Back to code-only MCP servers

mcp-ml-lab

updated this year

ML Experiment Runner MCP : natural-language MLrun_experiment("compare XGBoost vs LightGBM on this CSV with these hyperparam ranges, return Pareto frontier of accuracy vs training time"). Includes model training, cross-validation, hyperparameter search, leaderboard, run comparison, simple report generation.

Code-only MCP server: no hosted endpoint, so you install and run it yourself. It is not probed, graded or counted in our reachability statistics.

Get it

Repository
github.com/rohithraju-ops/mcp-ml-lab
Package
pypi: mcp-ml-lab
Run (stdio)
uvx mcp-ml-lab
The usual command for this package registry; check the repository README for required settings.
License
MIT
Last update
2026-05-29
GitHub stars
★ 0

Listed in

Run this server as a hosted endpoint? Submit the endpoint and it moves to the remote directory, where it is probed and graded.