How to integrate Kaggle MCP with CrewAI

Trusted by
AWS
Glean
Zoom
Airtable
GET STARTED FOR FREEGET A DEMO

30 min · no commitment · see it on your stack

Kaggle logo
CrewAI logo
divider

Introduction

This guide walks you through connecting Kaggle to CrewAI 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 your covid-19 dataset, check processing status of your uploaded dataset through natural language commands.

This guide will help you understand how to give your CrewAI 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.

Also integrate Kaggle with

TL;DR

Here's what you'll learn:
  • Get a Composio API key and configure your Kaggle connection
  • Set up CrewAI with an MCP enabled agent
  • Create a Tool Router session or standalone MCP server for Kaggle
  • Build a conversational loop where your agent can execute Kaggle operations

What is CrewAI?

CrewAI is a powerful framework for building multi-agent AI systems. It provides primitives for defining agents with specific roles, creating tasks, and orchestrating workflows through crews.

Key features include:

  • Agent Roles: Define specialized agents with specific goals and backstories
  • Task Management: Create tasks with clear descriptions and expected outputs
  • Crew Orchestration: Combine agents and tasks into collaborative workflows
  • MCP Integration: Connect to external tools through Model Context Protocol

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 filesDownloads all data files for a Kaggle competition as a single zip archive.
Submit Competition EntrySubmit an entry to a Kaggle competition using a previously uploaded file.
Get Kaggle Config DirectoryTool to retrieve the directory of the Kaggle API configuration file.
Initialize Kaggle ConfigurationInitialize Kaggle API client configuration.
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 ConfigurationView local Kaggle API credentials and configuration settings.
Dataset CreateCreate a new Kaggle dataset with metadata.
Kaggle Dataset InitTool to initialize a dataset-metadata.
List Kaggle Dataset FilesTool to list files in a Kaggle dataset.
Get Dataset StatusCheck the processing status of a Kaggle dataset after creation or version update.
Create Dataset VersionCreate a new version of an existing Kaggle dataset.
Download competition fileTool to download a specific data file from a Kaggle competition.
Download competition leaderboardTool to download the entire competition leaderboard as a CSV file packaged in a ZIP archive.
Download Kaggle DatasetTool to download all files from a Kaggle dataset as a zip archive.
Download Kaggle Dataset FileTool to download a specific file from a Kaggle dataset.
Generate Competition Submission URLTool to generate a pre-signed URL for uploading competition submission files.
Get Dataset MetadataTool to get comprehensive metadata for a Kaggle dataset including title, description, licenses, and tags.
Get Model DetailsTool to get a Kaggle model's details including metadata and description.
Get Model Instance DetailsTool to get details for a specific Kaggle model instance (variation).
Kaggle Kernel InitInitialize a kernel-metadata.
Download kernel outputTool to download the output of a Kaggle kernel.
Get Kernel StatusGet the execution status of a Kaggle kernel (notebook).
List competition data filesTool to list all data files available for a Kaggle competition.
List Kaggle CompetitionsTool to list available Kaggle competitions with filters and pagination.
List Kaggle DatasetsTool to list Kaggle datasets with filters and pagination.
List Kernel Output FilesTool to list output files for a specific kernel run.
List Kaggle KernelsTool to list Kaggle kernels (notebooks and scripts) with filters and pagination.
List Model Instance Version FilesTool to list files for a specific version of a model variation.
List Kaggle ModelsTool to list Kaggle models with optional filters for owner, sorting, search, and pagination.
Pull Kernel CodeTool to pull (download) the source code of a Kaggle kernel to local storage.
View competition leaderboardTool to view competition leaderboard information showing rankings and scores of participants.

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

What is Composio SDK?

