How to Use the Duoplane MCP in Pydantic AI

Q: Why should I use Pydantic AI with Duoplane instead of a standard client?

It gives you strict runtime validation for tools like listactivevendors. If the API returns unexpected data, your agent stops executing immediately instead of operating on bad assumptions.

Q: How do I initialize the Duoplane MCP Server in Pydantic AI?

You use the unified MCPToolset constructor with the streamable HTTP endpoint provided by Vinkius. Once registered, you pass the toolset to your Agent, making endpoints like searchordersbyreference active.

Q: Can I use this setup to audit my vendor profiles safely?

Yes, the getvendorprofile tool fetches detailed partner configurations. Pydantic AI parses this data against your internal vendor models to ensure all contact and shipping fields are present and valid.

Run type-safe multi-vendor operations with Pydantic AI validating every Duoplane order and inventory payload at runtime.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Duoplane MCP to Pydantic AI

Create your Vinkius account to connect Duoplane 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 Duoplane with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Pydantic AI Type-Safe Ingestion

The `get_order_details` tool returns structured customer order data that Pydantic AI validates against your strict Python models. If a vendor drops a field or sends an invalid address format, the runtime catches it immediately. This validation happens before your agent attempts to process the transaction, avoiding silent database corruption. Your agent can also use `list_ecommerce_orders` to safely batch-verify incoming orders over this MCP link without risking type mismatches.

Strict Supplier Inventory Verification

The `quick_vendor_inventory_audit` tool delivers high-level stock summaries directly to your validation pipelines. Pydantic AI ensures that product counts, SKU strings, and vendor IDs conform to your exact schemas. When auditing stock across channels, the agent runs `list_synced_products` to verify that active listings match supplier records. If a vendor sends a malformed catalog payload, the system fails loudly so you can fix it.

Fail-Safe Purchase Order Audits

The `get_purchase_order_details` tool provides the precise structure of any outstanding PO sent to your dropship partners via this MCP Server. Because Pydantic AI enforces type safety, your agents will never process a purchase order with missing price fields. To check for delays, the agent calls `list_unfulfilled_purchase_orders` to get a list of pending shipments. The system validates each PO payload, ensuring your inventory reports remain 100% accurate.

Setup guide

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

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

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

It gives you strict runtime validation for tools like `list_active_vendors`. If the API returns unexpected data, your agent stops executing immediately instead of operating on bad assumptions.

You use the unified `MCPToolset` constructor with the streamable HTTP endpoint provided by Vinkius. Once registered, you pass the toolset to your Agent, making endpoints like `search_orders_by_reference` active.

If your Pydantic model requires that field, the agent raises a validation error during the `get_purchase_order_details` call. This prevents your agent from sending broken data to other backend systems.

Yes, the `get_vendor_profile` tool fetches detailed partner configurations. Pydantic AI parses this data against your internal vendor models to ensure all contact and shipping fields are present and valid.

The server runs in an isolated V8 sandbox on Vinkius, ensuring your customer records and API tokens remain private. No order data or vendor profiles are cached, keeping your supply chain operations secure.

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