How to Use the Flexport MCP in Pydantic AI

Q: How do I install and configure the Flexport MCP Server with Pydantic AI?

Install using pip install pydantic-ai-slimmcp and initialize MCPToolset with your Vinkius HTTP URL. Pass this toolset directly into your Agent's toolsets parameter.

Q: How does Pydantic AI handle validation failures on Flexport MCP tools?

When a tool like listcommercialinvoices returns data that violates your schema, Pydantic AI raises a validation error. You can catch this error and trigger fallback logic or log it for review.

Q: How does Pydantic AI secure my Flexport shipment details?

Your shipment details retrieved via getshipment are processed entirely in memory within your local Python environment. The framework does not store, log, or share your tracking data with external servers, keeping your supply chain logs strictly confidential.

Build bulletproof Flexport integrations with runtime type validation using Pydantic AI and this 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 Flexport MCP to Pydantic AI

Create your Vinkius account to connect Flexport 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 Flexport with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Enforce strict schemas on Pydantic AI purchase orders

The `create_purchase_order` tool requires precise data matching to prevent pipeline failures. Pydantic AI validates every field against your data models at runtime, blocking malformed orders before they reach the API. If the server returns unexpected fields when calling `get_purchase_order` or `list_purchase_orders`, the framework raises an immediate validation error. This prevents corrupt data from silently polluting your ERP.

Validate freight invoices at runtime

The `get_invoice` tool pulls billing details directly into your type-safe Python applications. Pydantic AI ensures that currency values, line items, and totals match your internal data structures exactly. By running validations on `list_invoices` and `list_shipment_invoices`, you catch billing mismatches immediately. If a carrier applies an unexpected charge format, the system halts execution so you can fix it.

Handle shipping document metadata safely

The `get_document` tool returns structured metadata that must be parsed correctly to download files. Pydantic AI maps this metadata to strict Python classes, making file management predictable and secure. When your agent calls `list_documents` or uses `download_document`, you don't have to worry about missing fields or null values breaking your code. The framework guarantees that every output matches your schema.

Setup guide

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

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

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

Install using pip install pydantic-ai-slim[mcp] and initialize MCPToolset with your Vinkius HTTP URL. Pass this toolset directly into your Agent's toolsets parameter.

Raw API calls can fail silently or return unexpected formats. Pydantic AI forces strict schema validation on this MCP server's tools like list_shipments, ensuring your agent only works with valid data.

Yes, the framework is designed for high-performance async workflows. You can query get_shipment and download files in parallel without blocking your main application loop.

When a tool like list_commercial_invoices returns data that violates your schema, Pydantic AI raises a validation error. You can catch this error and trigger fallback logic or log it for review.

Your shipment details retrieved via get_shipment are processed entirely in memory within your local Python environment. The framework does not store, log, or share your tracking data with external servers, keeping your supply chain logs strictly confidential.

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