MCP Tools Directory
← Browse integrations

Developer tools

Safe Kaggle MCP

Free account · sign-in required

Contact Safe Kaggle MCP

Loading secure sign-in…

Tools for autonomous AI agents

About this integration

Safety-first Kaggle MCP — confirm-gated destructive ops, submission budget, injection-fenced.

Transport
stdio
Authentication
api-key
Initial setup
credentials
Runtime
unattended
Evidence
documented
Version
0.4.1
Package
safe-kaggle-mcp
Last compatibility test
Not independently tested

Connect your agent

safe-kaggle-mcp

Publisher README and manifest reviewed offline; documented configuration only; package and endpoint were not executed or independently security-audited. Destructive and public-publish tools are documented as opt-in and confirmation-gated.

Capabilities: Dataset discovery, Competition analysis, Notebook execution workflows, Guarded submissions

Connected profiles

Additional details

Registry identifier

io.github.parkseokjune/kaggle-mcp

Source ↗ · Checked 2026-09-17
Published version

0.4.1

Source ↗ · Checked 2026-09-17
Metadata license

CC0-1.0; package licenses are separate

Source ↗ · Checked 2026-09-17
Package ecosystem

pypi

Source ↗ · Checked 2026-09-17
Source artifact

safe-kaggle-mcp

Source ↗ · Checked 2026-09-19
Source manifest version

0.4.2

Source ↗ · Checked 2026-09-19
Unattended configuration

The publisher documents an explicit local stdio registration command.

Source ↗ · Checked 2026-09-19
Authentication and prerequisites

Kaggle authentication uses either a current API token or the legacy username/key pair.

Source ↗ · Checked 2026-09-19
Connection configuration

The MCP client launches kaggle-mcp from the safe-kaggle-mcp distribution through uvx.

Source ↗ · Checked 2026-09-19
Review scope

Publisher documentation reviewed; package and integration endpoint not executed or independently security-audited.

Source ↗ · Checked 2026-09-19