# How to integrate Kaggle MCP with LlamaIndex

```json
{
  "title": "How to integrate Kaggle MCP with LlamaIndex",
  "toolkit": "Kaggle",
  "toolkit_slug": "kaggle",
  "framework": "LlamaIndex",
  "framework_slug": "llama-index",
  "url": "https://composio.dev/toolkits/kaggle/framework/llama-index",
  "markdown_url": "https://composio.dev/toolkits/kaggle/framework/llama-index.md",
  "updated_at": "2026-05-12T10:16:40.031Z"
}
```

## Introduction

This guide walks you through connecting Kaggle to LlamaIndex 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 LlamaIndex 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

- [ChatGPT](https://composio.dev/toolkits/kaggle/framework/chatgpt)
- [OpenAI Agents SDK](https://composio.dev/toolkits/kaggle/framework/open-ai-agents-sdk)
- [Claude Agent SDK](https://composio.dev/toolkits/kaggle/framework/claude-agents-sdk)
- [Claude Code](https://composio.dev/toolkits/kaggle/framework/claude-code)
- [Claude Cowork](https://composio.dev/toolkits/kaggle/framework/claude-cowork)
- [Codex](https://composio.dev/toolkits/kaggle/framework/codex)
- [Cursor](https://composio.dev/toolkits/kaggle/framework/cursor)
- [VS Code](https://composio.dev/toolkits/kaggle/framework/vscode)
- [OpenCode](https://composio.dev/toolkits/kaggle/framework/opencode)
- [OpenClaw](https://composio.dev/toolkits/kaggle/framework/openclaw)
- [Hermes](https://composio.dev/toolkits/kaggle/framework/hermes-agent)
- [CLI](https://composio.dev/toolkits/kaggle/framework/cli)
- [Google ADK](https://composio.dev/toolkits/kaggle/framework/google-adk)
- [LangChain](https://composio.dev/toolkits/kaggle/framework/langchain)
- [Vercel AI SDK](https://composio.dev/toolkits/kaggle/framework/ai-sdk)
- [Mastra AI](https://composio.dev/toolkits/kaggle/framework/mastra-ai)
- [CrewAI](https://composio.dev/toolkits/kaggle/framework/crew-ai)

## TL;DR

Here's what you'll learn:
- Set your OpenAI and Composio API keys
- Install LlamaIndex and Composio packages
- Create a Composio Tool Router session for Kaggle
- Connect LlamaIndex to the Kaggle MCP server
- Build a Kaggle-powered agent using LlamaIndex
- Interact with Kaggle through natural language

## What is LlamaIndex?

LlamaIndex is a data framework for building LLM applications. It provides tools for connecting LLMs to external data sources and services through agents and tools.
Key features include:
- ReAct Agent: Reasoning and acting pattern for tool-using agents
- MCP Tools: Native support for Model Context Protocol
- Context Management: Maintain conversation context across interactions
- Async Support: Built for async/await patterns

