How to Use the Kelkoo MCP in Google ADK

Q: How do I restrict Kelkoo tools in Google ADK?

You can use the toolnames filter when initializing the McpToolset. This limits the Kelkoo functions your agent can see.

Q: Is Kelkoo data compatible with Gemini in Google ADK?

Yes. The JSON payloads from getcategorytree and other tools are native to Gemini's input format. It processes the retail hierarchy with zero friction.

Connect Kelkoo to Google ADK to build enterprise agents that analyze global retail inventory within the Gemini ecosystem.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Kelkoo MCP to Google ADK

Create your Vinkius account to connect Kelkoo 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 Kelkoo with Google ADK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Analyze retail inventory via Google ADK

Your Gemini-powered agent can now query global product catalogs using `search_offers`. By passing the country code, you get region-specific pricing data directly into your agent's memory. This setup works well with your existing Google Cloud infrastructure. Since the agent handles the `get_offer_details` call, you can pipe the result straight into BigQuery for long-term analysis.

Filter merchants with Google ADK

Use `list_merchants` to define the scope of your agent's retail search. This prevents the agent from wasting tokens on irrelevant data sources. Combine this with `list_categories` to build a structured navigation flow. Your agent will know exactly which categories exist before it tries to fetch specific product details.

Automate coupon discovery in Google ADK

Let your agent hunt for active deals using `search_coupons`. It effectively turns your agent into a real-time shopping assistant that can verify current discounts. It’s a straightforward way to add value to your user-facing tools. The agent manages the `search_coupons` request and presents the final, validated discount information.

Setup guide

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

You can use the tool_names filter when initializing the McpToolset. This limits the Kelkoo functions your agent can see.

Yes. The JSON payloads from `get_category_tree` and other tools are native to Gemini's input format. It processes the retail hierarchy with zero friction.

You can. While HTTP is the default for remote setups, the McpToolset supports Stdio if your environment requires a local process connection.

The connection uses encrypted endpoints. Vinkius manages the auth, so your agent only needs the provided token to start querying retail data.

It accesses public retail product details, merchant listings, and your own publisher reporting metrics. No private user info is ever exposed.

Use it with your favorite AI tools

Connect this server to Cursor, Claude, VS Code, and more.

OpenAI Agents SDK sdk-python