How to Use the Dutchie POS MCP in Pydantic AI

Q: How do I initialize the Dutchie POS toolset in Pydantic AI?

Install pydantic-ai-slimmcp and use the unified MCP toolset class pointing to your Vinkius HTTP endpoint. Pass this toolset directly to your agent constructor.

Enforce runtime validation on Dutchie POS inventory and order data using Pydantic AI to prevent agent hallucinations.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Dutchie POS MCP to Pydantic AI

Create your Vinkius account to connect Dutchie POS 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 Dutchie POS with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Type-safe retail operations using Pydantic AI

Do not let your agent hallucinate inventory quantities or stock levels. This MCP setup validates every single incoming payload from `list_current_inventory` against strict Python types at runtime. If the API returns a string where a number was expected, your system fails loudly. This prevents corrupt data from polluting your inventory logs or messing up your restock orders.

Bulletproof sales audits with this MCP Server

Run your compliance checks with absolute certainty. By connecting your agent to this MCP Server, you can pull transaction summaries using `quick_pos_sales_audit` and enforce schema validation instantly. Your agent can parse `get_order_details` knowing that every field matches your Pydantic models. It eliminates the risk of silent failures during busy dispensary tax audits.

Model-agnostic catalog management

You are not locked into any single LLM provider for managing your store. Use OpenAI, Anthropic, or local models to run queries like `search_catalog_products` and `get_product_details`. The validation layer sits in your Python code, not the LLM. This means your product catalog data stays structured and accurate, regardless of which model you choose to drive your agent.

Setup guide

Set up Dutchie POS 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": {
        "dutchie-pos-mcp": {
            "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
        }
    }
})

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

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

Install `pydantic-ai-slim[mcp]` and use the unified MCP toolset class pointing to your Vinkius HTTP endpoint. Pass this toolset directly to your agent constructor.

The framework will raise a validation error immediately. This stops the agent from acting on corrupt data when running tools like `list_retail_orders`.

Yes, this setup is completely model-agnostic. You can switch from Claude to GPT-4 without rewriting your validation schemas for `list_retail_products`.

Yes, it supports both Streamable HTTP and SSE transports. You can connect your python environment to the external Vinkius server using either method.

Vinkius routes all customer names and order records through a zero-trust, ephemeral V8 sandbox. No data is stored or logged on the host platform, keeping your retail compliance intact.

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