How to Use the Commerce Layer MCP in Google ADK

Q: How do I initialize Commerce Layer tools in Google ADK?

You use the McpToolset class and point it to your Vinkius HTTP server URL. Pass this MCP toolset directly to your LlmAgent to expose the commerce tools to Gemini.

Q: Can Google ADK filter which Commerce Layer tools are active?

Yes, you can use the optional toolnames filter in the ADK setup. This lets you restrict the agent to read-only tools like listskus if you want to prevent automated ordering.

Run enterprise retail agents on Google ADK with direct access to your Commerce Layer store via MCP.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Commerce Layer MCP to Google ADK

Create your Vinkius account to connect Commerce Layer 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 Commerce Layer with Google ADK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Query markets and customer lists with Google ADK

The `list_markets` and `list_customers` tools allow your Gemini-powered agent to segment buyers based on their geographic region. This ensures your agent displays localized storefronts and correct currency options during long-running chats. You can combine this data with your existing BigQuery datasets. The agent parses millions of tokens of historical purchase data to match registered customers with their preferred regional markets instantly.

Build checkout flows using this MCP Server

The `list_payment_methods` and `create_order` tools give your agent the ability to set up transactions on the fly. It fetches available checkout options and prepares the draft order for the customer. Because the ADK runs natively on Google Cloud, you can trigger these actions directly from your enterprise databases. The agent coordinates the entire checkout process without dropping the conversation context.

Track order status and verify delivery locations

Your agent uses `list_addresses` and `list_orders` to check where a shipment is going and review past purchases. This lets the agent handle address corrections before a draft order is finalized. Gemini's massive context window means the agent remembers previous address changes across days of chat history. You don't have to rebuild state machines to track user preferences.

Setup guide

Set up Commerce Layer 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 Commerce Layer 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="Commerce Layer_agent",
    model="gemini-2.0-flash",
    instruction="You have access to Commerce Layer 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 Commerce Layer. 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 Commerce Layer 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 Commerce Layer MCP in Google ADK

You use the `McpToolset` class and point it to your Vinkius HTTP server URL. Pass this MCP toolset directly to your `LlmAgent` to expose the commerce tools to Gemini.

Yes, you can use the optional `tool_names` filter in the ADK setup. This lets you restrict the agent to read-only tools like `list_skus` if you want to prevent automated ordering.

The agent leverages Gemini's long context to parse results from `list_orders` alongside your BigQuery warehouse logs. It can analyze thousands of order histories in a single turn.

Yes, the ADK supports both Stdio and HTTP transports. For production cloud deployments, the Streamable HTTP transport hosted on Vinkius is the recommended MCP approach.

The MCP architecture ensures your SKU lists, prices, and active promotions are retrieved via secure HTTPS requests. No catalog data is cached on Google's model servers, keeping your competitive pricing structures private.

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