How to Use the Klevu (E-commerce AI Search) MCP in Google ADK

Q: How do I connect Klevu (E-commerce AI Search) to Google ADK?

Install the google-adk package. Initialize an McpToolset pointing to your MCP Server URL and pass it to the LlmAgent tools array. It supports both Stdio and HTTP transports.

Q: Can Google ADK agents pull specific items from Klevu (E-commerce AI Search)?

Absolutely. The agent executes searchproductid to grab exact details for a single SKU. This is perfect for answering support tickets about specific merchandise.

Q: Does Klevu (E-commerce AI Search) work with Google ADK recommendations?

Yes. The agent triggers the searchrecs tool to fetch AI-driven product suggestions. It then merges those recommendations with customer history from BigQuery.

Q: How do I handle large result sets?

The agent uses the searchpagination tool over the MCP standard. It requests specific pages of results, preventing payload limits from breaking the context window.

Bring Klevu catalog search to Google ADK and let Gemini agents query product data across your enterprise infrastructure.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Klevu (E-commerce AI Search) MCP to Google ADK

Create your Vinkius account to connect Klevu (E-commerce AI Search) 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 Klevu (E-commerce AI Search) with Google ADK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Query catalogs inside massive Gemini contexts

Gemini models can hold millions of tokens. When you connect this MCP Server, your agent pulls hundreds of products via `search_category` and evaluates them all at once. It cross-references Klevu search results with user profiles stored natively in BigQuery. The agent uses `search_keyword` to find specific items. Because the Google ADK handles the transport layer naturally, your enterprise agents query the catalog, filter the results, and generate personalized shopping reports without dropping context.

Build predictive search with Google ADK

Fast discovery drives revenue. Your Gemini agent calls `search_autocomplete` to grab suggestions the millisecond a user starts typing. It anticipates what the shopper wants before they finish the sentence. Shoppers often narrow things down by attributes. The `search_filtered` tool lets the agent apply exact constraints like size, color, or stock status. It acts as a direct pipe from natural language to precise catalog queries.

Tap into global trends and raw API access

You want your agents to know what is selling right now. They hit the `search_trending` tool to pull globally relevant merchandise and surface those items in chat interfaces or automated email campaigns. For complex enterprise use cases, the `search_raw` tool accepts custom JSON payloads. If you have custom routing logic built in Vertex AI, your agent crafts exact API requests and bypasses standard MCP abstractions.

Setup guide

Set up Klevu (E-commerce AI Search) 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 Klevu (E-commerce AI Search) 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="Klevu (E-commerce AI Search)_agent",
    model="gemini-2.0-flash",
    instruction="You have access to Klevu (E-commerce AI Search) 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 Klevu. 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 Klevu (E-commerce AI Search) 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 Klevu (E-commerce AI Search) MCP in Google ADK

Install the `google-adk` package. Initialize an `McpToolset` pointing to your MCP Server URL and pass it to the `LlmAgent` tools array. It supports both Stdio and HTTP transports.

Absolutely. The agent executes `search_product_id` to grab exact details for a single SKU. This is perfect for answering support tickets about specific merchandise.

Yes. The agent triggers the `search_recs` tool to fetch AI-driven product suggestions. It then merges those recommendations with customer history from BigQuery.

The agent uses the `search_pagination` tool over the MCP standard. It requests specific pages of results, preventing payload limits from breaking the context window.

The integration processes product IDs, keywords, and facet filters. Every execution runs in an ephemeral, zero-trust container that terminates when the API returns, ensuring no query history lingers in memory.

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