How to Use the Kelkoo MCP in LangChain

Q: Can I trace Kelkoo API latency inside LangSmith using LangChain?

Yes, every single call to the Kelkoo MCP Server tools like getofferdetails or searchcoupons gets fully logged in LangSmith. You can inspect the exact execution time, input parameters, and raw JSON payloads returned by the merchant API.

Q: How do I pass Kelkoo category trees into a LangChain stateful agent?

You can load the taxonomy using getcategorytree and store it in LangChain's memory or pass it as context to a LangGraph state node. This allows subsequent steps in your chain to filter searchoffers results based on the correct category IDs.

Feed real-time retail pricing and coupon data from Kelkoo directly into your LangChain multi-step reasoning chains.

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 LangChain

Create your Vinkius account to connect Kelkoo to LangChain 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 LangChain

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Chain Kelkoo searches with LangChain reasoning

Right. So. Your LangChain agent can now run a multi-step search starting with `search_offers` to pull pricing, then feed those raw offer IDs straight into `get_offer_details` to verify merchant specifics. This chain runs dynamically without hardcoded API glue. Because LangChain handles state transitions, your agent decides whether to pull the hierarchical taxonomy via `get_category_tree` or jump straight to looking up active discount codes using `search_coupons` based on user intent.

Trace Kelkoo MCP Server inputs via LangSmith

Monitor exactly how your chains format the required country codes when calling the Kelkoo MCP Server tool `search_offers` to avoid bad requests. LangSmith records every latency spike and payload detail. When an agent pulls merchant lists via `list_merchants`, you see the exact JSON exchange in your trace. This keeps your token usage predictable and makes debugging broken country parameters a non-event.

Build multi-country comparison pipelines

Let your LangChain pipeline inspect global pricing by combining `list_countries` with concurrent calls to `list_categories` across different regions. This lets you map out product availability without writing custom loops. You can feed the final aggregated offers into a reporting chain that uses `get_reporting_summary` to track click performance. LangChain handles the passing of these data payloads from one step to the next natively.

Setup guide

Set up Kelkoo MCP in LangChain

Prerequisites

Python 3.10+ installed
langchain-mcp-adapters + langgraph packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run pip install langchain-mcp-adapters langgraph langchain-openai. The MCP adapters package converts MCP tools into native LangChain BaseTool objects.
2

Connect via HTTP transport
Use MultiServerMCPClient with "transport": "http" pointing to your Vinkius endpoint. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Create a ReAct agent
Pass the discovered tools to create_react_agent() from LangGraph. The agent automatically routes Kelkoo tool calls through the MCP protocol.
4

Run with any LLM
Swap ChatOpenAI for ChatAnthropic, ChatGoogleGenerativeAI, or any LangChain-compatible model. The MCP tools work identically across all providers.

agent.py

from langchain_mcp_adapters.client import MultiServerMCPClient
from langgraph.prebuilt import create_react_agent
from langchain_openai import ChatOpenAI

async with MultiServerMCPClient({
    "kelkoo-mcp": {
        "transport": "http",
        "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp",
    }
}) as client:
    tools = client.get_tools()

    agent = create_react_agent(
        ChatOpenAI(model="gpt-4o"),
        tools,
    )
    result = await agent.ainvoke({
        "messages": "List recent Kelkoo transactions"
    })
    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 LangChain

Your LangChain agent extracts the country code from user prompts and passes it directly to `search_offers`. If the country is ambiguous, the agent can call `list_countries` first to validate the input before executing the main search.

Yes, every single call to the Kelkoo MCP Server tools like `get_offer_details` or `search_coupons` gets fully logged in LangSmith. You can inspect the exact execution time, input parameters, and raw JSON payloads returned by the merchant API.

You can load the taxonomy using `get_category_tree` and store it in LangChain's memory or pass it as context to a LangGraph state node. This allows subsequent steps in your chain to filter `search_offers` results based on the correct category IDs.

The MultiServerMCPClient automatically converts the schemas of tools like `list_merchants` and `get_reporting_summary` into standard LangChain tool definitions. Your agents can call them immediately without manually writing JSON schemas.

This MCP server only processes search queries, country codes, coupon terms, and reporting metrics. Vinkius runs the server in an isolated sandbox, meaning your proprietary LangChain prompt templates and API keys never touch external logs or persistent databases.

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