How to Use the VTEX Catalog MCP in Google ADK

Q: What is the process of using VTEX Catalog with Google ADK?

You initialize the LlmAgent with the McpToolset, passing in your server details. The agent then uses Gemini's reasoning to decide when and how to invoke a tool like getproduct against VTEX Catalog.

Q: Can I use Google ADK to update products in VTEX Catalog?

Yes, you can. Tools like saveproduct allow your agent to create or modify product records. This is ideal for agents that need to push changes from a central Google Cloud data source.

Q: What kind of tools does the MCP Server offer for VTEX Catalog in Google ADK?

It gives you seven tools, including getsku, searchproducts, managestock, and others. These let your agent interact with everything from product details to stock levels.

Connect VTEX Catalog to Google ADK. Run product management and inventory actions using Gemini models on Google Cloud.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect VTEX Catalog MCP to Google ADK

Create your Vinkius account to connect VTEX Catalog 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 VTEX Catalog with Google ADK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Building Enterprise Agents

The `save_product` tool lets your agent create or update products in VTEX Catalog, but it does this within the secure context of Google Cloud. This is for agents running on big enterprise infrastructure. The native integration with BigQuery means that before your agent acts, it can cross-reference the product data against massive datasets you already store.

Advanced Product Querying

Need to find something specific? The `search_products` tool lets your LlmAgent query VTEX Catalog by text, brand, or category. It's powerful stuff. Using the Google ADK with Gemini models means that even if you have a complex, multi-step search criteria, the agent can handle it because of its long context window.

Managing Inventory and Metadata

Don't mess up your stock counts. Call `manage_stock` to update quantities for any SKU in VTEX Catalog. You can also use `get_brand` or `get_category` to pull metadata needed for accurate inventory management. The Google ADK supports Stdio and HTTP transports, so you can fit this MCP Server into whatever existing Google Cloud data pipeline you're running.

Setup guide

Set up VTEX Catalog 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 VTEX Catalog 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="VTEX Catalog_agent",
    model="gemini-2.0-flash",
    instruction="You have access to VTEX Catalog 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 VTEX. 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 VTEX Catalog 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 VTEX Catalog MCP in Google ADK

You initialize the LlmAgent with the `McpToolset`, passing in your server details. The agent then uses Gemini's reasoning to decide when and how to invoke a tool like `get_product` against VTEX Catalog.

Yes, you can. Tools like `save_product` allow your agent to create or modify product records. This is ideal for agents that need to push changes from a central Google Cloud data source.

The Google ADK facilitates this connection by allowing the agent to hold large context windows (1M+ tokens) and reason over both your internal BigQuery data and live catalog data from VTEX Catalog.

It gives you seven tools, including `get_sku`, `search_products`, `manage_stock`, and others. These let your agent interact with everything from product details to stock levels.

This server manages core e-commerce information, including SKU availability, brand metadata, category hierarchies, and full product descriptions within your VTEX Catalog.

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