## 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

| Tool slug | Name | Description |
|---|---|---|
| `KAGGLE_COMPETITION_DOWNLOAD_FILES` | Download competition data files | Downloads all data files for a Kaggle competition as a single zip archive. Returns the local file path where the zip was saved. Note: You must have accepted the competition's rules on Kaggle's website before downloading (403 error if not accepted). |
| `KAGGLE_COMPETITION_SUBMIT` | Submit Competition Entry | Submit an entry to a Kaggle competition using a previously uploaded file. Prerequisites: 1. You must have accepted the competition rules on Kaggle's website 2. You must have uploaded your submission file and obtained a blob_file_tokens (use Kaggle's file upload API endpoint first) This action performs the final submission step after file upload. The blob token identifies your uploaded file and associates it with your competition submission. |
| `KAGGLE_CONFIG_DIR` | Get Kaggle Config Directory | Tool to retrieve the directory of the Kaggle API configuration file. Use when you need to locate the directory containing your kaggle.json credentials. |
| `KAGGLE_CONFIG_INIT` | Initialize Kaggle Configuration | Initialize Kaggle API client configuration. This action sets up the necessary configuration file for Kaggle API access by first attempting to use the Kaggle CLI's 'kaggle config init' command. If the CLI is unavailable, it falls back to creating a kaggle.json file at ~/.kaggle/kaggle.json (or $KAGGLE_CONFIG_DIR/kaggle.json if that environment variable is set). The action is idempotent - if configuration already exists, it will not overwrite it. No parameters are required; the action uses environment variables and metadata when available. Run this before other Kaggle actions when credentials are missing or when KAGGLE_CONFIG_VIEW returns empty/error output. |
| `KAGGLE_CONFIG_KEYS` | List Kaggle Configuration Keys | Tool to list local Kaggle API configuration keys. Use when you need to see which configuration options are set without revealing values. |
| `KAGGLE_CONFIG_PATH` | Get Kaggle Config Path | Tool to retrieve local Kaggle API configuration file path. Use when you need to know the location of the Kaggle config before operations. |
| `KAGGLE_CONFIG_RESET` | Reset Kaggle Configuration | Tool to reset local Kaggle CLI configuration to defaults. Clears CLI-managed keys ('competition', 'path', 'proxy'). |
| `KAGGLE_CONFIG_SET` | Set Kaggle Configuration | Tool to set a Kaggle CLI configuration parameter. Use when updating local CLI settings such as default download path or proxy. Ensure Kaggle CLI is installed. |
| `KAGGLE_CONFIG_UNSET` | Unset Kaggle Configuration | Tool to unset a Kaggle CLI configuration parameter. Use when removing local CLI settings such as default download path or proxy. Ensure Kaggle CLI is installed. |
| `KAGGLE_CONFIG_VIEW` | View Kaggle Configuration | View local Kaggle API credentials and configuration settings. This action reads Kaggle configuration from local sources (does NOT make API calls to Kaggle). Configuration is retrieved in the following precedence order: 1. kaggle.json file (from KAGGLE_CONFIG_DIR env var, ~/.config/kaggle/, or ~/.kaggle/) 2. 'kaggle config view' CLI output (for proxy/path settings) 3. Environment variables (KAGGLE_USERNAME, KAGGLE_KEY) 4. Authorization header from metadata Use this action to: - Verify Kaggle credentials are configured before making API calls - Check current proxy settings - Debug authentication issues Returns empty strings for username/key if no credentials are found; use KAGGLE_CONFIG_INIT to set up credentials first. Note: username and key are independent — an empty username field does not indicate missing or invalid credentials. WARNING: This action returns sensitive API key data in plain text. |
| `KAGGLE_DATASET_CREATE` | Dataset Create | Create a new Kaggle dataset with metadata. IMPORTANT: Dataset creation requires at least one data file. Ensure files are uploaded before calling this action. The 'id' field must use your authenticated Kaggle username as the owner. Returns the creation status and any message from the Kaggle API. |
| `KAGGLE_DATASET_INIT` | Kaggle Dataset Init | Tool to initialize a dataset-metadata.json file in a local folder. Use when preparing a dataset folder before uploading to Kaggle. |
| `KAGGLE_DATASET_LIST_FILES` | List Kaggle Dataset Files | Tool to list files in a Kaggle dataset. Use when you need to retrieve paginated file listings by owner and dataset slugs, with optional version and paging controls. |
| `KAGGLE_DATASET_STATUS` | Get Dataset Status | Check the processing status of a Kaggle dataset after creation or version update. This endpoint is used to monitor datasets that are currently being processed by Kaggle's servers. It returns status information for datasets that are actively uploading, processing, or experiencing errors. For already-published datasets, this endpoint typically returns 404 (Not Found), which is expected behavior. Use this tool immediately after creating a new dataset (KAGGLE_DATASET_CREATE) or updating an existing dataset version (KAGGLE_DATASET_VERSION) to check when the dataset becomes ready. Poll this endpoint periodically until the status indicates completion or error. |
| `KAGGLE_DATASET_VERSION` | Create Dataset Version | Create a new version of an existing Kaggle dataset. Prerequisites: - You must own the dataset or have edit permissions - Files must be uploaded first to obtain upload tokens (required for the 'files' parameter) Use this when you have updated files or metadata and need to publish a new version of an existing dataset. |
