$ loading_
Manage projects and run evaluation, comparison, splitting, and analysis via MCP.
Copy the install command and let the AI configure it · recommended for beginners
No copy-paste install info for "skore-mcp" yet — see the docs or source repo.
Use skore-mcp to run evaluate on my classification project and generate a report summary with key metrics, error inspection, and data analysis.
A summary of evaluation results with main metrics, problematic sample insights, and readable analysis conclusions.
Use skore-mcp to compare results from Experiment A and Experiment B, show metric differences, and explain which performs better and why.
A structured comparison showing metric differences, performance judgment, and a brief explanation.
Use skore-mcp to run train_test_split on the current dataset with an 80/20 split, and report sample counts plus follow-up evaluation suggestions.
A train/test split result with sample counts and recommendations for next evaluation steps.
Publish, author, and reuse AI tools and skills via MCP and REST.
Run dev checks and get compact error summaries for faster debugging.
Analyze MCP tool security risks, detect malicious behavior, and provide risk scores.
Build custom analysis MCP tools via JSON with built-in safety and quality controls.
Analyze project architecture and detect similar code patterns for cross-language consistency.
Turn CVs and projects into MCP tools for querying and job matching.