How do I get an AfterShip API Key?

Sign up at [**AfterShip**](https://www.aftership.com/), go to Settings > API Keys, and generate a new key. Free tier includes 100 shipments/month.

How many couriers are supported?

AfterShip supports 1,000+ courier companies worldwide including FedEx, UPS, DHL, USPS, Royal Mail, Canada Post, Australia Post, and many regional carriers.

Can I automatically detect which courier handles my tracking number?

Yes! Use the `detect_courier` tool with just the tracking number. It returns a ranked list of likely courier companies based on the tracking number format.

AfterShip MCP Server for Pydantic AI 9 tools — connect in under 2 minutes

Name: AfterShip
Availability: InStock
Author: Vinkius

ai.pydantic.dev/mcp

Built by Vinkius GDPR 9 Tools SDK

Pydantic AI brings type-safe agent development to Python with first-class MCP support. Connect AfterShip through Vinkius and every tool is automatically validated against Pydantic schemas. catch errors at build time, not in production.

Get MCP Server for AI Agents

ASK AI ABOUT THIS MCP SERVER

Open in ChatGPT Open in Claude Open in Perplexity

Vinkius supports streamable HTTP and SSE.

python

import asyncio
from pydantic_ai import Agent
from pydantic_ai.mcp import MCPServerHTTP

async def main():
    # Your Vinkius token. get it at cloud.vinkius.com
    server = MCPServerHTTP(url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp")

    agent = Agent(
        model="openai:gpt-4o",
        mcp_servers=[server],
        system_prompt=(
            "You are an assistant with access to AfterShip "
            "(9 tools)."
        ),
    )

    result = await agent.run(
        "What tools are available in AfterShip?"
    )
    print(result.data)

asyncio.run(main())

Fully ManagedVinkius Servers

60%Token savings

High SecurityEnterprise-grade

IAMAccess control

EU AI ActCompliant

DLPData protection

V8 IsolateSandboxed

Ed25519Audit chain

<40msKill switch

Stream every event to Splunk, Datadog, or your own webhook in real-time

* Every MCP server runs on Vinkius-managed infrastructure inside AWS - a purpose-built runtime with per-request V8 isolates, Ed25519 signed audit chains, and sub-40ms cold starts optimized for native MCP execution. See our infrastructure

About AfterShip MCP Server

Connect AfterShip tracking platform to any AI agent and track packages from 1,000+ couriers worldwide, auto-detect shipping companies, and manage all your shipments through natural language.

Pydantic AI validates every AfterShip tool response against typed schemas, catching data inconsistencies at build time. Connect 9 tools through Vinkius and switch between OpenAI, Anthropic, or Gemini without changing your integration code. full type safety, structured output guarantees, and dependency injection for testable agents.

What you can do

Package Tracking — Create and monitor shipments from FedEx, UPS, DHL, USPS, and 1,000+ other couriers
Auto-Detect Courier — Automatically identify the shipping company from just a tracking number
Tracking History — View complete delivery history with checkpoint timestamps and locations
Delivery Management — Mark trackings as completed, retrack expired ones, or delete old entries
Customer Notifications — Set up email and SMS notifications for delivery updates
Courier Directory — Browse all supported courier companies with their contact info and requirements

The AfterShip MCP Server exposes 9 tools through the Vinkius. Connect it to Pydantic AI in under two minutes — no API keys to rotate, no infrastructure to provision, no vendor lock-in. Your configuration, your data, your control.

How to Connect AfterShip to Pydantic AI via MCP

Follow these steps to integrate the AfterShip MCP Server with Pydantic AI.

Install Pydantic AI

Run pip install pydantic-ai

Replace the token

Replace [YOUR_TOKEN_HERE] with your Vinkius token

Run the agent

Save to agent.py and run: python agent.py

Explore tools

The agent discovers 9 tools from AfterShip with type-safe schemas

Why Use Pydantic AI with the AfterShip MCP Server

Pydantic AI provides unique advantages when paired with AfterShip through the Model Context Protocol.

Full type safety: every MCP tool response is validated against Pydantic models, catching data inconsistencies before they reach your application

Model-agnostic architecture. switch between OpenAI, Anthropic, or Gemini without changing your AfterShip integration code

Structured output guarantee: Pydantic AI ensures tool results conform to defined schemas, eliminating runtime type errors

Dependency injection system cleanly separates your AfterShip connection logic from agent behavior for testable, maintainable code

AfterShip + Pydantic AI Use Cases

Practical scenarios where Pydantic AI combined with the AfterShip MCP Server delivers measurable value.

Type-safe data pipelines: query AfterShip with guaranteed response schemas, feeding validated data into downstream processing

API orchestration: chain multiple AfterShip tool calls with Pydantic validation at each step to ensure data integrity end-to-end

Production monitoring: build validated alert agents that query AfterShip and output structured, schema-compliant notifications

Testing and QA: use Pydantic AI's dependency injection to mock AfterShip responses and write comprehensive agent tests

AfterShip MCP Tools for Pydantic AI (9)

These 9 tools become available when you connect AfterShip to Pydantic AI via MCP:

create_tracking

Requires at least the tracking number. Optionally specify the courier slug, title, customer emails, SMS phone numbers, order ID, and custom fields. Create a new package tracking

delete_tracking

This action cannot be undone. Delete a tracking entry

detect_courier

Useful when the user provides a tracking number but doesn't know which courier it belongs to. Returns a ranked list of likely couriers. Auto-detect courier from tracking number

get_tracking

Get details of a specific tracking

list_couriers

) that can be used for tracking packages. List all supported courier companies

list_trackings

Supports extensive filtering by courier (slug), tag, keyword, origin, destination, date ranges, and delivery status. List all package trackings

mark_tracking_completed

Useful when the package has been delivered but the courier hasn't updated the final status. Mark a tracking as completed

retrack_tracking

This restarts monitoring and will fetch new checkpoint updates. Retrack an expired tracking

update_tracking

Does not affect the tracking number or courier. Update an existing tracking

Example Prompts for AfterShip in Pydantic AI

Ready-to-use prompts you can give your Pydantic AI agent to start working with AfterShip immediately.

"Track my package with tracking number 1Z999AA10123456784."

"What courier handles tracking number 9400111899223344556677?"

"Show me all my active trackings."

Troubleshooting AfterShip MCP Server with Pydantic AI

Common issues when connecting AfterShip to Pydantic AI through the Vinkius, and how to resolve them.

MCPServerHTTP not found

Update: pip install --upgrade pydantic-ai

AfterShip + Pydantic AI FAQ

Common questions about integrating AfterShip MCP Server with Pydantic AI.

How does Pydantic AI discover MCP tools?

Create an MCPServerHTTP instance with the server URL. Pydantic AI connects, discovers all tools, and generates typed Python interfaces automatically.

Does Pydantic AI validate MCP tool responses?

Yes. When you define result types as Pydantic models, every tool response is validated against the schema. Invalid data raises a clear error instead of silently corrupting your pipeline.

Can I switch LLM providers without changing MCP code?

Absolutely. Pydantic AI abstracts the model layer. your AfterShip MCP integration works identically with OpenAI, Anthropic, Google, or any supported provider.