| `KAGGLE_DOWNLOAD_COMPETITION_FILE` | Download competition file | Tool to download a specific data file from a Kaggle competition. Use when you need to retrieve a single file from a competition by specifying the competition slug and filename. Note: You must have accepted the competition's rules on Kaggle's website before downloading. |
| `KAGGLE_DOWNLOAD_COMPETITION_LEADERBOARD` | Download competition leaderboard | Tool to download the entire competition leaderboard as a CSV file packaged in a ZIP archive. Use when you need to analyze or review competition standings and scores. |
| `KAGGLE_DOWNLOAD_DATASET` | Download Kaggle Dataset | Tool to download all files from a Kaggle dataset as a zip archive. Supports downloading specific versions by providing the dataset_version_number parameter. |
| `KAGGLE_DOWNLOAD_DATASET_FILE` | Download Kaggle Dataset File | Tool to download a specific file from a Kaggle dataset. Use when you need to retrieve a single file from a dataset by specifying the owner, dataset, and filename. |
| `KAGGLE_GENERATE_COMPETITION_SUBMISSION_URL` | Generate Competition Submission URL | Tool to generate a pre-signed URL for uploading competition submission files. Use this before uploading your submission file to Kaggle. This action generates a temporary upload URL and token for submitting to a competition. You must provide the competition ID, file size, and last modified timestamp. After obtaining the URL, upload your submission file to the createUrl, then use the token to finalize the submission. |
| `KAGGLE_GET_DATASET_METADATA` | Get Dataset Metadata | Tool to get comprehensive metadata for a Kaggle dataset including title, description, licenses, and tags. Use when you need detailed information about a dataset's structure, schema, or properties. |
| `KAGGLE_GET_MODEL` | Get Model Details | Tool to get a Kaggle model's details including metadata and description. Use when you need information about a specific model on Kaggle. |
| `KAGGLE_GET_MODEL_INSTANCE` | Get Model Instance Details | Tool to get details for a specific Kaggle model instance (variation). Returns metadata including overview, usage instructions, download URL, version information, and license details. Use when you need to inspect or retrieve information about a specific model variation before downloading or using it. |
| `KAGGLE_KERNEL_INIT` | Kaggle Kernel Init | Initialize a kernel-metadata.json template file in a specified folder. This file is required before pushing/uploading a kernel to Kaggle. The template includes default values for kernel configuration (language, kernel_type, GPU settings, etc.) that can be customized before pushing. Use this when setting up a new Kaggle kernel locally. |
| `KAGGLE_KERNEL_OUTPUT` | Download kernel output | Tool to download the output of a Kaggle kernel. Use when needing the latest kernel results locally. |
| `KAGGLE_KERNELS_STATUS` | Get Kernel Status | Get the execution status of a Kaggle kernel (notebook). Returns current status (running, complete, error), timestamps, and output URL. Use this to monitor kernel execution after pushing/submitting a kernel. Note: You need permission to access the kernel - typically only your own kernels or public kernels you have access to. |
| `KAGGLE_LIST_COMPETITION_FILES` | List competition data files | Tool to list all data files available for a Kaggle competition. Use when you need to retrieve file names, sizes, and metadata for competition datasets before downloading. |
| `KAGGLE_LIST_COMPETITIONS` | List Kaggle Competitions | Tool to list available Kaggle competitions with filters and pagination. Use when you need to discover competitions, search by keywords, or filter by category, group, and sorting options. |
| `KAGGLE_LIST_DATASETS` | List Kaggle Datasets | Tool to list Kaggle datasets with filters and pagination. Use after authenticating with Kaggle API key. |
| `KAGGLE_LIST_KERNEL_OUTPUT_FILES` | List Kernel Output Files | Tool to list output files for a specific kernel run. Use when you need to retrieve paginated file listings by kernel owner and slug. |
| `KAGGLE_LIST_KERNELS` | List Kaggle Kernels | Tool to list Kaggle kernels (notebooks and scripts) with filters and pagination. Use to discover kernels by search terms, user, language, type, competition, or dataset. |
| `KAGGLE_LIST_MODEL_INSTANCE_VERSION_FILES` | List Model Instance Version Files | Tool to list files for a specific version of a model variation. Use when you need to retrieve files for a particular model framework instance version by owner, model, framework, variation, and version. |
| `KAGGLE_LIST_MODELS` | List Kaggle Models | Tool to list Kaggle models with optional filters for owner, sorting, search, and pagination. Use to discover available models on Kaggle's platform. |
| `KAGGLE_PULL_KERNEL` | Pull Kernel Code | Tool to pull (download) the source code of a Kaggle kernel to local storage. Use when you need to retrieve a kernel's notebook, script, or metadata files. Optionally include metadata JSON file with kernel configuration details. |
| `KAGGLE_VIEW_COMPETITION_LEADERBOARD` | View competition leaderboard | Tool to view competition leaderboard information showing rankings and scores of participants. Use when you need to check competition standings, team scores, or analyze leaderboard positions. |

