How to Use the Wise MCP in Pydantic AI

Q: What kind of financial operations are possible with Wise using Pydantic AI?

The system lets you check quotes (createquote), list statements (liststatements), and view all transfers. Every output adheres to a strict, predictable schema.

Q: Does the Pydantic AI handle complex multi-currency data from Wise?

Yes. By validating outputs like listbalances, it ensures that even when dealing with multiple currencies and associated fields, every piece of information is correctly typed and accessible.

Ensure perfect data structure for money moves using Pydantic AI.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Wise MCP to Pydantic AI

Create your Vinkius account to connect Wise to Pydantic AI and route execution through our secure gateway. The platform manages server hosting, runtime updates, and security layers. Configuration requires no manual server provisioning.

GDPR Free for Subscribers

Setup Wise with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Guaranteeing Correct Quotes and Rates with MCP Server

Correctness matters here. When you run `get_exchange_rate`, the response will validate against your defined Pydantic schema, so you never get unexpected field names. Similarly, when creating a quote using `create_quote`, the agent is forced to adhere to strict types. This prevents silent data corruption in your production system.

Structured Access to Wise Balances via Pydantic AI

The agent makes sure every piece of balance data returned from `list_balances` matches the expected schema. You'll get clean, reliable Python objects, not messy JSON. This level of type safety is essential when you need to process transaction details using tools like `get_balance`.

Validated Management of Transfers and Recipients

When tracking payments, the agent uses Pydantic validation on every step. If a transfer record from `list_transfers` is missing an expected field, your system fails loudly—you know exactly what's wrong. It also validates recipient data when using `list_recipients`, making sure your agent only works with correctly formatted contact information.

Setup guide

Set up Wise MCP in Pydantic AI

Prerequisites

Python 3.10+ installed
pydantic-ai-slim[fastmcp] package
Active Vinkius subscription with a valid endpoint token

1

Install Pydantic AI with FastMCP
Run pip install "pydantic-ai-slim[fastmcp]". The FastMCP toolset replaces the deprecated MCPServerHTTP class with full protocol support.
2

Configure the FastMCPToolset
Pass a JSON-style config dict to FastMCPToolset with your Vinkius URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. Supports Streamable HTTP, SSE, and Stdio transports.
3

Create and run your agent
Pass the toolset to Agent(toolsets=[toolset]) and call agent.run(). Swap openai:gpt-4o for any supported model — Anthropic, Google, Mistral, or Groq.

agent.py

from pydantic_ai import Agent
from pydantic_ai.toolsets.fastmcp import FastMCPToolset

toolset = FastMCPToolset({
    "mcpServers": {
        "wise-mcp": {
            "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
        }
    }
})

agent = Agent(
    "openai:gpt-4o",
    toolsets=[toolset],
    system_prompt="You have access to Wise tools.",
)

result = await agent.run("List recent Wise transactions")
print(result.output)

Get your connection token →

Independent Platform Disclaimer: Vinkius is an independent platform and is not affiliated with, endorsed by, sponsored by, verified by, or otherwise authorized by Wise. All third-party trademarks, logos, and brand names are the property of their respective owners. Their use on this website is strictly for informational purposes to identify service compatibility and interoperability.

Why Choose Vinkius

Vinkius connects your tools to AI with real-time monitoring and automatic cost savings — all from one dashboard.

Connect Wise now

Real-time monitoring

Live

visibility into every interaction

Connect your favorite tools to your AI and see exactly what's happening — every request, every response, in real time.

Built-in savings

60%

lower AI costs

Vinkius compresses data between your apps and your AI automatically. Lower bills every month — no configuration required.

Single dashboard

One

place for every integration

Every tool your AI connects to, managed from a single screen. One account, complete control.

Common questions about Wise MCP in Pydantic AI

The MCP Server forces all tool responses to conform to Python types you define. This means whether it's a rate or a balance, the data structure is guaranteed before your agent uses it.

You can. The primary benefit of this setup is that if the underlying API returns malformed data, the agent throws a clear validation error—there’s no guessing what went wrong.

The system lets you check quotes (`create_quote`), list statements (`list_statements`), and view all transfers. Every output adheres to a strict, predictable schema.

Yes. By validating outputs like `list_balances`, it ensures that even when dealing with multiple currencies and associated fields, every piece of information is correctly typed and accessible.

This server handles critical financial records, including balances (`list_balances`), transfer logs (`list_transfers`), and account statements (`list_statements`).

Use it with your favorite AI tools

Connect this server to Cursor, Claude, VS Code, and more.

OpenAI Agents SDK sdk-python

Google ADK sdk-python

Pydantic AI sdk-python

Vercel AI SDK sdk-typescript