Kaggle MCP server

Connect Kaggle to Claude, ChatGPT, Cursor, Claude Code, Codex, Gemini, GitHub Copilot and any other MCP client, for your whole team. Metorial adds security, governance, and tracing, and gives everyone one Magic MCP URL to connect.

Deploy KaggleBook a demo

What you can do with the Kaggle MCP server

Ask your agent in plain language. Each of these maps to a real tool on the server.

  • Use the push notebook tool in Kaggle
  • Use the get dataset details tool in Kaggle
  • Use the create dataset tool in Kaggle
  • Use the search models tool in Kaggle
  • Use the get competition details tool in Kaggle
  • Use the search datasets tool in Kaggle

Supported Tools

push_kernel

Push Notebook

Create or update a Kaggle notebook (kernel) and execute it. Push source code to run as a notebook or script. The execution is asynchronous — use "Get Notebook Details" to check the run status afterward.

get_dataset_details

Get Dataset Details

Retrieve detailed information about a specific Kaggle dataset including metadata and file listing. Provide the dataset reference in "owner/dataset" format (e.g., "zillow/zecon").

create_dataset

Create Dataset

Create a new Kaggle dataset or publish a new version of an existing dataset. For new datasets, provide a title and file tokens obtained from file uploads. For new versions, specify the existing dataset reference and version notes.

search_models

Search Models

Search and list Kaggle models. Find models by keyword, owner, and sort by various criteria. Models support multiple variations (e.g., different frameworks like TensorFlow, PyTorch) and each variation can have multiple versions.

get_competition_details

Get Competition Details

Retrieve detailed information about a specific Kaggle competition, including its data files, leaderboard, and your submission history. Provide the competition slug (e.g., "titanic") to get comprehensive details.

search_datasets

Search Datasets

Search and list Kaggle datasets with comprehensive filtering. Find datasets by keyword, file type, license, size range, and tags. Sort results by hotness, votes, updated date, relevance, or size.

manage_model

Manage Model

Create, update, or delete a Kaggle model. Use this tool to manage top-level model resources. For managing model variations and versions, use the "Manage Model Variation" tool instead.

get_model_details

Get Model Details

Retrieve detailed information about a Kaggle model and optionally a specific variation. Provide the model reference as "owner/model-slug" and optionally a framework and variation slug to get a specific instance.

search_competitions

Search Competitions

Search and list Kaggle competitions with filtering options. Find competitions by keyword, category (featured, research, playground, etc.), and sort by various criteria like deadline, recently created, or number of teams.

manage_model_variation

Manage Model Variation

Create, update, or delete a model variation (instance) and manage variation versions. A variation represents a specific framework implementation (e.g., TensorFlow, PyTorch) of a model. You can also create new versions of existing variations.

get_kernel_details

Get Notebook Details

Retrieve source code and execution details for a specific Kaggle notebook (kernel). Optionally fetch execution output and run status. Provide the notebook reference as "username/kernel-slug".

search_kernels

Search Notebooks

Search and list Kaggle notebooks (kernels) with comprehensive filtering. Find notebooks by keyword, dataset, competition, language, type, and author. Sort by hotness, date created, date run, relevance, votes, or views.

download_model_version

Download Model Version

Prepare a downloadable tar.gz archive of a specific Kaggle model variation version. Use get_model_details to discover models and variations.

download_dataset

Download Dataset

Prepare a downloadable ZIP archive of a Kaggle dataset, or download one named file. Use get_dataset_details to discover file names and dataset versions.

download_competition_data

Download Competition Data

Prepare downloadable competition data as a ZIP archive or one named file. Your account must have accepted the competition rules. Use get_competition_details to discover file names.

Connect Kaggle to your AI client

Every client uses the same Magic MCP URL, and so does any other MCP client. Add it once and sign in with SSO.

  1. Enable Kaggle in Metorial. In your Metorial portal, enable the Kaggle MCP server and sign in with the account that owns the data. Access stays governed by your team policies.
  2. Add a custom connector. Open Customize, then Connectors. Select Add, then Custom, then Web.
  3. Paste your Metorial MCP URL. Name it Metorial, paste your Magic MCP URL (<your-magic-mcp-url>) and continue.
  4. Sign in. Select Add and sign in to load Kaggle tools.