Composio's Composio SDK 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 Composio SDK

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

How the Composio SDK works

The Composio SDK 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, make sure you have:
  • Python 3.9 or higher
  • A Composio account and API key
  • A Kaggle connection authorized in Composio
  • An OpenAI API key for the CrewAI LLM
  • Basic familiarity with Python

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

bash
pip install composio crewai crewai-tools[mcp] python-dotenv
What's happening:
  • composio connects your agent to Kaggle via MCP
  • crewai provides Agent, Task, Crew, and LLM primitives
  • crewai-tools[mcp] includes MCP helpers
  • python-dotenv loads environment variables from .env

Set up environment variables

bash
COMPOSIO_API_KEY=your_composio_api_key_here
USER_ID=your_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 with Composio
  • USER_ID scopes the session to your account
  • OPENAI_API_KEY lets CrewAI use your chosen OpenAI model

Import dependencies

python
import os
from composio import Composio
from crewai import Agent, Task, Crew
from crewai_tools import MCPServerAdapter
import dotenv

dotenv.load_dotenv()

COMPOSIO_API_KEY = os.getenv("COMPOSIO_API_KEY")
COMPOSIO_USER_ID = os.getenv("COMPOSIO_USER_ID")

if not COMPOSIO_API_KEY:
    raise ValueError("COMPOSIO_API_KEY is not set")
if not COMPOSIO_USER_ID:
    raise ValueError("COMPOSIO_USER_ID is not set")
What's happening:
  • CrewAI classes define agents and tasks, and run the workflow
  • MCPServerHTTP connects the agent to an MCP endpoint
  • Composio will give you a short lived Kaggle MCP URL

Create a Composio Tool Router session for Kaggle

python
composio_client = Composio(api_key=COMPOSIO_API_KEY)
session = composio_client.create(user_id=COMPOSIO_USER_ID, toolkits=["kaggle"])

url = session.mcp.url
What's happening:
  • You create a Kaggle only session through Composio
  • Composio returns an MCP HTTP URL that exposes Kaggle tools

Initialize the MCP Server

python
server_params = {
    "url": url,
    "transport": "streamable-http",
    "headers": {"x-api-key": COMPOSIO_API_KEY},
}

with MCPServerAdapter(server_params) as tools:
    agent = Agent(
        role="Search Assistant",
        goal="Help users search the internet effectively",
        backstory="You are a helpful assistant with access to search tools.",
        tools=tools,
        verbose=False,
        max_iter=10,
    )
What's Happening:
  • Server Configuration: The code sets up connection parameters including the MCP server URL, streamable HTTP transport, and Composio API key authentication.
  • MCP Adapter Bridge: MCPServerAdapter acts as a context manager that converts Composio MCP tools into a CrewAI-compatible format.
  • Agent Setup: Creates a CrewAI Agent with a defined role (Search Assistant), goal (help with internet searches), and access to the MCP tools.
  • Configuration Options: The agent includes settings like verbose=False for clean output and max_iter=10 to prevent infinite loops.
  • Dynamic Tool Usage: Once created, the agent automatically accesses all Composio Search tools and decides when to use them based on user queries.

Create a CLI Chatloop and define the Crew

python
print("Chat started! Type 'exit' or 'quit' to end.\n")

conversation_context = ""

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

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

    if not user_input:
        continue

    conversation_context += f"\nUser: {user_input}\n"
    print("\nAgent is thinking...\n")

    task = Task(
        description=(
            f"Conversation history:\n{conversation_context}\n\n"
            f"Current request: {user_input}"
        ),
        expected_output="A helpful response addressing the user's request",
        agent=agent,
    )

    crew = Crew(agents=[agent], tasks=[task], verbose=False)
    result = crew.kickoff()
    response = str(result)

    conversation_context += f"Agent: {response}\n"
    print(f"Agent: {response}\n")
What's Happening:
  • Interactive CLI Setup: The code creates an infinite loop that continuously prompts for user input and maintains the entire conversation history in a string variable.
  • Input Validation: Empty inputs are ignored to prevent processing blank messages and keep the conversation clean.
  • Context Building: Each user message is appended to the conversation context, which preserves the full dialogue history for better agent responses.
  • Dynamic Task Creation: For every user input, a new Task is created that includes both the full conversation history and the current request as context.
  • Crew Execution: A Crew is instantiated with the agent and task, then kicked off to process the request and generate a response.
  • Response Management: The agent's response is converted to a string, added to the conversation context, and displayed to the user, maintaining conversational continuity.