## Supported Triggers

None listed.

## Creating MCP Server - Stand-alone vs Composio SDK

The Kaggle MCP server is an implementation of the Model Context Protocol that connects your AI agent to Kaggle. It provides structured and secure access so your agent can perform Kaggle operations on your behalf through a secure, permission-based interface.
With Composio's managed implementation, you don't have to create your own developer app. For production, if you're building an end product, we recommend using your own credentials. The managed server helps you prototype fast and go from 0-1 faster.

## Step-by-step Guide

### 1. Prerequisites

Before you begin, make sure you have:
- Python 3.8/Node 16 or higher installed
- A Composio account with the API key
- An OpenAI API key
- A Kaggle account and project
- Basic familiarity with async Python/Typescript

### 1. Getting API Keys for OpenAI, Composio, and Kaggle

No description provided.

### 2. Installing dependencies

No description provided.
```python
pip install composio-llamaindex llama-index llama-index-llms-openai llama-index-tools-mcp python-dotenv
```

```typescript
npm install @composio/llamaindex @llamaindex/openai @llamaindex/tools @llamaindex/workflow dotenv
```

### 3. Set environment variables

Create a .env file in your project root:
These credentials will be used to:
- Authenticate with OpenAI's GPT-5 model
- Connect to Composio's Tool Router
- Identify your Composio user session for Kaggle access
```bash
OPENAI_API_KEY=your-openai-api-key
COMPOSIO_API_KEY=your-composio-api-key
COMPOSIO_USER_ID=your-user-id
```

### 4. Import modules

No description provided.
```python
import asyncio
import os
import dotenv

from composio import Composio
from composio_llamaindex import LlamaIndexProvider
from llama_index.core.agent.workflow import ReActAgent
from llama_index.core.workflow import Context
from llama_index.llms.openai import OpenAI
from llama_index.tools.mcp import BasicMCPClient, McpToolSpec

dotenv.load_dotenv()
```

```typescript
import "dotenv/config";
import readline from "node:readline/promises";
import { stdin as input, stdout as output } from "node:process";

import { Composio } from "@composio/core";

import { mcp } from "@llamaindex/tools";
import { agent as createAgent } from "@llamaindex/workflow";
import { openai } from "@llamaindex/openai";

dotenv.config();
```

### 5. Load environment variables and initialize Composio

No description provided.
```python
OPENAI_API_KEY = os.getenv("OPENAI_API_KEY")
COMPOSIO_API_KEY = os.getenv("COMPOSIO_API_KEY")
COMPOSIO_USER_ID = os.getenv("COMPOSIO_USER_ID")

if not OPENAI_API_KEY:
    raise ValueError("OPENAI_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")
```

```typescript
const OPENAI_API_KEY = process.env.OPENAI_API_KEY;
const COMPOSIO_API_KEY = process.env.COMPOSIO_API_KEY;
const COMPOSIO_USER_ID = process.env.COMPOSIO_USER_ID;

if (!OPENAI_API_KEY) throw new Error("OPENAI_API_KEY is not set");
if (!COMPOSIO_API_KEY) throw new Error("COMPOSIO_API_KEY is not set");
if (!COMPOSIO_USER_ID) throw new Error("COMPOSIO_USER_ID is not set");
```

### 6. Create a Tool Router session and build the agent function

What's happening here:
- We create a Composio client using your API key and configure it with the LlamaIndex provider
- We then create a tool router MCP session for your user, specifying the toolkits we want to use (in this case, kaggle)
- The session returns an MCP HTTP endpoint URL that acts as a gateway to all your configured tools
- LlamaIndex will connect to this endpoint to dynamically discover and use the available Kaggle tools.
- The MCP tools are mapped to LlamaIndex-compatible tools and plug them into the Agent.
```python
async def build_agent() -> ReActAgent:
    composio_client = Composio(
        api_key=COMPOSIO_API_KEY,
        provider=LlamaIndexProvider(),
    )

    session = composio_client.create(
        user_id=COMPOSIO_USER_ID,
        toolkits=["kaggle"],
    )

    mcp_url = session.mcp.url
    print(f"Composio MCP URL: {mcp_url}")

    mcp_client = BasicMCPClient(mcp_url, headers={"x-api-key": COMPOSIO_API_KEY})
    mcp_tool_spec = McpToolSpec(client=mcp_client)
    tools = await mcp_tool_spec.to_tool_list_async()

    llm = OpenAI(model="gpt-5")

    description = "An agent that uses Composio Tool Router MCP tools to perform Kaggle actions."
    system_prompt = """
    You are a helpful assistant connected to Composio Tool Router.
    Use the available tools to answer user queries and perform Kaggle actions.
    """
    return ReActAgent(tools=tools, llm=llm, description=description, system_prompt=system_prompt, verbose=True)
```

```typescript
async function buildAgent() {

  console.log(`Initializing Composio client...${COMPOSIO_USER_ID!}...`);
  console.log(`COMPOSIO_USER_ID: ${COMPOSIO_USER_ID!}...`);

  const composio = new Composio({
    apiKey: COMPOSIO_API_KEY,
    provider: new LlamaindexProvider(),
  });

  const session = await composio.create(
    COMPOSIO_USER_ID!,
    {
      toolkits: ["kaggle"],
    },
  );

  const mcpUrl = session.mcp.url;
  console.log(`Composio Tool Router MCP URL: ${mcpUrl}`);

  const server = mcp({
    url: mcpUrl,
    clientName: "composio_tool_router_with_llamaindex",
    requestInit: {
      headers: {
        "x-api-key": COMPOSIO_API_KEY!,
      },
    },
    // verbose: true,
  });

  const tools = await server.tools();

  const llm = openai({ apiKey: OPENAI_API_KEY, model: "gpt-5" });

  const agent = createAgent({
    name: "composio_tool_router_with_llamaindex",
        description : "An agent that uses Composio Tool Router MCP tools to perform actions.",
    systemPrompt:
      "You are a helpful assistant connected to Composio Tool Router."+
"Use the available tools to answer user queries and perform Kaggle actions." ,
    llm,
    tools,
  });

  return agent;
}
```

