search every saved recipient, not just one page, by name (any order, accents and case ignored), currency, or the last digits of their account. Use it to match a payment request to the recipient to pay. Best matches first.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "find_recipient"
  }
}

Input Schema

Name	Required	Description
`name`	No	All or part of their name, such as 'jane supplier' or 'Müller'.
`profile`	No	The Wise profile id to act for. Defaults to WISE_PROFILE_ID, else the only business profile. See list_profiles.
`currency`	No	Only recipients in this currency, such as EUR.
`account_ending`	No	The last digits of their account number or IBAN, such as 3000.

Schema Changelog

Changes observed during successful MCP inspections.

First observedv1.2.0Nov 7, 2026

TDQS

A4/5.0

Behavior4/5

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

Annotations already declare readOnlyHint, idempotentHint, and destructiveHint=false, so safety is covered. The description adds genuinely new behavior: it searches the entire recipient set rather than a single page, matching is normalized (accents and case ignored, name tokens in any order), and results are ranked with best matches first — all facts 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.

Conciseness5/5

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

Three short sentences, each carrying a distinct payload: scope, use case, matching semantics, and ordering. The search scope is front-loaded and there is no filler or repetition of the title.

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

Completeness3/5

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

There is no output schema, and the description says only that best matches come first — it never indicates what a result contains (recipient id, account summary, match score) or what happens when all four optional parameters are omitted. For a zero-required-parameter search tool, that missing edge-case guidance leaves a real gap.

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 real meaning beyond the schema: name matching ignores order, accents, and case, and the criteria are presented as combinable alternatives ('by name..., currency, or the last digits'). It does not state the combining logic (AND vs OR) or what an empty call returns.

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 opens with a specific verb and resource ('Search every saved recipient') and adds a scope qualifier ('not just one page') that implicitly separates it from the paginated list_recipients and the single-record get_recipient. It never names those siblings explicitly, so the differentiation is inferred rather than stated.

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?

'Use it to match a payment request to the recipient to pay' gives a concrete task-level trigger for selecting this tool over the other recipient tools. It stops short of explicit exclusions (e.g. 'use get_recipient when you already have an id' or 'use list_recipients to browse'), so an agent must still infer when-not to use it.

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