Wise MCP Server

Start a batch of payments

create_batch

Starts a Wise batch to group several unpaid transfers from one currency; add payments by batch ID and close the batch when all are included—no money is sent.

Instructions

Start a batch: several payments from one currency, set up one by one with create_transfer and its batch_id, then paid together in Wise. Nothing is sent. Close it with update_batch when every payment is in.

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": {
      "name": "<name>",
      "source_currency": "<source_currency>"
    },
    "name": "create_batch"
  }
}

Input Schema

Name	Required	Description
`name`	Yes	A name, such as 'Invoices week 45'.
`profile`	No	The Wise profile id to act for. Defaults to WISE_PROFILE_ID, else the only business profile. See list_profiles.
`source_currency`	Yes	The currency every payment is paid from.

Schema Changelog

Changes observed during successful MCP inspections.

First observedv1.2.0Nov 7, 2026

TDQS

A4.2/5.0

Behavior4/5

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

The annotations declare it is a non-read-only, non-idempotent, open-world write, and the description adds the crucial behavioral fact those annotations cannot convey: "Nothing is sent" until the batch is closed, and funds move only when the batch is paid together in Wise. It does not mention permissions, profile requirements, or whether a batch can be abandoned.

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?

Two tight sentences: the first defines the resource and its workflow, the second delivers the safety-relevant caveat up front. No filler and no repetition of the title.

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 workflow-initiating tool with no output schema, the description covers initiation and closure well. It never states that the response yields a batch identifier needed by create_transfer, though the phrase "its batch_id" hints at it.

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

Parameters3/5

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

Schema description coverage is 100%, so name, source_currency, and profile are already documented in the schema. The description adds only the constraint that all payments share one source currency, which reinforces but does not extend the schema's meaning. Baseline 3 applies.

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 verb and resource ("Start a batch") and immediately defines what a batch is: "several payments from one currency" that are "paid together in Wise." This clearly separates it from create_transfer, which the description positions as the per-payment step rather than the container.

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 lays out the full usage sequence — call this first, add payments via create_transfer with the batch_id, then close with update_batch — which tells an agent exactly where this tool sits in the workflow. It stops short of an explicit exclusion (e.g., "for a single payment, use create_transfer directly"), leaving that to inference.

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