Kaggle
Kaggle-MCP provides a bridge between Claude AI and the Kaggle API, enabling AI assistants to interact with Kaggle's competitions, datasets, kernels, and models. The implementation offers a comprehensive set of tools for authenticating with Kaggle, browsing competitions, downloading datasets, managing kernels, and working with machine learning models. Built on the Model Context Protocol, it allows Claude to perform operations like listing active competitions, searching datasets, submitting to competitions, and creating or updating models—all while maintaining proper authentication and file handling. This integration is particularly valuable for data scientists and machine learning practitioners who want to leverage Claude's capabilities while working with Kaggle's resources.
Composite of vulnerability cleanliness, spec conformance, provenance, stability, and usage signals — scanned and weighted by Cognium. Human and agent signals are tracked separately.
View full trust & usage report →Metadata
- Version
- 1.0.0
- Skill type
- atomic
- Execution layer
- mcp-remote
- Category
- ai-ml
- Source
- PulseMCP
- Repository
- github.com/54yyyu/kaggle-mcp
- Author type
- human
- Updated
- 2026-04-29
Use via MCP
Resolve Kaggle from your agent
Streamable HTTP transport at https://api.skillsregistry.net/mcp. No auth for read tools. Discovery: .well-known/mcp.json.
One command in your shell — Claude Code wires it up and verifies the connection. Run /mcp in any session to confirm.
claude mcp add --transport http --scope user skillsregistry https://api.skillsregistry.net/mcp--scope user for --scope project to commit it to .mcp.json.