About this integration
MCP server for the Kaggle API: competitions, datasets, kernels, and models.
- Transport
- stdio
- Authentication
- api-key
- Initial setup
- credentials
- Runtime
- unattended
- Evidence
- documented
- Version
- 0.1.1
- Package
- mcp-server-kaggle
- Last compatibility test
- Not independently tested
Connect your agent
mcp-server-kagglePinned publisher documentation and manifest were reviewed without installing the package or contacting Kaggle. The documented tools include uploads, submissions, creation, updates, and deletion; operations inherit the configured Kaggle account's permissions.
Capabilities: List competitions and manage competition files and submissions, Search, download, create, and version datasets, List, push, pull, and inspect Kaggle kernels, Create, update, download, and delete Kaggle models and instances
Connected profiles
Additional details
io.github.Seif-Sameh/Kaggle-mcp
Source ↗ · Checked 2026-09-170.1.1
Source ↗ · Checked 2026-09-17CC0-1.0; package licenses are separate
Source ↗ · Checked 2026-09-17pypi
Source ↗ · Checked 2026-09-17KAGGLE_USERNAME, KAGGLE_API_KEY
Source ↗ · Checked 2026-09-17mcp-server-kaggle
Source ↗ · Checked 2026-09-190.1.1
Source ↗ · Checked 2026-09-19Publisher documentation describes a client-launched uvx MCP server and standalone executable or Python-module forms.
Source ↗ · Checked 2026-09-19A Kaggle account is required, with KAGGLE_USERNAME and KAGGLE_API_KEY supplied to the server environment or a local environment file.
Source ↗ · Checked 2026-09-19Configure the MCP client to run uvx with mcp-server-kaggle and pass the Kaggle username and API key in the environment.
Source ↗ · Checked 2026-09-19Publisher documentation reviewed; package and integration endpoint not executed or independently security-audited.
Source ↗ · Checked 2026-09-19