How to Use the AfterShip Returns MCP in Pydantic AI

Add type-safe returns management to your Pydantic AI agent. Get validated RMA data from AfterShip Returns every time.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect AfterShip Returns MCP to Pydantic AI

Create your Vinkius account to connect AfterShip Returns 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 Returns with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Get Structurally Valid Return Data

The `list_returns` and `get_return_details` tools fetch RMA information from AfterShip. That's the easy part. The hard part is making sure that data is always correct and structured the way you expect. With Pydantic AI, every response from this MCP Server is automatically validated against a Pydantic model. If the API ever sends an unexpected field or the wrong data type, your agent will raise a `ValidationError` immediately. No silent data corruption, no guesswork.

Execute Actions with Confidence

When your agent decides to act, you need to trust it. The `approve_return` and `receive_items` tools change the state of a return in AfterShip, which is a big deal. Because your tool inputs and outputs are strictly typed, you can be certain your agent is calling the function correctly. You won't accidentally try to approve a return with an invalid RMA number. Pydantic AI enforces correctness before the API call is even made.

Model-Agnostic Returns MCP Server

Just add the `MCPToolset` to your Pydantic AI agent and you're good to go. The tools are discovered and ready for use, fully typed and validated at runtime. It doesn't matter if you're using GPT-4, Gemini, or a local Llama model. Your agent gets the same reliable functions for managing returns. This lets you focus on your agent's logic, not on writing boilerplate data validation code.

Setup guide

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

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

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

It's simple. After installing the required package, you initialize `MCPToolset` with your Vinkius endpoint URL. Then, you pass the toolset into the `toolsets` list when creating your Pydantic AI agent.

Correctness. Every single piece of data your agent gets from AfterShip, like return status or item lists, is validated against a Pydantic model. If the data structure is ever wrong, your code will fail loudly instead of processing bad data.

Yes, Pydantic AI is model-agnostic. You can use models from OpenAI, Anthropic, Google, or even local models. The MCP tools will work the same way, with the same type-safety guarantees, regardless of the LLM you choose.

It's the standard way to connect an MCP Server to a Pydantic AI agent. You give it the server URL, and it handles tool discovery and type-safe execution. It's the modern replacement for the old `MCPServerHTTP` class.

Yes. The server only handles the data needed to manage returns, like RMA details and item conditions. Pydantic's models add another layer of security by ensuring only expected data fields are processed. Vinkius provides a secure, isolated environment for every API call, authenticated with your unique token.

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