How to Use the ShipEngine MCP in Pydantic AI

Q: How do I integrate ShipEngine with Pydantic AI?

You pass the toolset to your Agent. The agent calls getshippingrates, and before you use that data, Pydantic validates it against your defined Python models. This guarantees the data structure is correct.

Q: Can I validate addresses with ShipEngine and Pydantic AI?

Absolutely. Use validateaddress. The resulting validated address object will be strongly typed, meaning you can't accidentally treat a ZIP code as a street name in your subsequent logic.

Q: How do I list recent shipments with ShipEngine and Pydantic AI?

The agent calls listshipments, receiving a clean, validated JSON array of records. You can immediately process this data because the tool output is guaranteed to match your defined schema.

Q: What happens if rate comparison fails with ShipEngine and Pydantic AI?

If getshippingrates returns unexpected data, the agent doesn't proceed. It throws a loud validation error immediately, telling you exactly which field broke the expected model schema.

Build reliable Python agents that use ShipEngine with Pydantic AI's validation layer.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect ShipEngine MCP to Pydantic AI

Create your Vinkius account to connect ShipEngine 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 ShipEngine with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Compare rates and get structured output

Need pricing data? Use `get_shipping_rates`. This tool returns raw rate objects, but because you use Pydantic AI, your agent will validate that these results match the expected schema. You won't get corrupted fields. This strong typing means when your agent processes the output, it knows exactly what field contains the cost and which field holds the carrier name.

Generate labels with guaranteed data integrity

When you call `create_shipping_label`, Pydantic AI ensures the resulting label metadata conforms to your models. This prevents issues where an unexpected field might cause a downstream failure. The agent can then use `list_created_labels` and validate that the returned list of labels is complete and correctly formatted.

Manage shipment lifecycle with type safety

Use this toolset to manage the whole process. First, create the record via `create_shipment_object`. Then, use `get_shipment_info` to pull the details back into your Python environment for validation. The agent can reliably track state changes using `track_package`, knowing that every status update it receives is correctly typed.

Setup guide

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

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

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

You pass the toolset to your Agent. The agent calls `get_shipping_rates`, and before you use that data, Pydantic validates it against your defined Python models. This guarantees the data structure is correct.

Absolutely. Use `validate_address`. The resulting validated address object will be strongly typed, meaning you can't accidentally treat a ZIP code as a street name in your subsequent logic.

This server handles physical shipping parameters: addresses (via `validate_address`), dimensions, weights, and carrier-specific rate structures. All outputs are strictly typed.

The agent calls `list_shipments`, receiving a clean, validated JSON array of records. You can immediately process this data because the tool output is guaranteed to match your defined schema.

If `get_shipping_rates` returns unexpected data, the agent doesn't proceed. It throws a loud validation error immediately, telling you exactly which field broke the expected model schema.

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