Complete Code

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

python
from crewai import Agent, Task, Crew, LLM
from crewai_tools import MCPServerAdapter
from composio import Composio
from dotenv import load_dotenv
import os

load_dotenv()

GOOGLE_API_KEY = os.getenv("GOOGLE_API_KEY")
COMPOSIO_API_KEY = os.getenv("COMPOSIO_API_KEY")
COMPOSIO_USER_ID = os.getenv("COMPOSIO_USER_ID")

if not GOOGLE_API_KEY:
    raise ValueError("GOOGLE_API_KEY is not set in the environment.")
if not COMPOSIO_API_KEY:
    raise ValueError("COMPOSIO_API_KEY is not set in the environment.")
if not COMPOSIO_USER_ID:
    raise ValueError("COMPOSIO_USER_ID is not set in the environment.")

# Initialize Composio and create a session
composio = Composio(api_key=COMPOSIO_API_KEY)
session = composio.create(
    user_id=COMPOSIO_USER_ID,
    toolkits=["kaggle"],
)
url = session.mcp.url

# Configure LLM
llm = LLM(
    model="gpt-5",
    api_key=os.getenv("OPENAI_API_KEY"),
)

server_params = {
    "url": url,
    "transport": "streamable-http",
    "headers": {"x-api-key": COMPOSIO_API_KEY},
}

with MCPServerAdapter(server_params) as tools:
    agent = Agent(
        role="Search Assistant",
        goal="Help users with internet searches",
        backstory="You are an expert assistant with access to Composio Search tools.",
        tools=tools,
        llm=llm,
        verbose=False,
        max_iter=10,
    )

    print("Chat started! Type 'exit' or 'quit' to end.\n")

    conversation_context = ""

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

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

        if not user_input:
            continue

        conversation_context += f"\nUser: {user_input}\n"
        print("\nAgent is thinking...\n")

        task = Task(
            description=(
                f"Conversation history:\n{conversation_context}\n\n"
                f"Current request: {user_input}"
            ),
            expected_output="A helpful response addressing the user's request",
            agent=agent,
        )

        crew = Crew(agents=[agent], tasks=[task], verbose=False)
        result = crew.kickoff()
        response = str(result)

        conversation_context += f"Agent: {response}\n"
        print(f"Agent: {response}\n")

Conclusion

You now have a CrewAI agent connected to Kaggle through Composio's Tool Router. The agent can perform Kaggle operations through natural language commands.

Next steps:

  • Add role-specific instructions to customize agent behavior
  • Plug in more toolkits for multi-app workflows
  • Chain tasks for complex multi-step operations

How to build Kaggle MCP Agent with another framework

ChatGPT logo

ChatGPT

Use Kaggle MCP with ChatGPT

OpenAI Agents SDK logo

OpenAI Agents SDK

Use Kaggle MCP with OpenAI Agents SDK

Claude Agent SDK logo

Claude Agent SDK

Use Kaggle MCP with Claude Agent SDK

Claude Code logo

Claude Code

Use Kaggle MCP with Claude Code

Claude Cowork logo

Claude Cowork

Use Kaggle MCP with Claude Cowork

Codex logo

Codex

Use Kaggle MCP with Codex

Cursor logo

Cursor

Use Kaggle MCP with Cursor

OpenClaw logo

OpenClaw

Use Kaggle MCP with OpenClaw

Hermes logo

Hermes

Use Kaggle MCP with Hermes

CLI logo

CLI

Use Kaggle MCP with CLI

Google ADK logo

Google ADK

Use Kaggle MCP with Google ADK

LangChain logo

LangChain

Use Kaggle MCP with LangChain

Vercel AI SDK logo

Vercel AI SDK

Use Kaggle MCP with Vercel AI SDK

Mastra AI logo

Mastra AI

Use Kaggle MCP with Mastra AI

LlamaIndex logo

LlamaIndex

Use Kaggle MCP with LlamaIndex

OpenCode logo

OpenCode

Use Kaggle MCP with OpenCode

VS Code logo

VS Code

Use Kaggle MCP with VS Code

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 CrewAI?

Yes, you can. CrewAI 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
Letta
glean
HubSpot
Agent.ai
Altera
DataStax
Entelligence
Rolai
Context
Letta
glean
HubSpot
Agent.ai
Altera
DataStax
Entelligence
Rolai
Context
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.

Get started for freeGet a demo↗