How do I get my Wise API token?

You need a **Wise Business account** with 2-Step Verification enabled. Log in at **wise.com**, click your profile icon in the top right corner, then go to **Settings → API tokens → Add new token**. Name your token, complete the 2-Step Verification, and copy it immediately — it is only shown once. Paste it into the configuration below. Note: this feature is only available on the web — not the mobile app.

Can I check how much a transfer will cost before sending money?

Yes. Ask your AI agent to get a quote for any currency pair and amount. It returns the live exchange rate, Wise's fee, the estimated delivery time, and the exact amount the recipient will receive — so you can make informed decisions before committing to a transfer.

What if I need to track a transfer that seems delayed?

Just ask your AI agent 'What's the status of my last transfer?' It returns the current processing stage, estimated delivery date, exchange rate used, and any holds or compliance reviews in progress — all without opening Wise in a browser or switching contexts.

Is this suitable for companies operating in multiple currencies?

Absolutely. Wise supports 50+ currencies, and your AI agent can check balances in all of them simultaneously. Perfect for global e-commerce businesses, international agencies, remote-first companies paying contractors worldwide, and treasury teams managing FX exposure across multiple regions.

Wise MCP Server for Pydantic AI 10 tools — connect in under 2 minutes

Name: Wise
Availability: InStock
Author: Vinkius

ai.pydantic.dev/mcp

Built by Vinkius GDPR 10 Tools SDK

Pydantic AI brings type-safe agent development to Python with first-class MCP support. Connect Wise through the Vinkius and every tool is automatically validated against Pydantic schemas — catch errors at build time, not in production.

Get MCP Server for AI Agents

ASK AI ABOUT THIS MCP SERVER

Open in ChatGPT Open in Claude Open in Perplexity

Vinkius supports streamable HTTP and SSE.

python

import asyncio
from pydantic_ai import Agent
from pydantic_ai.mcp import MCPServerHTTP

async def main():
    # Your Vinkius token — get it at cloud.vinkius.com
    server = MCPServerHTTP(url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp")

    agent = Agent(
        model="openai:gpt-4o",
        mcp_servers=[server],
        system_prompt=(
            "You are an assistant with access to Wise "
            "(10 tools)."
        ),
    )

    result = await agent.run(
        "What tools are available in Wise?"
    )
    print(result.data)

asyncio.run(main())

Fully ManagedVinkius Servers

60%Token savings

High SecurityEnterprise-grade

IAMAccess control

EU AI ActCompliant

DLPData protection

V8 IsolateSandboxed

Ed25519Audit chain

<40msKill switch

Stream every event to Splunk, Datadog, or your own webhook in real-time

* Every MCP server runs on Vinkius-managed infrastructure inside AWS - a purpose-built runtime with per-request V8 isolates, Ed25519 signed audit chains, and sub-40ms cold starts optimized for native MCP execution. See our infrastructure

About Wise MCP Server

Connect your Wise Business account to your AI agent and manage international payments and multi-currency operations conversationally.

Pydantic AI validates every Wise tool response against typed schemas, catching data inconsistencies at build time. Connect 10 tools through the Vinkius and switch between OpenAI, Anthropic, or Gemini without changing your integration code — full type safety, structured output guarantees, and dependency injection for testable agents.

What you can do

Multi-Currency Balances — Check real-time balances across all your currency accounts (USD, EUR, GBP, and 50+ currencies) instantly.
Transfer Tracking — Monitor the status of outgoing transfers, view estimated delivery dates, and check exchange rates applied.
Recipient Management — List, search, and manage your payment recipients across countries and currencies.
Exchange Rates — Get live exchange rates and compare costs before initiating transfers.

The Wise MCP Server exposes 10 tools through the Vinkius. Connect it to Pydantic AI in under two minutes — no API keys to rotate, no infrastructure to provision, no vendor lock-in. Your configuration, your data, your control.

How to Connect Wise to Pydantic AI via MCP

Follow these steps to integrate the Wise MCP Server with Pydantic AI.

Install Pydantic AI

Run pip install pydantic-ai

Replace the token

Replace [YOUR_TOKEN_HERE] with your Vinkius token

Run the agent

Save to agent.py and run: python agent.py

Explore tools

The agent discovers 10 tools from Wise with type-safe schemas

Why Use Pydantic AI with the Wise MCP Server

Pydantic AI provides unique advantages when paired with Wise through the Model Context Protocol.

Full type safety: every MCP tool response is validated against Pydantic models, catching data inconsistencies before they reach your application

Model-agnostic architecture — switch between OpenAI, Anthropic, or Gemini without changing your Wise integration code

Structured output guarantee: Pydantic AI ensures tool results conform to defined schemas, eliminating runtime type errors

Dependency injection system cleanly separates your Wise connection logic from agent behavior for testable, maintainable code

Wise + Pydantic AI Use Cases

Practical scenarios where Pydantic AI combined with the Wise MCP Server delivers measurable value.

Type-safe data pipelines: query Wise with guaranteed response schemas, feeding validated data into downstream processing

API orchestration: chain multiple Wise tool calls with Pydantic validation at each step to ensure data integrity end-to-end

Production monitoring: build validated alert agents that query Wise and output structured, schema-compliant notifications

Testing and QA: use Pydantic AI's dependency injection to mock Wise responses and write comprehensive agent tests

Wise MCP Tools for Pydantic AI (10)

These 10 tools become available when you connect Wise to Pydantic AI via MCP:

create_quote

Create a transfer quote

get_balance

Get specific balance details

get_currencies

List supported currencies

get_exchange_rate

Get live exchange rate

get_transfer

Get transfer details

list_balances

List multi-currency balances

list_profiles

List Wise business profiles

list_recipients

List payment recipients

list_statements

List account statements

list_transfers

List all transfers

Example Prompts for Wise in Pydantic AI

Ready-to-use prompts you can give your Pydantic AI agent to start working with Wise immediately.

"What are my current balances across all currencies?"

"Get me a quote to send €10,000 from my EUR balance to a USD account."

"Track the status of my recent transfer to our London office."

Troubleshooting Wise MCP Server with Pydantic AI

Common issues when connecting Wise to Pydantic AI through the Vinkius, and how to resolve them.

MCPServerHTTP not found

Update: pip install --upgrade pydantic-ai

Wise + Pydantic AI FAQ

Common questions about integrating Wise MCP Server with Pydantic AI.

How does Pydantic AI discover MCP tools?

Create an MCPServerHTTP instance with the server URL. Pydantic AI connects, discovers all tools, and generates typed Python interfaces automatically.

Does Pydantic AI validate MCP tool responses?

Yes. When you define result types as Pydantic models, every tool response is validated against the schema. Invalid data raises a clear error instead of silently corrupting your pipeline.

Can I switch LLM providers without changing MCP code?

Absolutely. Pydantic AI abstracts the model layer — your Wise MCP integration works identically with OpenAI, Anthropic, Google, or any supported provider.