Run Kaggle through the Metorial gateway

One governed layer for every app your agents reach, not a separate connector per tool.

  • Give Kaggle and every other app to your whole team through one MCP gateway, behind your SSO.
  • Scope which teams and agents can use Kaggle tools with role-based access control, and trace every call.
  • Prefer to run it yourself? Metorial is open source and self-hostable.

More integrations teams use with Kaggle

GitHub

Manage repositories, issues, and pull requests. Create and configure branches, star repositories, review code, and merge changes. Automate CI/CD workflows with GitHub Actions, manage workflow runs, secrets, and artifacts. Track issues with labels, milestones, and assignees. Search across code, repositories, issues, and users. Manage organizations, teams, and memberships. Create and manage projects, gists, packages, deployments, and environments. Access security alerts including code scanning, secret scanning, and Dependabot alerts. Read and write file contents in repositories. Manage webhooks, notifications, and codespaces.

Salesforce

Manage CRM data including Accounts, Contacts, Leads, Opportunities, Cases, and custom objects. Create, read, update, and delete records. Query data using SOQL and search across objects using SOSL. Perform bulk data operations for large-scale imports, exports, and migrations. Execute composite requests to batch multiple operations in a single API call. Access analytics, reports, and dashboards. Manage files and attachments associated with records. Interact with Chatter feeds, posts, and groups for social collaboration. Manage org metadata including custom objects, fields, layouts, and workflows. Query data using GraphQL for precise data retrieval across related objects.

Sharepoint

Manage SharePoint sites, document libraries, lists, and files. Create, read, update, and delete lists and list items with custom columns. Resolve site users to numeric Person/Group LookupId values. Upload, download, move, copy, and version files in document libraries. Search across sites, files, folders, lists, and list items using Microsoft Search. Manage permissions at site, list, and item levels with granular access control. Define and manage content types and site columns. Retrieve site properties and search for sites across Microsoft 365.

Airtable

Create, read, update, and delete records in Airtable bases and tables. Manage base schemas including creating tables and fields. Filter records using formulas, sort by fields, and scope queries to specific views. Upsert records to find, create, or update in a single call. Upload attachments to records, read and write record comments, list accessible bases, and receive real-time base change events through webhooks.

Sentry

Track, manage, and resolve application errors and performance issues. List, query, and bulk-update issues and error events with filters like status, assignment, and tags. Create and manage releases, associate commits, and upload source maps. Configure issue alert rules and metric alert rules with notification actions. Set up cron monitors to detect missed or failed scheduled jobs. Build custom dashboards with configurable widgets. Run ad-hoc Discover queries across errors and transactions for performance analysis. Manage organizations, teams, projects, and members. Provision users via SCIM. Access session replay data.

Bitbucket

Manage Git repositories, pull requests, and CI/CD pipelines on Bitbucket Cloud. Create, fork, and configure repositories within workspaces and projects. Create, review, approve, merge, and decline pull requests with inline code comments. Browse source code, list commits, and manage branches and tags. Trigger, monitor, and manage Bitbucket Pipelines. List workspace members, configure repository default reviewers and branch restrictions, create and manage repository webhooks, and search code across repositories.

Technical notes for Kaggle

Search Kaggle competitions, datasets, notebooks, and models. Inspect files, leaderboards, submissions, metadata, and execution status; create dataset versions, push notebooks, and manage models and variations. Download dataset and competition data and specific model versions.

Frequently asked questions

Common questions about connecting Kaggle to AI agents with Metorial.

  1. How many tools does the Kaggle MCP server have?
    The Kaggle MCP server exposes 15 tools, including Push Notebook, Get Dataset Details, Create Dataset. Each one is governed and traced through Metorial.
  2. Kaggle exposes tools your agents call on demand; it does not publish event triggers yet. Everything still runs through one governed MCP URL.
  3. Any MCP client, including VS Code, Windsurf, Zed, OpenCode and Grok. Each one reaches the Kaggle MCP server through the same Metorial URL.
  4. Use role-based access control to decide which teams, users, and agents can use Kaggle and which of its tools they can call.
  5. Yes. Metorial is open source, so you can run the Kaggle MCP server yourself or use the hosted gateway.

Connect Kaggle to production AI agents

See how Metorial gives your team governed access to Kaggle, with tracing and security controls built in.

Book a demoDeploy Kaggle