### 7. Create an interactive chat loop

No description provided.
```python
async def chat_loop(agent: ReActAgent) -> None:
    ctx = Context(agent)
    print("Type 'quit', 'exit', or Ctrl+C to stop.")

    while True:
        try:
            user_input = input("\nYou: ").strip()
        except (KeyboardInterrupt, EOFError):
            print("\nBye!")
            break

        if not user_input or user_input.lower() in {"quit", "exit"}:
            print("Bye!")
            break

        try:
            print("Agent: ", end="", flush=True)
            handler = agent.run(user_input, ctx=ctx)

            async for event in handler.stream_events():
                # Stream token-by-token from LLM responses
                if hasattr(event, "delta") and event.delta:
                    print(event.delta, end="", flush=True)
                # Show tool calls as they happen
                elif hasattr(event, "tool_name"):
                    print(f"\n[Using tool: {event.tool_name}]", flush=True)

            # Get final response
            response = await handler
            print()  # Newline after streaming
        except KeyboardInterrupt:
            print("\n[Interrupted]")
            continue
        except Exception as e:
            print(f"\nError: {e}")
```

```typescript
async function chatLoop(agent: ReturnType<typeof createAgent>) {
  const rl = readline.createInterface({ input, output });

  console.log("Type 'quit' or 'exit' to stop.");

  while (true) {
    let userInput: string;

    try {
      userInput = (await rl.question("\nYou: ")).trim();
    } catch {
      console.log("\nAgent: Bye!");
      break;
    }

    if (!userInput) {
      continue;
    }

    const lower = userInput.toLowerCase();
    if (lower === "quit" || lower === "exit") {
      console.log("Agent: Bye!");
      break;
    }

    try {
      process.stdout.write("Agent: ");

      const stream = agent.runStream(userInput);
      let finalResult: any = null;

      for await (const event of stream) {
        // The event.data contains the streamed content
        const data: any = event.data;

        // Check for streaming delta content
        if (data?.delta) {
          process.stdout.write(data.delta);
        }

        // Store final result for fallback
        if (data?.result || data?.message) {
          finalResult = data;
        }
      }

      // If no streaming happened, show the final result
      if (finalResult) {
        const answer =
          finalResult.result ??
          finalResult.message?.content ??
          finalResult.message ??
          "";
        if (answer && typeof answer === "string" && !answer.includes("[object")) {
          process.stdout.write(answer);
        }
      }

      console.log(); // New line after streaming completes
    } catch (err: any) {
      console.error("\nAgent error:", err?.message ?? err);
    }
  }

  rl.close();
}
```

### 8. Define the main entry point

What's happening here:
- We're orchestrating the entire application flow
- The agent gets built with proper error handling
- Then we kick off the interactive chat loop so you can start talking to Kaggle
```python
async def main() -> None:
    agent = await build_agent()
    await chat_loop(agent)

if __name__ == "__main__":
    # Handle Ctrl+C gracefully
    signal.signal(signal.SIGINT, lambda s, f: (print("\nBye!"), exit(0)))
    try:
        asyncio.run(main())
    except KeyboardInterrupt:
        print("\nBye!")
```

```typescript
async function main() {
  try {
    const agent = await buildAgent();
    await chatLoop(agent);
  } catch (err) {
    console.error("Failed to start agent:", err);
    process.exit(1);
  }
}

main();
```

### 9. Run the agent

When prompted, authenticate and authorise your agent with Kaggle, then start asking questions.
```bash
python llamaindex_agent.py
```

```typescript
npx ts-node llamaindex-agent.ts
```

