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

Q: How do AutoGen agents collaborate to search Klevu (E-commerce AI Search)?

One agent can run searchkeyword to get initial results, while a second agent refines the list by calling searchrecs. They pass the tool outputs back and forth to build the final list.

Q: How do agents handle category merchandising using Klevu (E-commerce AI Search) in AutoGen?

The merchandising agent calls searchcategory to retrieve the active rules for a specific page. It then debates with the sales agent to decide if trending items from searchtrending should be injected.

Q: How do I handle complex custom search payloads using the Klevu (E-commerce AI Search) MCP Server in AutoGen?

You can route custom JSON directly through the searchraw tool. This lets your coordinating agents construct highly specific queries that standard tools cannot generate on their own.

Let your AutoGen agents debate and coordinate to deliver the perfect Klevu search results for your shoppers.

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 AutoGen

Create your Vinkius account to connect Klevu (E-commerce AI Search) to AutoGen 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 AutoGen

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Multi-agent search debate in AutoGen

Set up a shopper agent and a merchandising agent to negotiate product listings. One agent runs `search_keyword` to find matching items, while the other audits the list using `search_recs` to ensure maximum relevance. This consensus-driven approach prevents bad product matches from reaching the user. The agents debate the results in a conversation loop until they agree on the best selection.

Collaborative filtering via MCP Server

This MCP Server enables complex filtering workflows across multiple agents. A budget agent can demand price caps while a style agent looks for specific brands, both feeding parameters to `search_filtered`. The tool aggregates these inputs dynamically, allowing the agents to resolve conflicts. If the search is too restrictive, a third agent can trigger `search_autocomplete` to suggest broader terms.

Automated pagination and sorting coordination

AutoGen agents coordinate to handle long lists of search results. One agent manages the page count using `search_pagination` while another decides the best display order with `search_sorted`. This teamwork ensures the shopper sees the most relevant products first. By splitting the work, your agents process large catalogs without hitting token limits or slowing down.

Setup guide

Set up Klevu (E-commerce AI Search) MCP in AutoGen

Prerequisites

Python 3.10+ installed
autogen-ext[mcp] package
Active Vinkius subscription with a valid endpoint token

1

Install AutoGen with MCP
Run pip install "autogen-ext[mcp]" autogen-agentchat. The MCP extension includes mcp_server_tools for stateless tool access.
2

Fetch tools from the MCP
Call mcp_server_tools(SseServerParams(url=...)) with your Vinkius endpoint. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Run your agent
Pass the tools to AssistantAgent and call agent.run(). The agent invokes Klevu (E-commerce AI Search) tools and returns structured results.

agent.py

from autogen_ext.tools.mcp import SseServerParams, mcp_server_tools
from autogen_agentchat.agents import AssistantAgent
from autogen_ext.models.openai import OpenAIChatCompletionClient

server_params = SseServerParams(
    url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)

tools = await mcp_server_tools(server_params)

agent = AssistantAgent(
    name="Klevu (E-commerce AI Search)_assistant",
    model_client=OpenAIChatCompletionClient(model="gpt-4o"),
    tools=tools,
)

result = await agent.run("List recent Klevu (E-commerce AI Search) data")
print(result.messages[-1].content)

Get your connection token →

Prerequisites

Python 3.10+ installed
autogen-ext[mcp] + autogen-agentchat
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Same packages as above. McpWorkbench is ideal when your agent needs stateful sessions across multiple tool calls.
2

Use McpWorkbench as context manager
Wrap your agent in async with McpWorkbench(...) to maintain shared state and resources. The workbench manages the full MCP session lifecycle.
3

Run with workbench
Pass workbench=workbench to your agent. State is preserved across multiple tool calls within the same session.

agent.py

from autogen_ext.tools.mcp import McpWorkbench, SseServerParams
from autogen_agentchat.agents import AssistantAgent
from autogen_ext.models.openai import OpenAIChatCompletionClient

server_params = SseServerParams(
    url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)

async with McpWorkbench(server_params) as workbench:
    agent = AssistantAgent(
        name="Klevu (E-commerce AI Search)_assistant",
        model_client=OpenAIChatCompletionClient(model="gpt-4o"),
        workbench=workbench,
    )

    result = await agent.run("List recent Klevu (E-commerce AI Search) data")
    print(result.messages[-1].content)

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 AutoGen

One agent can run `search_keyword` to get initial results, while a second agent refines the list by calling `search_recs`. They pass the tool outputs back and forth to build the final list.

Yes, you can restrict tool access when initializing your agents. For example, you can allow a basic agent to only call `search_autocomplete` while giving the manager agent access to `search_raw`.

The merchandising agent calls `search_category` to retrieve the active rules for a specific page. It then debates with the sales agent to decide if trending items from `search_trending` should be injected.

You can route custom JSON directly through the `search_raw` tool. This lets your coordinating agents construct highly specific queries that standard tools cannot generate on their own.

Your data never leaves the secure, ephemeral sandbox. The server only processes transient search terms, facet selections, and product IDs, ensuring no customer data is ever persisted.

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