How to Use the Amazon Selling Partner MCP in Google ADK

Q: How do I connect a Google ADK agent to the Amazon Selling Partner tools?

You use the McpToolset and pass it your Vinkius server URL. Add the toolset to your LlmAgent constructor. The ADK is designed to integrate MCP servers this way, making setup fast.

Q: Can a Google ADK agent use the Amazon Selling Partner MCP to sync data with BigQuery?

Absolutely. That's a core use case. Your agent can call listorders or listfinancialevents and then use Google's own tools to push that data directly into a BigQuery table for analysis.

Q: Can I limit which Amazon Selling Partner tools my Google ADK agent can use?

Yes. The McpToolset constructor accepts a toolnames filter. This lets you expose only a subset of tools, like listfbainventory, to a specific agent for more granular control.

Q: Does this work with all Amazon marketplaces?

First, you'll need to call listmarketplaces to get the correct IDs for the regions you operate in. Once you have those IDs, you can pass them to other tool calls like listorders to get region-specific data.

Connect Google ADK agents to your Amazon Selling Partner data, right from your Google Cloud environment.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Amazon Selling Partner MCP to Google ADK

Create your Vinkius account to connect Amazon Selling Partner 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 Amazon Selling Partner with Google ADK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Analyze Sales Data with BigQuery

Pull your Amazon sales and financial data directly into your Google Cloud ecosystem. An agent running on Gemini can use `list_orders` and `list_financial_events` to fetch fresh data, then pipe it straight into a BigQuery table. This means you can run complex analytics on your Amazon business using the tools you already have. No more manual CSV exports or brittle, custom-built data pipelines. Your agent just keeps the data flowing.

Long-Context Inventory Planning

Gemini's massive context window changes how you can do inventory analysis. Your agent can pull months of inventory history using `list_fba_inventory` and hold it all in memory. It can see seasonal trends and sales velocity without constantly re-fetching data. This allows for much smarter decision-making. The agent can reason over a complete dataset to recommend restocking levels, identify slow-moving products, and spot problems before they drain your cash.

Your Amazon MCP Server for Google ADK

This MCP Server is the bridge between your agent in Vertex AI and your data in Amazon. It's a secure, managed endpoint that exposes only the necessary e-commerce tools. Your Gemini agent doesn't need broad API access, just these specific functions. Setting it up is simple. You point the Google ADK's `McpToolset` at your Vinkius URL, and the tools are ready. You can even filter the toolset to grant an agent access to only one function, like `get_order_items`, for maximum security.

Setup guide

Set up Amazon Selling Partner 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 Amazon Selling Partner 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="Amazon Selling Partner_agent",
    model="gemini-2.0-flash",
    instruction="You have access to Amazon Selling Partner 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 Amazon Selling Partner. 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 Amazon Selling Partner 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 Amazon Selling Partner MCP in Google ADK

You use the `McpToolset` and pass it your Vinkius server URL. Add the toolset to your `LlmAgent` constructor. The ADK is designed to integrate MCP servers this way, making setup fast.

Absolutely. That's a core use case. Your agent can call `list_orders` or `list_financial_events` and then use Google's own tools to push that data directly into a BigQuery table for analysis.

Yes. The `McpToolset` constructor accepts a `tool_names` filter. This lets you expose only a subset of tools, like `list_fba_inventory`, to a specific agent for more granular control.

First, you'll need to call `list_marketplaces` to get the correct IDs for the regions you operate in. Once you have those IDs, you can pass them to other tool calls like `list_orders` to get region-specific data.

Your data, which includes order histories and financial event lists, is processed inside a V8 Isolate sandbox. Each request is totally isolated and ephemeral. Nothing is stored after your agent's request is complete.

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