## Complete Code

```python
import asyncio
import os
import signal
import dotenv

from composio import Composio
from composio_llamaindex import LlamaIndexProvider
from llama_index.core.agent.workflow import ReActAgent
from llama_index.core.workflow import Context
from llama_index.llms.openai import OpenAI
from llama_index.tools.mcp import BasicMCPClient, McpToolSpec

dotenv.load_dotenv()

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

if not OPENAI_API_KEY:
    raise ValueError("OPENAI_API_KEY is not set")
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")

async def build_agent() -> ReActAgent:
    composio_client = Composio(
        api_key=COMPOSIO_API_KEY,
        provider=LlamaIndexProvider(),
    )

    session = composio_client.create(
        user_id=COMPOSIO_USER_ID,
        toolkits=["kaggle"],
    )

    mcp_url = session.mcp.url
    print(f"Composio MCP URL: {mcp_url}")

    mcp_client = BasicMCPClient(mcp_url, headers={"x-api-key": COMPOSIO_API_KEY})
    mcp_tool_spec = McpToolSpec(client=mcp_client)
    tools = await mcp_tool_spec.to_tool_list_async()

    llm = OpenAI(model="gpt-5")
    description = "An agent that uses Composio Tool Router MCP tools to perform Kaggle actions."
    system_prompt = """
    You are a helpful assistant connected to Composio Tool Router.
    Use the available tools to answer user queries and perform Kaggle actions.
    """
    return ReActAgent(
        tools=tools,
        llm=llm,
        description=description,
        system_prompt=system_prompt,
        verbose=True,
    );

async def chat_loop(agent: ReActAgent) -> None:
    ctx = Context(agent)
    print("Type 'quit', 'exit', or Ctrl+C to stop.")

    while True:
        try:
            user_input = input("\nYou: ").strip()
        except (KeyboardInterrupt, EOFError):
            print("\nBye!")
            break

        if not user_input or user_input.lower() in {"quit", "exit"}:
            print("Bye!")
            break

        try:
            print("Agent: ", end="", flush=True)
            handler = agent.run(user_input, ctx=ctx)

            async for event in handler.stream_events():
                # Stream token-by-token from LLM responses
                if hasattr(event, "delta") and event.delta:
                    print(event.delta, end="", flush=True)
                # Show tool calls as they happen
                elif hasattr(event, "tool_name"):
                    print(f"\n[Using tool: {event.tool_name}]", flush=True)

            # Get final response
            response = await handler
            print()  # Newline after streaming
        except KeyboardInterrupt:
            print("\n[Interrupted]")
            continue
        except Exception as e:
            print(f"\nError: {e}")

async def main() -> None:
    agent = await build_agent()
    await chat_loop(agent)

if __name__ == "__main__":
    # Handle Ctrl+C gracefully
    signal.signal(signal.SIGINT, lambda s, f: (print("\nBye!"), exit(0)))
    try:
        asyncio.run(main())
    except KeyboardInterrupt:
        print("\nBye!")
```

```typescript
import "dotenv/config";
import readline from "node:readline/promises";
import { stdin as input, stdout as output } from "node:process";

import { Composio } from "@composio/core";
import { LlamaindexProvider } from "@composio/llamaindex";

import { mcp } from "@llamaindex/tools";
import { agent as createAgent } from "@llamaindex/workflow";
import { openai } from "@llamaindex/openai";

dotenv.config();

const OPENAI_API_KEY = process.env.OPENAI_API_KEY;
const COMPOSIO_API_KEY = process.env.COMPOSIO_API_KEY;
const COMPOSIO_USER_ID = process.env.COMPOSIO_USER_ID;

if (!OPENAI_API_KEY) {
    throw new Error("OPENAI_API_KEY is not set in the environment");
  }
if (!COMPOSIO_API_KEY) {
    throw new Error("COMPOSIO_API_KEY is not set in the environment");
  }
if (!COMPOSIO_USER_ID) {
    throw new Error("COMPOSIO_USER_ID is not set in the environment");
  }

async function buildAgent() {

  console.log(`Initializing Composio client...${COMPOSIO_USER_ID!}...`);
  console.log(`COMPOSIO_USER_ID: ${COMPOSIO_USER_ID!}...`);

  const composio = new Composio({
    apiKey: COMPOSIO_API_KEY,
    provider: new LlamaindexProvider(),
  });

  const session = await composio.create(
    COMPOSIO_USER_ID!,
    {
      toolkits: ["kaggle"],
    },
  );

  const mcpUrl = session.mcp.url;
  console.log(`Composio Tool Router MCP URL: ${mcpUrl}`);

  const server = mcp({
    url: mcpUrl,
    clientName: "composio_tool_router_with_llamaindex",
    requestInit: {
      headers: {
        "x-api-key": COMPOSIO_API_KEY!,
      },
    },
    // verbose: true,
  });

  const tools = await server.tools();

  const llm = openai({ apiKey: OPENAI_API_KEY, model: "gpt-5" });

  const agent = createAgent({
    name: "composio_tool_router_with_llamaindex",
    description:
      "An agent that uses Composio Tool Router MCP tools to perform actions.",
    systemPrompt:
      "You are a helpful assistant connected to Composio Tool Router."+
"Use the available tools to answer user queries and perform Kaggle actions." ,
    llm,
    tools,
  });

  return agent;
}

async function chatLoop(agent: ReturnType<typeof createAgent>) {
  const rl = readline.createInterface({ input, output });

  console.log("Type 'quit' or 'exit' to stop.");

  while (true) {
    let userInput: string;

    try {
      userInput = (await rl.question("\nYou: ")).trim();
    } catch {
      console.log("\nAgent: Bye!");
      break;
    }

    if (!userInput) {
      continue;
    }

    const lower = userInput.toLowerCase();
    if (lower === "quit" || lower === "exit") {
      console.log("Agent: Bye!");
      break;
    }

    try {
      process.stdout.write("Agent: ");

      const stream = agent.runStream(userInput);
      let finalResult: any = null;

      for await (const event of stream) {
        // The event.data contains the streamed content
        const data: any = event.data;

        // Check for streaming delta content
        if (data?.delta) {
          process.stdout.write(data.delta);
        }

        // Store final result for fallback
        if (data?.result || data?.message) {
          finalResult = data;
        }
      }

      // If no streaming happened, show the final result
      if (finalResult) {
        const answer =
          finalResult.result ??
          finalResult.message?.content ??
          finalResult.message ??
          "";
        if (answer && typeof answer === "string" && !answer.includes("[object")) {
          process.stdout.write(answer);
        }
      }

      console.log(); // New line after streaming completes
    } catch (err: any) {
      console.error("\nAgent error:", err?.message ?? err);
    }
  }

  rl.close();
}

async function main() {
  try {
    const agent = await buildAgent();
    await chatLoop(agent);
  } catch (err: any) {
    console.error("Failed to start agent:", err?.message ?? err);
    process.exit(1);
  }
}

main();
```

