How to Use the Nabis MCP in Pydantic AI

Q: How do I load the Nabis MCP Server in Pydantic AI?

Install pydantic-ai-slimmcp. Initialize MCPToolset with your HTTP endpoint URL, and pass the resulting toolset array to your Agent constructor.

Q: What happens if Nabis changes its API schema in Pydantic AI?

The agent fails loudly. If a tool like getinvoice returns an unexpected field format, Pydantic throws a ValidationError immediately.

Q: Should I use MCPServerHTTP for Nabis?

No. That class is deprecated. Use the unified MCPToolset class configured for Streamable HTTP or SSE transports.

Q: How does the MCP server protect Nabis order history?

This system processes bulk transaction records from listorders. Because Pydantic AI runs locally, this historical volume data stays entirely within your host environment and never hits third-party logging tools.

Enforce strict runtime validation for Nabis wholesale records 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 Nabis MCP to Pydantic AI

Create your Vinkius account to connect Nabis 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 Nabis with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Validate Nabis MCP Server inventory

The Nabis MCP server feeds exact stock counts into your type-safe Python framework. Your agent runs `list_inventory` and `get_warehouse_count`, parsing the results through strict Pydantic models. Missing fields trigger immediate validation errors. If the API drops a SKU or returns a string instead of an integer for unit counts, the script halts rather than silently corrupting your database.

Parse wholesale orders

Financial integrity requires exact numbers. The system calls `list_orders` to track bulk shipments and pulls specific line items via `get_order` for reconciliation. Invoices get the same rigorous treatment. Agents execute `list_invoices` and `get_invoice` to extract billing totals, guaranteeing that every dollar amount matches your expected schema before generating a report.

Audit retailer networks

Your AI client verifies buyer credentials by running `list_retailers` and extracting specific profiles with `get_retailer`. Every license number and address must pass your defined string constraints. Route planning relies on accurate facility data. The agent checks `list_warehouses` for active locations and confirms operating schedules using `get_days_off` to prevent dispatching trucks on holidays.

Setup guide

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

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

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

Install `pydantic-ai-slim[mcp]`. Initialize `MCPToolset` with your HTTP endpoint URL, and pass the resulting toolset array to your `Agent` constructor.

The agent fails loudly. If a tool like `get_invoice` returns an unexpected field format, Pydantic throws a `ValidationError` immediately.

No. That class is deprecated. Use the unified `MCPToolset` class configured for Streamable HTTP or SSE transports.

Yes. The framework natively supports async execution for tools like `list_warehouses` and `list_orders`, speeding up bulk data retrieval.

This system processes bulk transaction records from `list_orders`. Because Pydantic AI runs locally, this historical volume data stays entirely within your host environment and never hits third-party logging tools.

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