How to Use the eBay Shopper MCP in Pydantic AI

Q: How do I initialize the eBay Shopper MCP Server in Pydantic AI?

Install the package using pip install "pydantic-ai-slimmcp" and create an MCPToolset pointing to your server URL. Pass this toolset directly into your Agent constructor. This unified approach for MCP integrations replaces the deprecated HTTP server classes.

Q: Can my Pydantic AI agent search eBay Shopper by image?

Yes, your agent can call searchbyimage by passing an image URL. The tool returns a typed list of visually similar items, which Pydantic AI validates against your defined schema before returning them to the model.

Q: How do I paginate through eBay category listings?

Your agent can call searchbycategory using a valid category ID obtained from getcategories. You can control the results by passing typed limit and offset parameters to step through the listings safely.

Type-safe eBay product search and shipping estimates on this MCP Server for your Pydantic AI agents.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect eBay Shopper MCP to Pydantic AI

Create your Vinkius account to connect eBay Shopper 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 eBay Shopper with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Type-safe eBay searches with Pydantic AI

The `search_items` tool returns a structured list of product titles, prices, conditions, and image URLs. When your Pydantic AI agent calls this tool, all fields are validated against strict Python type schemas at runtime. If the eBay API returns unexpected or malformed data, the framework raises a clear validation error immediately. This prevents silent corruption in your database and keeps your agent from acting on broken product records.

Validate vehicle compatibility using this MCP Server

The `get_item_compatibility` tool provides critical fitment information for automotive listings. Pydantic AI ensures that the returned vehicle compatibility list matches your application's expected data models before your agent presents them to a user. If your agent needs deep seller details, it can call `get_merchant_item_details` and `get_categories` to build a complete profile of the merchant. Every step of this data gathering process is strictly typed, making it perfect for production systems that cannot afford errors.

Strict validation of shipping costs and customer reviews

Use the `get_shipping_estimate` tool to fetch delivery dates and shipping fees with absolute type safety. The framework validates the estimated cost structure so your agent never makes math errors when calculating total order values. You can also pull customer feedback using `get_item_reviews` and `get_item_rating`. The reviews are parsed into clean Pydantic models containing ratings, text, and reviewer names, ensuring your sentiment analysis tools receive clean inputs.

Setup guide

Set up eBay Shopper 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": {
        "ebay-shopper-mcp": {
            "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
        }
    }
})

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

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

Install the package using `pip install "pydantic-ai-slim[mcp]"` and create an `MCPToolset` pointing to your server URL. Pass this toolset directly into your `Agent` constructor. This unified approach for MCP integrations replaces the deprecated HTTP server classes.

The framework will throw a validation error at runtime instead of letting your agent hallucinate. This ensures your agent only processes valid eBay product listings, prices, and shipping estimates, rejecting bad data over the MCP connection.

Yes, your agent can call `search_by_image` by passing an image URL. The tool returns a typed list of visually similar items, which Pydantic AI validates against your defined schema before returning them to the model.

Your agent can call `search_by_category` using a valid category ID obtained from `get_categories`. You can control the results by passing typed `limit` and `offset` parameters to step through the listings safely.

The server runs in a secure, ephemeral V8 sandbox that does not store any of your postal codes, vehicle details, or eBay product IDs. All credentials and data exist only during the active runtime session and are completely destroyed afterward.

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