## Conclusion

You've successfully connected Kaggle to LlamaIndex through Composio's Tool Router MCP layer.
Key takeaways:
- Tool Router dynamically exposes Kaggle tools through an MCP endpoint
- LlamaIndex's ReActAgent handles reasoning and orchestration; Composio handles integrations
- The agent becomes more capable without increasing prompt size
- Async Python provides clean, efficient execution of agent workflows
You can easily extend this to other toolkits like Gmail, Notion, Stripe, GitHub, and more by adding them to the toolkits parameter.

## How to build Kaggle MCP Agent with another framework

- [ChatGPT](https://composio.dev/toolkits/kaggle/framework/chatgpt)
- [OpenAI Agents SDK](https://composio.dev/toolkits/kaggle/framework/open-ai-agents-sdk)
- [Claude Agent SDK](https://composio.dev/toolkits/kaggle/framework/claude-agents-sdk)
- [Claude Code](https://composio.dev/toolkits/kaggle/framework/claude-code)
- [Claude Cowork](https://composio.dev/toolkits/kaggle/framework/claude-cowork)
- [Codex](https://composio.dev/toolkits/kaggle/framework/codex)
- [Cursor](https://composio.dev/toolkits/kaggle/framework/cursor)
- [VS Code](https://composio.dev/toolkits/kaggle/framework/vscode)
- [OpenCode](https://composio.dev/toolkits/kaggle/framework/opencode)
- [OpenClaw](https://composio.dev/toolkits/kaggle/framework/openclaw)
- [Hermes](https://composio.dev/toolkits/kaggle/framework/hermes-agent)
- [CLI](https://composio.dev/toolkits/kaggle/framework/cli)
- [Google ADK](https://composio.dev/toolkits/kaggle/framework/google-adk)
- [LangChain](https://composio.dev/toolkits/kaggle/framework/langchain)
- [Vercel AI SDK](https://composio.dev/toolkits/kaggle/framework/ai-sdk)
- [Mastra AI](https://composio.dev/toolkits/kaggle/framework/mastra-ai)
- [CrewAI](https://composio.dev/toolkits/kaggle/framework/crew-ai)

