How to Use the Highnote MCP in Pydantic AI

Q: What's the setup for using Highnote tools with Pydantic AI?

It's straightforward. You install the pydantic-ai-slimmcp package, then create an MCPToolset instance pointing to your Vinkius URL. Pass that toolset to your Agent, and it's ready to work with all 11 Highnote tools.

Add type-safe financial operations to any Python agent using Highnote and Pydantic AI for guaranteed data correctness.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Highnote MCP to Pydantic AI

Create your Vinkius account to connect Highnote 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 Highnote with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Never Trust, Always Verify API Data

This MCP server gives your agent 11 tools for card management, from `list_card_products` to `get_transaction_details`. Your agent can read account balances, check card statuses, and review spending history. Pydantic AI automatically creates and validates a data model for every single response. If the Highnote API ever returns an unexpected null value or a string instead of an integer for a transaction, your agent will raise a `ValidationError`. No more silent data corruption.

Build Model-Agnostic Financial Agents

Use Highnote's tools to build reliable financial assistants. Your agent can find the right user with `list_account_holders`, check their account balance with `get_financial_account`, and see all their cards with `list_payment_cards`. Because Pydantic AI just handles the tool-use layer, you can swap the underlying LLM at any time. Point it at OpenAI, Gemini, or a local model running on your machine. Your Highnote integration code doesn't change because the Pydantic models provide a consistent interface.

Interact with Highnote like a Python Object

The framework turns messy API calls into clean, predictable function calls. Your agent's code won't be building HTTP requests; it will just call `update_card_status(card_id='...', status='FROZEN')` and get a validated Pydantic object back. This makes your agent's logic much easier to write, test, and debug. You're not parsing raw JSON from the Highnote MCP; you're working with typed Python objects that represent real-world cards, accounts, and transactions.

Setup guide

Set up Highnote 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": {
        "highnote-mcp": {
            "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
        }
    }
})

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

result = await agent.run("List recent Highnote 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 Highnote. 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 Highnote 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 Highnote MCP in Pydantic AI

Pydantic AI automatically generates a Pydantic model for the expected output of each Highnote tool. After the API call, it parses the response into that model. If the data doesn't match the model's types and structure, it fails loudly with an error.

Yes. Pydantic AI is model-agnostic. You can configure it to use any compatible LLM, including models running locally with frameworks like Ollama or llama.cpp, to drive the Highnote tools.

It's straightforward. You install the `pydantic-ai-slim[mcp]` package, then create an `MCPToolset` instance pointing to your Vinkius URL. Pass that toolset to your `Agent`, and it's ready to work with all 11 Highnote tools.

Pydantic AI surfaces errors clearly. If it's a data mismatch, you'll get a `ValidationError`. If the Highnote API itself returns an error, the exception will be propagated so you can handle it with standard Python `try...except` blocks.

Security has multiple layers. The Vinkius platform provides an authenticated, encrypted channel to the Highnote API. Pydantic AI adds another layer of security by ensuring that malformed transaction or ledger entry data can't be processed by your agent, preventing bugs caused by unexpected API responses.

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