data

MCP tool from Harness Ml by msilverblatt

Ingest sources, validate, fill nulls, rename, derive columns, manage views, upload to Drive/Kaggle

How to use it

data is exposed by the Harness Ml MCP server. Add the server to your MCP client (Claude Desktop, Cursor, Windsurf and others), and the data tool becomes available to the model automatically. See the full listing for setup details and every tool this server provides.

FULL HARNESS ML LISTING

Other tools in Harness Ml (5)

competitions

Simulations, brackets, scoring for tournament events

configure

Init projects, set backtest/ensemble config, run guardrail checks

experiments

Create/run/promote experiments with config overlays, required hypothesis, Bayesian exploration

models

Add/update/clone models, batch operations, class weighting, append/remove features

pipeline

Run backtests, predict, diagnostics, compare runs, explain models, workflow progress, export notebooks