How to Use the Klevu (E-commerce AI Search) MCP in OpenAI Agents SDK

Q: How do I configure Klevu (E-commerce AI Search) with the OpenAI Agents SDK?

Install openai-agents via pip. Create an MCPServerStreamableHttp instance with your endpoint URL and pass it to your Agent constructor. Set cacheToolsList=True to speed up MCP tool discovery.

Q: Can the OpenAI Agents SDK handle Klevu (E-commerce AI Search) autocomplete?

Yes. The agent calls searchautocomplete to suggest products as users type in a custom frontend interface. The built-in guardrails ensure it only returns valid catalog items.

Q: How does Klevu (E-commerce AI Search) manage sorting in the OpenAI Agents SDK?

The agent uses the searchsorted tool. If a shopper asks for the cheapest running shoes, the agent maps that intent to the correct price-ascending parameter automatically.

Connect Klevu to the OpenAI Agents SDK and give your production systems direct access to product catalogs and AI search.

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 OpenAI Agents SDK

Create your Vinkius account to connect Klevu (E-commerce AI Search) to OpenAI Agents SDK 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 OpenAI Agents SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Run complex catalog queries with OpenAI Agents SDK

Your agent needs to find specific merchandise fast. Connect this MCP Server to your OpenAI setup, and the agent auto-discovers tools like `search_keyword` and `search_filtered`. It maps user intent directly to Klevu's backend, pulling exact matches based on price, color, or brand. You do not want agents guessing at product availability. By chaining `search_category` with `search_pagination`, your multi-agent system scans entire departments and hands off the results to a specialized recommendation agent, all while OpenAI's guardrails validate the inputs.

Fetch real-time trends and recommendations

Static product grids kill conversion rates. Give your agent the ability to pull dynamic suggestions using the `search_recs` tool over your MCP integration. When a shopper views an item, the agent grabs related products instantly. You can also track what is hot globally. The `search_trending` tool lets your agent inject popular items into the conversation. If a user asks for ideas, the agent pulls live data instead of relying on stale training weights.

Execute raw payloads and precise lookups

Sometimes you need complete control over the query structure. The `search_raw` tool lets you bypass standard parameters and send custom JSON payloads straight to the Klevu API. When a user asks about a specific item they bought previously, the agent uses `search_product_id` to grab exact details. You get full visibility into these API calls through the OpenAI tracing dashboard, so you always know exactly what your agent is doing.

Setup guide

Set up Klevu (E-commerce AI Search) MCP in OpenAI Agents SDK

Prerequisites

Python 3.10+ installed
openai-agents package (pip install openai-agents)
Active Vinkius subscription with a valid endpoint token

1

Install the SDK

Run pip install openai-agents to install the OpenAI Agents SDK. The MCP integration is built-in — no extra dependencies needed.
2

Connect via SSE transport

Use MCPServerSse with your Vinkius endpoint URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. The SDK auto-discovers all Klevu (E-commerce AI Search) tools at runtime.
3

Create your Agent

Pass the MCP to Agent(mcp_servers=[server]). The agent receives Klevu (E-commerce AI Search) tools as native definitions — JSON schemas resolve automatically.
4

Run the agent

Call Runner.run(agent, prompt) to execute. The agent invokes the appropriate Klevu (E-commerce AI Search) tools and returns structured results. Copy the full example on the right to get started.

agent.py

import asyncio
from agents import Agent, Runner
from agents.mcp import MCPServerSse

async def main():
    async with MCPServerSse(
        url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    ) as server:
        agent = Agent(
            name="Klevu (E-commerce AI Search) Agent",
            instructions="You have access to Klevu (E-commerce AI Search) tools.",
            mcp_servers=[server],
        )
        result = await Runner.run(agent, "List recent transactions")
        print(result.final_output)

asyncio.run(main())

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 OpenAI Agents SDK

Install `openai-agents` via pip. Create an `MCPServerStreamableHttp` instance with your endpoint URL and pass it to your Agent constructor. Set `cacheToolsList=True` to speed up MCP tool discovery.

Yes. The agent calls `search_autocomplete` to suggest products as users type in a custom frontend interface. The built-in guardrails ensure it only returns valid catalog items.

The agent uses the `search_sorted` tool. If a shopper asks for the cheapest running shoes, the agent maps that intent to the correct price-ascending parameter automatically.

No. The MCP standard handles the schema automatically. The agent discovers the tools on initialization and knows exactly which arguments to pass.

The server only processes search queries, category IDs, and filter parameters. The V8 Isolate Sandbox destroys the environment immediately after the request, leaving zero residual data behind.

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