How to Use the Kelkoo MCP in CrewAI

Q: What's the best way for a CrewAI agent to explore the entire Kelkoo product catalog?

Have one agent call getcategorytree to get the full structure. It can then pass individual category IDs to other agents in the crew, which can then use searchoffers to investigate each part of the catalog in parallel.

Q: How does my crew get a summary of my performance?

Assign an 'Analyst' agent the getreportingsummary tool. It can run this tool periodically and use the output to inform the crew's strategy or tasking.

Deploy autonomous agent crews with CrewAI to perform market research and competitive analysis on the Kelkoo product catalog.

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 CrewAI

Create your Vinkius account to connect Kelkoo to CrewAI 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 CrewAI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Assemble an Offer Research Crew

Assign specialized roles to your agents. A 'Scout' agent can use `list_countries` and `list_categories` to map out the market. It then passes tasks to a 'Hunter' agent, whose only job is to run `search_offers` and `search_coupons` to find the best deals. Finally, a 'Reporter' agent takes the top findings from the Hunter, calls `get_offer_details` to get the fine print, and formats a summary. This is how you use CrewAI to turn a simple API into a full-fledged research department.

Run Autonomous Competitive Analysis

Set up a crew to track rival merchants on Kelkoo. One agent's role is to monitor a specific competitor, using `list_merchants` to get their ID and `search_offers` to track their pricing on key products. It works tirelessly in the background. Another 'Analyst' agent in the same crew compares that data to your own performance from `get_reporting_summary`. The crew can spot threats and opportunities on its own, then assign new research tasks without any human input.

Build a Catalog Intelligence Team

A 'Mapper' agent can build a complete map of Kelkoo's product hierarchy by calling `get_category_tree`. It then hands off that structure to a 'Data Miner' agent within the crew. This second agent's job is to cross-reference the category map with merchant data from `list_merchants`. Its goal is to identify which sellers are dominant in which product niches. Your crew builds a strategic dataset that would take a human analyst weeks to compile.

Setup guide

Set up Kelkoo MCP in CrewAI

Prerequisites

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

1

Install CrewAI
Run pip install crewai to install the framework. MCP support is built-in via the mcps parameter.
2

Add the MCP URL to your agent
Pass your Vinkius endpoint directly to the mcps list. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. CrewAI handles tool discovery and caching automatically.
3

Kick off your crew
Create a Crew with your agent and tasks. Call crew.kickoff() — the agent will automatically invoke Kelkoo tools as needed.

crew.py

from crewai import Agent, Task, Crew

agent = Agent(
    role="Kelkoo Analyst",
    goal="Access and analyze Kelkoo data via MCP.",
    backstory="Expert analyst with direct Kelkoo access.",
    mcps=[
        "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    ],
)

task = Task(
    description="List recent Kelkoo transactions",
    agent=agent,
    expected_output="A summary of recent activity",
)

crew = Crew(agents=[agent], tasks=[task])
result = crew.kickoff()
print(result)

Get your connection token →

Prerequisites

Python 3.10+ installed
crewai + crewai-tools packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run pip install crewai crewai-tools. The MCPServerAdapter handles lifecycle management and tool conversion.
2

Connect with MCPServerAdapter
Use MCPServerAdapter as a context manager with SseServerParameters pointing to your Vinkius endpoint. The adapter automatically manages connection lifecycle.
3

Assign tools and run
Pass the returned mcp_tools to your agent's tools parameter. The adapter converts MCP tools to native BaseTool objects compatible with all CrewAI agents.

crew.py

from crewai import Agent, Task, Crew
from crewai_tools import MCPServerAdapter
from mcp import SseServerParameters

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

with MCPServerAdapter(server_params) as mcp_tools:
    agent = Agent(
        role="Kelkoo Analyst",
        goal="Access and analyze Kelkoo data via MCP.",
        backstory="Expert analyst with direct Kelkoo access.",
        tools=mcp_tools,
    )

    task = Task(
        description="List recent Kelkoo transactions",
        agent=agent,
        expected_output="A summary of recent activity",
    )

    crew = Crew(agents=[agent], tasks=[task])
    result = crew.kickoff()
    print(result)

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 CrewAI

When you define each agent in CrewAI, you can pass a specific list of tools to it. This lets you create specialized agents, like one that can only use `search_offers` and another that can only use `get_reporting_summary`.

Yes, that's the point of CrewAI. One agent can find data with `search_offers`, and a manager agent can analyze its findings to delegate a new task, like using `get_offer_details`, to another specialist agent.

Have one agent call `get_category_tree` to get the full structure. It can then pass individual category IDs to other agents in the crew, which can then use `search_offers` to investigate each part of the catalog in parallel.

Assign an 'Analyst' agent the `get_reporting_summary` tool. It can run this tool periodically and use the output to inform the crew's strategy or tasking.

Securely. The server is designed to process requests for public e-commerce data—offers, categories, and merchants. Your CrewAI instance connects through a single, authenticated Vinkius endpoint, and the server environment that runs the tools is discarded after use.

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