How to Use the Kelkoo MCP in AutoGen

Q: How do AutoGen agents coordinate when searching Kelkoo offers?

One AutoGen agent can call searchoffers to get a list of products, then pass those results to a critic agent. This critic agent then calls getofferdetails over the MCP connection to verify merchant terms before confirming the purchase option.

Q: Can an AutoGen agent group use Kelkoo coupon codes to optimize carts?

Yes, you can assign a dedicated discount agent to run searchcoupons whenever the primary agent finds a product. The agents debate whether the coupon terms match the offer details before applying the discount.

Q: How does the MCP tool adapter convert schemas for AutoGen?

The adapter converts tools like listmerchants and getreportingsummary into schemas that AutoGen agents understand. This translation happens automatically, so your agents can call the MCP server tools without manual schema mapping.

Let AutoGen agents debate and find the best Kelkoo merchant offers and coupons through collaborative reasoning.

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 AutoGen

Create your Vinkius account to connect Kelkoo 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 Kelkoo with AutoGen

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Multi-agent price negotiation using AutoGen

Heads up: you can set up a buyer agent and a discount agent that negotiate using `search_offers` and `search_coupons`. The buyer agent locates the base prices while the discount agent searches for matching coupons to lower the total cost. By using `get_offer_details`, the agents can compare shipping costs and merchant ratings to decide which offer is actually the best deal, rather than just picking the lowest sticker price.

Let agents debate merchant reliability

Configure an AutoGen performance analyst agent that calls `get_reporting_summary` and `list_merchants` to analyze merchant performance. This analyst can challenge a procurement agent's choices if a merchant has poor conversion or reporting history. This multi-agent setup ensures that your system doesn't blindly recommend offers. The agents use the MCP Server tools to cross-reference data before presenting the final verified options to the user.

Automated catalog mapping and taxonomy validation

Deploy an AutoGen coordinator agent to run `list_countries` and delegate specific regions to sub-agents. These sub-agents then pull regional structures using `list_categories` and `get_category_tree` to map out local catalogs. The agents can compile their findings and debate the best way to categorize products across different borders, resolving taxonomical conflicts before outputting the final structured data.

Setup guide

Set up Kelkoo 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 Kelkoo 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="Kelkoo_assistant",
    model_client=OpenAIChatCompletionClient(model="gpt-4o"),
    tools=tools,
)

result = await agent.run("List recent Kelkoo 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="Kelkoo_assistant",
        model_client=OpenAIChatCompletionClient(model="gpt-4o"),
        workbench=workbench,
    )

    result = await agent.run("List recent Kelkoo 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 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 AutoGen

One AutoGen agent can call `search_offers` to get a list of products, then pass those results to a critic agent. This critic agent then calls `get_offer_details` over the MCP connection to verify merchant terms before confirming the purchase option.

Yes, you can assign a dedicated discount agent to run `search_coupons` whenever the primary agent finds a product. The agents debate whether the coupon terms match the offer details before applying the discount.

If an agent attempts a search with an invalid country, a supervisor agent can invoke `list_countries` to find the closest match. The supervisor then instructs the search agent to retry `search_offers` with the corrected locale code.

The adapter converts tools like `list_merchants` and `get_reporting_summary` into schemas that AutoGen agents understand. This translation happens automatically, so your agents can call the MCP server tools without manual schema mapping.

All API calls to Kelkoo run through an isolated, zero-trust Vinkius environment. Your AutoGen conversation logs, affiliate tracking IDs, and raw merchant reporting metrics are processed entirely in memory and never stored on disk.

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