How to Use the AfterShip MCP in Pydantic AI

Q: What's the right way to create a tracking entry with AfterShip and Pydantic AI if I don't know the courier?

The best practice is a two-step agent task. First, call detectcourier with the tracking number. Then, use the validated courier slug from that response to call createtracking.

Q: How do I update an existing shipment with AfterShip and Pydantic AI?

Your agent should use the updatetracking tool. It lets you modify fields like the title or customer contact details. Pydantic AI will ensure the data you send and receive matches the expected format.

Add type-safe, validated shipment tracking to your Pydantic AI agent. Get predictable AfterShip data structures in every response.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect AfterShip MCP to Pydantic AI

Create your Vinkius account to connect AfterShip 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 AfterShip with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Get Type-Safe Tracking Data, Every Time

When your agent calls `get_tracking`, Pydantic AI automatically validates the response against a Pydantic model. If the API ever returns an unexpected field or data type, your code will raise a `ValidationError` immediately. No silent data corruption. This works for every tool. Whether you're using `list_trackings` to get a list of shipments or `detect_courier` to get a list of carriers, you can trust the data structure your agent receives. It's either correct, or it fails.

Build Correct-by-Construction Agents

This MCP server exposes tools that fit neatly into reliable workflows. You can build an agent that first calls `detect_courier`, then uses the validated output to safely call `create_tracking`, knowing the courier slug is correct. You can also manage the lifecycle of a tracking entry with confidence. Your agent can use `update_tracking` to add a customer email for notifications, or `mark_tracking_completed` once delivery is confirmed, and Pydantic AI ensures the calls and responses stick to the schema.

A Model-Agnostic MCP Server for Logistics

Pydantic AI lets you swap LLMs—from OpenAI to a local model—without changing your tool code. This AfterShip MCP server works the same way regardless of the model you choose. The setup is simple. You just point the `MCPToolset` to your Vinkius URL. Pydantic AI handles the tool discovery and runtime validation, so you can focus on the agent's logic, not on parsing API responses.

Setup guide

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

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

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

Pydantic AI generates Pydantic models from the MCP server's schema. When your agent gets a response from a tool like `get_tracking`, it parses the JSON and validates it against the model. If there's any mismatch, it throws an error.

Yes. Pydantic AI is model-agnostic, and so is the Vinkius MCP server. As long as your Pydantic AI agent is configured with a local model, it can call the AfterShip tools just like it would with a cloud-based one.

The best practice is a two-step agent task. First, call `detect_courier` with the tracking number. Then, use the validated courier slug from that response to call `create_tracking`.

Your agent should use the `update_tracking` tool. It lets you modify fields like the title or customer contact details. Pydantic AI will ensure the data you send and receive matches the expected format.

The server only handles data related to your shipments: tracking numbers, courier names, order IDs, and optional customer contact information. Vinkius runs each MCP server in an ephemeral, sandboxed environment. Your connection is authenticated with a single token, keeping your data isolated.

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