How to Use the Amilia MCP in Pydantic AI

Q: What happens if the Amilia API changes and my Pydantic AI agent isn't updated?

Your agent will stop working and raise a ValidationError on the first call that gets an unexpected response. This is a feature, not a bug. It prevents your application from silently accepting and processing malformed data.

Q: Is it complicated to set up the Amilia MCP server with Pydantic AI?

No, it's a single line of code. You create an MCPToolset with the Vinkius URL and add it to your agent's toolsets list. Pydantic AI handles the tool discovery and response validation from there.

Get validated, type-safe access to your Amilia data in any Python agent with Pydantic AI's runtime guarantees.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Amilia MCP to Pydantic AI

Create your Vinkius account to connect Amilia 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 Amilia with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Manage Accounts with Guaranteed Data Correctness

Let your agent manage family accounts and contacts using `list_accounts` and `get_account_details`. The tools give you direct read-access to your Amilia database. With Pydantic AI, every response from the MCP server is automatically validated against a strict schema. If the Amilia API returns an extra field or an ID as a string instead of an integer, your code will raise a `ValidationError` instantly. No more silent data corruption or defensive `if key in dict` checks.

Build Reliable Program and Registration Lookups

When your agent needs to check on program schedules or registrations, it uses tools like `list_programs` and `list_registrations`. You can build internal dashboards or alerting systems on top of this data with confidence. Pydantic AI's main job is to ensure the data structures your code receives are always what you expect. This means you can build more robust systems faster because you're not spending half your time writing code to handle unexpected API responses.

Create a Model-Agnostic Amilia MCP Server Agent

This MCP server exposes all the tools you need to query your Amilia account, like `get_program_details` and `list_activities`. Pydantic AI lets you build an agent that uses these tools with any LLM you want. You can start with an OpenAI model and switch to a local Llama 3 instance or Anthropic's Claude 3 next week without changing your tool-calling logic. Pydantic AI abstracts the model-specific details, so your agent's connection to Amilia just works, regardless of the brain behind it.

Setup guide

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

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

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

It validates every API response from the Amilia MCP server against a Pydantic model at runtime. If any field is missing, has the wrong data type, or doesn't match the expected structure, your code will fail with a clear validation error instead of processing bad data.

Yes. Pydantic AI is model-agnostic. As long as your local model supports function calling, you can connect it to the Amilia MCP server and get the same type-safe, validated responses.

Your agent will stop working and raise a `ValidationError` on the first call that gets an unexpected response. This is a feature, not a bug. It prevents your application from silently accepting and processing malformed data.

No, it's a single line of code. You create an `MCPToolset` with the Vinkius URL and add it to your agent's `toolsets` list. Pydantic AI handles the tool discovery and response validation from there.

The server-side is secured by Vinkius, which processes requests for your account contacts and registration lists in memory and never writes them to disk. Client-side, Pydantic AI ensures that only data that perfectly matches your predefined schemas can even enter your application's state, protecting you from data structure anomalies.

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