## Related Toolkits

- [Composio](https://composio.dev/toolkits/composio) - Composio is an integration platform that connects AI agents with hundreds of business tools. It streamlines authentication and lets you trigger actions across services—no custom code needed.
- [Composio search](https://composio.dev/toolkits/composio_search) - Composio search is a unified web search toolkit spanning travel, e-commerce, news, financial markets, images, and more. It lets you and your apps tap into up-to-date web data from a single, easy-to-integrate service.
- [Perplexityai](https://composio.dev/toolkits/perplexityai) - Perplexityai delivers natural, conversational AI models for generating human-like text. Instantly get context-aware, high-quality responses for chat, search, or complex workflows.
- [Browser tool](https://composio.dev/toolkits/browser_tool) - Browser tool is a virtual browser integration that lets AI agents interact with the web programmatically. It enables automated browsing, scraping, and action-taking from any AI workflow.
- [Ai ml api](https://composio.dev/toolkits/ai_ml_api) - Ai ml api is a suite of AI/ML models for natural language and image tasks. It provides fast, scalable access to advanced AI capabilities for your apps and workflows.
- [Aivoov](https://composio.dev/toolkits/aivoov) - Aivoov is an AI-powered text-to-speech platform offering 1,000+ voices in over 150 languages. Instantly turn written content into natural, human-like audio for any application.
- [All images ai](https://composio.dev/toolkits/all_images_ai) - All-Images.ai is an AI-powered image generation and management platform. It helps you create, search, and organize images effortlessly with advanced AI capabilities.
- [Anthropic administrator](https://composio.dev/toolkits/anthropic_administrator) - Anthropic administrator is an API for managing Anthropic organizational resources like members, workspaces, and API keys. It helps you automate admin tasks and streamline resource management across your Anthropic organization.
- [Api labz](https://composio.dev/toolkits/api_labz) - Api labz is a platform offering a suite of AI-driven APIs and workflow tools. It helps developers automate tasks and build smarter, more efficient applications.
- [Apipie ai](https://composio.dev/toolkits/apipie_ai) - Apipie ai is an AI model aggregator offering a single API for accessing top AI models from multiple providers. It helps developers build cost-efficient, latency-optimized AI solutions without juggling multiple integrations.
- [Astica ai](https://composio.dev/toolkits/astica_ai) - Astica ai provides APIs for computer vision, NLP, and voice synthesis. Integrate advanced AI features into your app with a single API key.
- [Bigml](https://composio.dev/toolkits/bigml) - BigML is a machine learning platform that lets you build, train, and deploy predictive models from your data. Its intuitive interface and robust API make machine learning accessible and efficient.
- [Botbaba](https://composio.dev/toolkits/botbaba) - Botbaba is a platform for building, managing, and deploying conversational AI chatbots across messaging channels. It streamlines chatbot automation, making it easier to integrate AI into customer interactions.
- [Botpress](https://composio.dev/toolkits/botpress) - Botpress is an open-source platform for building, deploying, and managing chatbots. It helps teams automate conversations and deliver rich, interactive messaging experiences.
- [Chatbotkit](https://composio.dev/toolkits/chatbotkit) - Chatbotkit is a platform for building and managing AI-powered chatbots using robust APIs and SDKs. It lets you easily add conversational AI to your apps for better user engagement.
- [Cody](https://composio.dev/toolkits/cody) - Cody is an AI assistant built for businesses, trained on your company's knowledge and data. It delivers instant answers and insights, tailored for your team.
- [Context7 MCP](https://composio.dev/toolkits/context7_mcp) - Context7 MCP delivers live, version-specific code docs and examples right from the source. It helps developers and AI agents instantly retrieve authoritative programming info—no more out-of-date docs.
- [Customgpt](https://composio.dev/toolkits/customgpt) - CustomGPT.ai lets you build and deploy chatbots tailored to your own data and business needs. Get precise and context-aware AI conversations without writing code.
- [Datarobot](https://composio.dev/toolkits/datarobot) - Datarobot is a machine learning platform that automates model development, deployment, and monitoring. It empowers organizations to quickly gain predictive insights from large datasets.
- [Deepgram](https://composio.dev/toolkits/deepgram) - Deepgram is an AI-powered speech recognition platform for accurate audio transcription and understanding. It enables fast, scalable speech-to-text with advanced audio intelligence features.

## Frequently Asked Questions

### 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 LlamaIndex?

Yes, you can. LlamaIndex 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.

---
[See all toolkits](https://composio.dev/toolkits) · [Composio docs](https://docs.composio.dev/llms.txt)