How to Use the Sellfy MCP in Pydantic AI

Q: How does Pydantic AI connect to the Sellfy MCP server?

It's straightforward. After you pip install "pydantic-ai-slimmcp", you just instantiate an MCPToolset with your Vinkius server URL. Pass that into your agent's toolsets list and you're good to go.

Build rock-solid Sellfy agents. Pydantic AI validates every API response so your data is always correct.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers — Included with Plan

Connect Sellfy MCP to Pydantic AI

Create your Vinkius account to connect Sellfy to Pydantic AI — we handle the hosting, security, and runtime updates so you don't have to. No server setup required.

GDPR Included with Plan

Setup Sellfy with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity Vinkius runs on Gemini

Gemini

Grok

Get Correct Store Data, Every Time

Use this server's tools like `get_order_details` or `list_customers` to pull information from your Sellfy store. Your agent gets access to all the critical data it needs to perform its job. But here's the key with Pydantic AI: every response is automatically validated against a Pydantic model. If the API ever sends back an extra field or the wrong data type, your code will raise a `ValidationError` immediately. It's a guarantee against silent data corruption.

Create Products with Any LLM on Pydantic AI

This MCP server exposes a `create_product` tool, letting your agent add new items to your store. It requires a title and price, and the response confirms the creation. Pydantic AI is model-agnostic, so you can run this with OpenAI, Gemini, or a local model, and your tool-handling code doesn't change. The output is always parsed into the same Pydantic model, giving you predictable, reliable behavior no matter which LLM is driving the agent.

Build Reports You Can Actually Trust

You can build an agent to generate daily sales or inventory reports using `list_orders` and `list_products`. The agent fetches the data and formats it for you. Because Pydantic AI is in the loop, you know the report isn't built on hallucinated data. The framework forces the data to fit a strict schema before your code even sees it. If the data isn't right, it fails loudly. This means your reports are always based on the actual data structures from the API.

Setup guide

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

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

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

It's straightforward. After you `pip install "pydantic-ai-slim[mcp]"`, you just instantiate an `MCPToolset` with your Vinkius server URL. Pass that into your agent's `toolsets` list and you're good to go.

This is exactly what Pydantic AI protects you from. Your agent will raise a `ValidationError` with a clear message showing where the API response differs from your Pydantic model. You'll know immediately, instead of processing bad data.

Yes. Pydantic AI doesn't care which LLM you use. As long as you have a compatible client for your local model, you can use the Sellfy tools without any changes to your tool-handling logic.

The validation errors are your best debugging tool. They provide a precise traceback showing which field in the Sellfy API response didn't match your Pydantic model. It takes the guesswork out of debugging API integrations.

The tools work with your store's product catalog, order records, and customer lists. Vinkius ensures data is handled securely by running the MCP server in a sandboxed environment where data is streamed, not stored. Your Pydantic models also act as a clear declaration of exactly what data your application expects to handle.

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