How to integrate Kaggle MCP with LangChain

BOOK A CALLGET STARTED FOR FREE
Framework Integration Gradient
Kaggle Logo
LangChain Logo
divider

Introduction

This guide walks you through connecting Kaggle to LangChain using the Composio tool router. By the end, you'll have a working Kaggle agent that can download data files for the titanic competition, create a new version of my covid-19 dataset, check processing status of my uploaded dataset, submit my predictions to the house prices competition through natural language commands.

This guide will help you understand how to give your LangChain agent real control over a Kaggle account through Composio's Kaggle MCP server.

Before we dive in, let's take a quick look at the key ideas and tools involved.

TL;DR

Here's what you'll learn:
  • Get and set up your OpenAI and Composio API keys
  • Connect your Kaggle project to Composio
  • Create a Tool Router MCP session for Kaggle
  • Initialize an MCP client and retrieve Kaggle tools
  • Build a LangChain agent that can interact with Kaggle
  • Set up an interactive chat interface for testing

What is LangChain?

LangChain is a framework for developing applications powered by language models. It provides tools and abstractions for building agents that can reason, use tools, and maintain conversation context.

Key features include:

  • Agent Framework: Build agents that can use tools and make decisions
  • MCP Integration: Connect to external services through Model Context Protocol adapters
  • Memory Management: Maintain conversation history across interactions
  • Multi-Provider Support: Works with OpenAI, Anthropic, and other LLM providers

What is the Kaggle MCP server, and what's possible with it?

The Kaggle MCP server is an implementation of the Model Context Protocol that connects your AI agent and assistants like Claude, Cursor, etc directly to your Kaggle account. It provides structured and secure access to your Kaggle datasets, competitions, and configurations, so your agent can perform actions like downloading competition data, creating datasets, submitting entries, and managing dataset versions on your behalf.

  • Competition data access and download: Let your agent fetch and download competition datasets quickly by specifying a competition ID, so you always have the latest files for analysis.
  • Automated dataset creation and management: Have your agent create new Kaggle datasets, update metadata, and publish new dataset versions seamlessly, streamlining the process of sharing your work with the community.
  • Competition entry submission: Empower your agent to submit competition entries automatically once your solution is ready and uploaded, helping you participate in challenges without manual hassle.
  • Configuration management and setup: Allow your agent to initialize, locate, and update Kaggle API configuration files and keys, ensuring smooth and authenticated operations every time.
  • Dataset status monitoring: Ask your agent to check the status of uploaded datasets or processing jobs, so you always know when your data is ready for use or public sharing.

Supported Tools & Triggers

Tools
Download competition data filesTool to download competition data files.
Initialize Kaggle ConfigurationTool to initialize Kaggle API client configuration.
Dataset CreateTool to create a new Kaggle dataset with full metadata.
Get Dataset StatusTool to get the status of a dataset upload or processing job.
Create Dataset VersionTool to create a new dataset version on Kaggle.
Submit Competition EntryTool to submit an entry to a Kaggle competition.
Get Kaggle Config DirectoryTool to retrieve the directory of the Kaggle API configuration file.
Get Kaggle Config FileTool to retrieve the filename of the Kaggle API configuration file.
List Kaggle Configuration KeysTool to list local Kaggle API configuration keys.
Get Kaggle Config PathTool to retrieve local Kaggle API configuration file path.
Reset Kaggle ConfigurationTool to reset local Kaggle CLI configuration to defaults.
Set Kaggle ConfigurationTool to set a Kaggle CLI configuration parameter.
Unset Kaggle ConfigurationTool to unset a Kaggle CLI configuration parameter.
View Kaggle ConfigurationTool to view local Kaggle API configuration.
Kaggle Dataset InitTool to initialize a dataset-metadata.
List Kaggle Dataset FilesTool to list files in a Kaggle dataset.
Kaggle Kernel InitTool to initialize a kernel-metadata.
Download kernel outputTool to download the output of a Kaggle kernel.
Get Kernel StatusTool to get the status of a Kaggle kernel run.
List Kaggle DatasetsTool to list Kaggle datasets with filters and pagination.

What is the Composio tool router, and how does it fit here?

What is Tool Router?

Composio's Tool Router helps agents find the right tools for a task at runtime. You can plug in multiple toolkits (like Gmail, HubSpot, and GitHub), and the agent will identify the relevant app and action to complete multi-step workflows. This can reduce token usage and improve the reliability of tool calls. Read more here: Getting started with Tool Router

The tool router generates a secure MCP URL that your agents can access to perform actions.

