How to Use the Kibo Commerce MCP in Google ADK

Q: Can Google ADK agents filter which Kibo Commerce tools they use?

Yes. You can use the toolnames filter in the ADK setup to restrict the agent. For example, you can allow getinventorystatus but block listcustomers for specific Gemini instances.

Q: Can I link Kibo API data to BigQuery?

Yes. Your agent can pull live order metrics via listorders and immediately write that structured data into your BigQuery tables using Google Cloud's native integrations.

Q: Is my Kibo order data secure when queried through this MCP server?

When your agent executes getorderdetails or listcustomers, it handles real names, addresses, and purchase histories. The Vinkius zero-trust architecture ensures this data only passes through an ephemeral V8 isolate. Authentication requires just one endpoint token, and the memory state is wiped the second the Gemini request completes.

Feed Kibo Commerce MCP server data into Google ADK. Let Gemini agents analyze massive product catalogs alongside your BigQuery data.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Kibo Commerce MCP to Google ADK

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Kibo Commerce MCP Server on Gemini

Gemini's massive context window changes how you handle retail catalogs. Your Google ADK agent can pull thousands of items via `list_products` and hold the entire dataset in memory. It reads `list_categories` to understand your taxonomy, then cross-references that structure against search trends stored in BigQuery. Instead of piecemeal queries, the agent analyzes your whole catalog at once. It runs `get_product_details` for specific anomalies and maps them against enterprise data on Google Cloud. You get deep, cross-platform insights without writing custom integration scripts.

Cross-platform inventory analysis

Managing physical stock requires merging API data with historical records. Your agent pulls real-time warehouse data using `list_locations` and checks current stock with `get_inventory_status`. It then joins this live Kibo data with your historical sales data sitting in Vertex AI. This means your agent spots stockouts before they happen. It uses `get_location_details` to map fulfillment centers, comparing live capacity against predicted demand. The Google ADK handles the tool execution natively, letting Gemini do the heavy lifting of enterprise forecasting.

Deep order history processing

Troubleshooting complex commerce orders requires massive context. When an agent runs `list_orders`, it can ingest months of transaction history in a single pass. It follows up with `get_order_details` to extract line-item specifics for problematic shipments. You can configure the McpToolset to only expose these order-specific tools if you want a dedicated customer support agent. By adding `list_customers` to the mix, the agent cross-references user accounts against your internal Google Cloud CRM data to flag high-value buyers.

Setup guide

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

Install google-adk and configure an McpToolset using StreamableHttpServerParameters. Pass this toolset directly into your LlmAgent initialization to expose the Kibo catalog tools.

Yes. You can use the tool_names filter in the ADK setup to restrict the agent. For example, you can allow get_inventory_status but block list_customers for specific Gemini instances.

It absolutely does. You can dump massive JSON payloads from list_products directly into the prompt. Gemini easily digests the entire Kibo catalog structure without losing track of specific item details.

Yes. Your agent can pull live order metrics via list_orders and immediately write that structured data into your BigQuery tables using Google Cloud's native integrations.

When your agent executes get_order_details or list_customers, it handles real names, addresses, and purchase histories. The Vinkius zero-trust architecture ensures this data only passes through an ephemeral V8 isolate. Authentication requires just one endpoint token, and the memory state is wiped the second the Gemini request completes.

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