How to Use the Shippo MCP in Pydantic AI

Q: Can I use Shippo and Pydantic AI for compliance?

Yes. When listing customs items using listcustomsitems, the returned list adheres to your defined schemas, making it easy for your agent to process legal requirements without errors.

Q: Is tracking status reliable with Shippo and Pydantic AI?

It is highly reliable. By validating the output of trackpackagestatus, your agent always gets a structured response, eliminating guesswork about which fields are present or what data type they use.

Guarantee flawless shipping data validation with Pydantic AI and Shippo MCP Server.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Shippo MCP to Pydantic AI

Create your Vinkius account to connect Shippo 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 Shippo with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Buy labels with guaranteed fields.

When money's involved, you need certainty. Running `purchase_shipping_label` through the Pydantic-AI framework means that every piece of data—from carrier ID to final cost—must match a defined schema. If Shippo sends back anything unexpected, your agent fails LOUDLY. No silent corruption here. You know immediately if the API returned malformed tracking numbers or missing payment confirmations.

Validate every address field.

Before any shipment starts, run `create_and_validate_address`. Pydantic ensures that the resulting address object is type-safe and complete. Your agent can't proceed with rate checking or label purchasing if this validation step fails. This strict enforcement means your deployment environment remains clean and reliable.

Parse tracking status reliably.

Tracking updates are messy, but they don't have to be. When you call `track_package_status`, Pydantic validates the response structure. You get a predictable object every time, regardless of how varied the carrier’s raw data is. This consistency makes writing reliable downstream code much easier.

Setup guide

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

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

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

It uses the MCP Server to deliver tools, but Pydantic-AI wraps the responses. This means that when your agent calls a function like `create_shipment_get_rates`, it's guaranteed to receive data in a predictable Python object format.

Yes. When listing customs items using `list_customs_items`, the returned list adheres to your defined schemas, making it easy for your agent to process legal requirements without errors.

The benefit is correctness. You get runtime validation on every single data point, preventing the agent from acting on hallucinated or malformed API fields, which saves you major headaches.

It is highly reliable. By validating the output of `track_package_status`, your agent always gets a structured response, eliminating guesswork about which fields are present or what data type they use.

It provides raw shipping and logistics data—like carrier manifests (`list_carrier_manifests`) and purchased label records (`list_purchased_labels`). Your framework then forces that data into safe, typed Python objects.

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