How to Use the Kelkoo MCP in LlamaIndex

Q: How do I index Kelkoo product categories into a LlamaIndex vector store?

You can call getcategorytree to fetch the taxonomy and load the output directly into a LlamaIndex document reader using the MCP tool spec. Once indexed, your query engine can run semantic searches to match user queries to the correct category IDs.

Q: Can LlamaIndex query engines search Kelkoo coupons in real time?

Yes, by registering searchcoupons as an agent tool, LlamaIndex can dynamically query active discounts. The agent retrieves the coupon codes and injects them directly into the response context to answer user pricing questions.

Q: How does LlamaIndex handle country filters for Kelkoo searches?

Your LlamaIndex agent uses listcountries to check valid locales before executing a search. When a user asks for prices, the agent injects the correct country code into searchoffers based on the user's location.

Index live Kelkoo retail pricing and category data directly into your LlamaIndex vector stores for grounded RAG.

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 LlamaIndex

Create your Vinkius account to connect Kelkoo to LlamaIndex 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 LlamaIndex

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Ground LlamaIndex RAG in live Kelkoo offer data

Look, here's the deal. Instead of letting your agent guess current retail prices, use `search_offers` to pull real-time pricing and index the raw results straight into your LlamaIndex document store. This keeps your generation grounded in actual merchant numbers. Your system can pull structured lists via `get_offer_details` to update metadata filters dynamically. This prevents hallucinations by ensuring your vector index only references active, verified products.

Index merchant catalogs for semantic retrieval

Use `list_merchants` and `get_category_tree` to map out the merchant roster, then write those structures directly into a LlamaIndex VectorStoreIndex. Users can then query complex retail structures using natural language. By loading categories via `list_categories`, your index gains a semantic understanding of how products are grouped. This allows the LlamaIndex query engine to route search terms to the exact right retail category.

Build coupon search indexes with this MCP Server

Connect your query engine to the MCP Server tool `search_coupons` to retrieve active discount codes on demand. LlamaIndex can parse these unstructured coupon strings and match them to user shopping carts. You can run scheduled indexing jobs that pull `get_reporting_summary` to evaluate which merchant offers are performing best, updating your index weights based on actual conversion data.

Setup guide

Set up Kelkoo MCP in LlamaIndex

Prerequisites

Python 3.10+ installed
llama-index-tools-mcp package
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run pip install llama-index-tools-mcp llama-index-llms-openai. The MCP tools package provides BasicMCPClient and McpToolSpec.
2

Connect with BasicMCPClient
Point BasicMCPClient to your Vinkius endpoint URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. Supports SSE and Streamable HTTP transports.
3

Convert to LlamaIndex tools
Call mcp_tool_spec.to_tool_list_async() to convert all Kelkoo MCP tools into native FunctionTool objects that any LlamaIndex agent can use.
4

Run with any LLM
Create a FunctionAgent with the tools and your preferred LLM. Swap OpenAI for Anthropic, Gemini, or any LlamaIndex-supported provider.

agent.py

from llama_index.tools.mcp import BasicMCPClient, McpToolSpec
from llama_index.core.agent.workflow import FunctionAgent
from llama_index.llms.openai import OpenAI

# Connect to the MCP
mcp_client = BasicMCPClient(
    "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)
mcp_tool_spec = McpToolSpec(client=mcp_client)

# Convert MCP tools to LlamaIndex tools
tools = await mcp_tool_spec.to_tool_list_async()

# Create and run the agent
agent = FunctionAgent(
    tools=tools,
    llm=OpenAI(model="gpt-4o"),
    system_prompt="You have access to Kelkoo tools.",
)
response = await agent.run("List recent Kelkoo data")

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 LlamaIndex

You can call `get_category_tree` to fetch the taxonomy and load the output directly into a LlamaIndex document reader using the MCP tool spec. Once indexed, your query engine can run semantic searches to match user queries to the correct category IDs.

Yes, by registering `search_coupons` as an agent tool, LlamaIndex can dynamically query active discounts. The agent retrieves the coupon codes and injects them directly into the response context to answer user pricing questions.

Your LlamaIndex agent uses `list_countries` to check valid locales before executing a search. When a user asks for prices, the agent injects the correct country code into `search_offers` based on the user's location.

Yes, you can combine vector search of your own product database with live API lookups using `get_offer_details` and `list_merchants`. This lets you merge static catalog data with live pricing.

The MCP server only transmits public e-commerce data like offers, merchant IDs, and coupon codes. All traffic passes through a secure, ephemeral Vinkius sandbox, ensuring that your indexed LlamaIndex queries and raw API payloads are never cached or exposed.

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