How the Tool Router works

The Tool Router follows a three-phase workflow:

  1. Discovery: Searches for tools matching your task and returns relevant toolkits with their details.
  2. Authentication: Checks for active connections. If missing, creates an auth config and returns a connection URL via Auth Link.
  3. Execution: Executes the action using the authenticated connection.

Step-by-step Guide

Prerequisites

Before starting this tutorial, make sure you have:
  • Python 3.10 or higher installed on your system
  • A Composio account with an API key
  • An OpenAI API key
  • Basic familiarity with Python and async programming

Getting API Keys for OpenAI and Composio

OpenAI API Key
  • Go to the OpenAI dashboard and create an API key. You'll need credits to use the models, or you can connect to another model provider.
  • Keep the API key safe.
Composio API Key
  • Log in to the Composio dashboard.
  • Navigate to your API settings and generate a new API key.
  • Store this key securely as you'll need it for authentication.

Install dependencies

pip install composio-langchain langchain-mcp-adapters langchain python-dotenv

Install the required packages for LangChain with MCP support.

What's happening:

  • composio-langchain provides Composio integration for LangChain
  • langchain-mcp-adapters enables MCP client connections
  • langchain is the core agent framework
  • python-dotenv loads environment variables

Set up environment variables

bash
COMPOSIO_API_KEY=your_composio_api_key_here
COMPOSIO_USER_ID=your_composio_user_id_here
OPENAI_API_KEY=your_openai_api_key_here

Create a .env file in your project root.

What's happening:

  • COMPOSIO_API_KEY authenticates your requests to Composio's API
  • COMPOSIO_USER_ID identifies the user for session management
  • OPENAI_API_KEY enables access to OpenAI's language models

Import dependencies

from langchain_mcp_adapters.client import MultiServerMCPClient
from langchain.agents import create_agent
from dotenv import load_dotenv
from composio import Composio
import asyncio
import os

load_dotenv()
What's happening:
  • We're importing LangChain's MCP adapter and Composio SDK
  • The dotenv import loads environment variables from your .env file
  • This setup prepares the foundation for connecting LangChain with Kaggle functionality through MCP

Initialize Composio client

async def main():
    composio = Composio(api_key=os.getenv("COMPOSIO_API_KEY"))

    if not os.getenv("COMPOSIO_API_KEY"):
        raise ValueError("COMPOSIO_API_KEY is not set")
    if not os.getenv("COMPOSIO_USER_ID"):
        raise ValueError("COMPOSIO_USER_ID is not set")
What's happening:
  • We're loading the COMPOSIO_API_KEY from environment variables and validating it exists
  • Creating a Composio instance that will manage our connection to Kaggle tools
  • Validating that COMPOSIO_USER_ID is also set before proceeding

Create a Tool Router session

# Create Tool Router session for Kaggle
session = composio.create(
    user_id=os.getenv("COMPOSIO_USER_ID"),
    toolkits=['kaggle']
)

url = session.mcp.url
What's happening:
  • We're creating a Tool Router session that gives your agent access to Kaggle tools
  • The create method takes the user ID and specifies which toolkits should be available
  • The returned session.mcp.url is the MCP server URL that your agent will use
  • This approach allows the agent to dynamically load and use Kaggle tools as needed

Configure the agent with the MCP URL

client = MultiServerMCPClient({
    "kaggle-agent": {
        "transport": "streamable_http",
        "url": session.mcp.url,
        "headers": {
            "x-api-key": os.getenv("COMPOSIO_API_KEY")
        }
    }
})

tools = await client.get_tools()

agent = create_agent("gpt-5", tools)
What's happening:
  • We're creating a MultiServerMCPClient that connects to our Kaggle MCP server via HTTP
  • The client is configured with a name and the URL from our Tool Router session
  • get_tools() retrieves all available Kaggle tools that the agent can use
  • We're creating a LangChain agent using the GPT-5 model

Set up interactive chat interface

conversation_history = []

print("Chat started! Type 'exit' or 'quit' to end the conversation.\n")
print("Ask any Kaggle related question or task to the agent.\n")

while True:
    user_input = input("You: ").strip()

    if user_input.lower() in ['exit', 'quit', 'bye']:
        print("\nGoodbye!")
        break

    if not user_input:
        continue

    conversation_history.append({"role": "user", "content": user_input})
    print("\nAgent is thinking...\n")

    response = await agent.ainvoke({"messages": conversation_history})
    conversation_history = response['messages']
    final_response = response['messages'][-1].content
    print(f"Agent: {final_response}\n")
What's happening:
  • We initialize an empty conversation_history list to maintain context across interactions
  • A while loop continuously accepts user input from the command line
  • When a user types a message, it's added to the conversation history and sent to the agent
  • The agent processes the request using the ainvoke() method with the full conversation history
  • Users can type 'exit', 'quit', or 'bye' to end the chat session gracefully

