How to Use the eBay Shopper MCP in Google ADK

Q: How do I set up the eBay Shopper MCP Server within Google ADK?

Run pip install google-adk and configure an McpToolset using your HTTP endpoint URL. Pass this toolset to your LlmAgent in the tools list. The framework configures the MCP connection automatically so the Gemini model can call all 10 eBay tools.

Q: Can I restrict which eBay Shopper tools my Google ADK agent can access?

Yes, you can use the toolnames filter parameter when initializing your McpToolset. This lets you restrict your agent to specific MCP tools like getitemcompatibility while blocking others like merchant tools.

Q: How does my agent verify if a car part fits using this setup?

The agent calls the getitemcompatibility tool with the specific eBay item ID. It returns a list of compatible vehicles, which your agent can match against your user's fleet database in Google Cloud.

Run enterprise eBay market analysis by connecting this MCP Server to your Google ADK pipelines.

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 Google ADK

Create your Vinkius account to connect eBay Shopper to Google ADK 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 Google ADK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Analyze eBay category trends with Google ADK

Your Google ADK agent can map out the entire eBay catalog structure using the `get_categories` tool. Because the Gemini models support long-context reasoning, your agent can ingest thousands of subcategories at once to identify market gaps. You can then pass these category IDs to `search_by_category` to pull real-time inventory data. The framework lets you feed these massive datasets directly into BigQuery for long-term trend analysis.

Visual search powered by Vertex AI and eBay

The `search_by_image` tool lets your agent find matching products on eBay using visual inputs. Feed image URLs generated by your Vertex AI pipelines straight into this tool to get real-time pricing and availability. Once the agent finds visually similar items, it can pull their granular specs using `get_item_details`. This bridges the gap between Google Cloud's computer vision and actual e-commerce listings.

Calculate total cost of ownership on Google Cloud

Use the `get_shipping_estimate` tool to calculate delivery fees and arrival dates directly inside your agent workflows. This tool requires specific item IDs and postal codes to return accurate shipping costs before you commit to a purchase. Your agent can cross-reference these shipping costs with seller trust metrics using `get_item_reviews` and `get_item_rating`. The Google ADK manages these MCP tool calls via an `McpToolset` instance, keeping your cloud-native agents fast and responsive.

Setup guide

Set up eBay Shopper MCP in Google ADK

Prerequisites

Python 3.10+ installed
google-adk package (pip install google-adk)
Active Vinkius subscription with a valid endpoint token

1

Install Google ADK

Run pip install google-adk to install the Agent Development Kit. MCP support is included via the McpToolset class.
2

Connect via SSE transport

Use McpToolset.from_server() with SseServerParams pointing to your Vinkius endpoint. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Create an LlmAgent

Pass the returned mcp_tools list directly to LlmAgent(tools=mcp_tools). The ADK maps each MCP tool to a native Gemini function call — no manual schema definitions required.
4

Run with any Gemini model

The agent works with any Gemini model (gemini-2.0-flash, gemini-2.5-pro, etc.). Copy the full example on the right to get started with eBay Shopper tools in your ADK agent.

agent.py

from google.adk.agents import LlmAgent
from google.adk.tools.mcp_tool.mcp_toolset import McpToolset
from google.adk.tools.mcp_tool.mcp_session_manager import SseServerParams

# Connect to the MCP via SSE
mcp_tools, exit_stack = await McpToolset.from_server(
    connection_params=SseServerParams(
        url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    )
)

# Create your agent with auto-discovered tools
agent = LlmAgent(
    name="eBay Shopper_agent",
    model="gemini-2.0-flash",
    instruction="You have access to eBay Shopper tools via MCP.",
    tools=mcp_tools,
)

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 Google ADK

Run `pip install google-adk` and configure an `McpToolset` using your HTTP endpoint URL. Pass this toolset to your `LlmAgent` in the tools list. The framework configures the MCP connection automatically so the Gemini model can call all 10 eBay tools.

Yes, you can use the `tool_names` filter parameter when initializing your `McpToolset`. This lets you restrict your agent to specific MCP tools like `get_item_compatibility` while blocking others like merchant tools.

The framework takes advantage of Gemini's 1M+ token context window to process hundreds of items returned by `search_items`. Your agent can compare multiple listings, reviews, and shipping estimates in a single prompt without losing context.

The agent calls the `get_item_compatibility` tool with the specific eBay item ID. It returns a list of compatible vehicles, which your agent can match against your user's fleet database in Google Cloud.

Yes, the server operates inside an ephemeral, zero-trust sandbox that never persists your eBay item IDs, vehicle compatibility queries, or shipping addresses. All data transit is secure, and Vinkius handles the underlying endpoint authentication automatically.

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