How to Use the Altoviz MCP in Pydantic AI

Q: How do I add the Altoviz MCP Server to Pydantic AI?

Install pydantic-ai-slimmcp. Initialize an MCPToolset with your Vinkius HTTP URL and pass it via the toolsets argument to your Agent.

Q: Should I use MCPServerHTTP for Altoviz in Pydantic AI?

No, that approach is deprecated. You must use the unified MCPToolset class which supports both Streamable HTTP and SSE transports.

Build type-safe billing agents that validate Altoviz invoice data strictly 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 Altoviz MCP to Pydantic AI

Create your Vinkius account to connect Altoviz 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 Altoviz with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Type-Safe Altoviz Invoices in Pydantic AI

Financial data requires absolute precision, which is why your agent uses the Altoviz MCP Server to fetch records. When your agent calls `get_sale_invoice_details`, Pydantic AI forces the response to match your predefined Python models. If the MCP Server returns a string where you expected a float for the invoice total, the framework fails loudly. You catch the validation error immediately instead of silently corrupting your database.

Query Customers Across Any LLM

You might prototype with OpenAI but deploy with a local model to query Altoviz data. Pydantic AI keeps your tool logic identical regardless of the underlying LLM. The agent executes `list_customers` to pull your client roster and `get_customer_details` for specific metadata. The exact same code works perfectly whether you run Claude 3.5 Sonnet or Llama 3.

Parse Sale Quotes with Strict Schemas

Extracting pricing details from raw Altoviz text often leads to hallucinated numbers if you don't use strict tools. Your agent calls `list_sale_quotes` to fetch the raw data directly from the source API. It then pulls the exact line items via `get_sale_quote_details`. Because every output routes through a Pydantic schema, you know the final quote amount is a real number, not a generative artifact.

Setup guide

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

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

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

Install `pydantic-ai-slim[mcp]`. Initialize an `MCPToolset` with your Vinkius HTTP URL and pass it via the `toolsets` argument to your Agent.

No, that approach is deprecated. You must use the unified `MCPToolset` class which supports both Streamable HTTP and SSE transports.

The framework throws a strict validation error. Your agent stops execution rather than passing malformed product details downstream.

Yes, the framework is heavily async-native. You can run multiple agents concurrently to fetch receipts and suppliers without blocking the main event loop.

Customer profiles and quote details pass through a strict, ephemeral V8 sandbox. Vinkius handles the authentication layer externally, so the agent only holds a temporary endpoint token.

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