Run the application

if __name__ == "__main__":
    asyncio.run(main())
What's happening:
  • We call the main() function using asyncio.run() to start the application

Complete Code

Here's the complete code to get you started with Kaggle and LangChain:

from langchain_mcp_adapters.client import MultiServerMCPClient
from langchain.agents import create_agent
from dotenv import load_dotenv
from composio import Composio
import asyncio
import os

load_dotenv()

async def main():
    composio = Composio(api_key=os.getenv("COMPOSIO_API_KEY"))
    
    if not os.getenv("COMPOSIO_API_KEY"):
        raise ValueError("COMPOSIO_API_KEY is not set")
    if not os.getenv("COMPOSIO_USER_ID"):
        raise ValueError("COMPOSIO_USER_ID is not set")
    
    session = composio.create(
        user_id=os.getenv("COMPOSIO_USER_ID"),
        toolkits=['kaggle']
    )

    url = session.mcp.url
    
    client = MultiServerMCPClient({
        "kaggle-agent": {
            "transport": "streamable_http",
            "url": url,
            "headers": {
                "x-api-key": os.getenv("COMPOSIO_API_KEY")
            }
        }
    })
    
    tools = await client.get_tools()
  
    agent = create_agent("gpt-5", tools)
    
    conversation_history = []
    
    print("Chat started! Type 'exit' or 'quit' to end the conversation.\n")
    print("Ask any Kaggle related question or task to the agent.\n")
    
    while True:
        user_input = input("You: ").strip()
        
        if user_input.lower() in ['exit', 'quit', 'bye']:
            print("\nGoodbye!")
            break
        
        if not user_input:
            continue
        
        conversation_history.append({"role": "user", "content": user_input})
        print("\nAgent is thinking...\n")
        
        response = await agent.ainvoke({"messages": conversation_history})
        conversation_history = response['messages']
        final_response = response['messages'][-1].content
        print(f"Agent: {final_response}\n")

if __name__ == "__main__":
    asyncio.run(main())

Conclusion

You've successfully built a LangChain agent that can interact with Kaggle through Composio's Tool Router.

Key features of this implementation:

  • Dynamic tool loading through Composio's Tool Router
  • Conversation history maintenance for context-aware responses
  • Async Python provides clean, efficient execution of agent workflows
You can extend this further by adding error handling, implementing specific business logic, or integrating additional Composio toolkits to create multi-app workflows.

How to build Kaggle MCP Agent with another framework

OpenAI Agents SDK

OpenAI Agents SDK

Use Kaggle MCP with OpenAI Agents SDK

Claude Agent SDK

Claude Agent SDK

Use Kaggle MCP with Claude Agent SDK

Google ADK

Google ADK

Use Kaggle MCP with Google ADK

Vercel AI SDK

Vercel AI SDK

Use Kaggle MCP with Vercel AI SDK

Mastra AI

Mastra AI

Use Kaggle MCP with Mastra AI

LlamaIndex

LlamaIndex

Use Kaggle MCP with LlamaIndex

CrewAI

CrewAI

Use Kaggle MCP with CrewAI

FAQ

What are the differences in Tool Router MCP and Kaggle MCP?

With a standalone Kaggle MCP server, the agents and LLMs can only access a fixed set of Kaggle tools tied to that server. However, with the Composio Tool Router, agents can dynamically load tools from Kaggle and many other apps based on the task at hand, all through a single MCP endpoint.

Can I use Tool Router MCP with LangChain?

Yes, you can. LangChain fully supports MCP integration. You get structured tool calling, message history handling, and model orchestration while Tool Router takes care of discovering and serving the right Kaggle tools.

Can I manage the permissions and scopes for Kaggle while using Tool Router?

Yes, absolutely. You can configure which Kaggle scopes and actions are allowed when connecting your account to Composio. You can also bring your own OAuth credentials or API configuration so you keep full control over what the agent can do.

How safe is my data with Composio Tool Router?

All sensitive data such as tokens, keys, and configuration is fully encrypted at rest and in transit. Composio is SOC 2 Type 2 compliant and follows strict security practices so your Kaggle data and credentials are handled as safely as possible.

Used by agents from

Context
ASU
Letta
glean
HubSpot
Agent.ai
Altera
DataStax
Entelligence
Rolai
Context
ASU
Letta
glean
HubSpot
Agent.ai
Altera
DataStax
Entelligence
Rolai
Context
ASU
Letta
glean
HubSpot
Agent.ai
Altera
DataStax
Entelligence
Rolai

Never worry about agent reliability

We handle tool reliability, observability, and security so you never have to second-guess an agent action.

Book a call↗Get started for free