Mmcp.market

Autocarver MCP server

by mdefrance·io.github.mdefrance/autocarver·v7.8.0
No reviews yet

Qualify dataset columns and process them against a target with AutoCarver, fully on your machine.

A92/100grade A
Write a reviewInstall
What users say
No reviews yet
Be the first
Safety scan
A92/100

full report

Adoption
Growing

11 stars318 downloads/wk

Reviews

Write one

Nobody has reviewed Autocarver yet.

If you have run it, two minutes of your experience saves the next person an afternoon.

Autocarver tools (13, 2 write)

write = sends, deletes, buys or posts

Read from the package source without running it. The installed server may list more.

  • datetime_reference_candidates

    Summarise datetime columns (span + coverage) to help choose a reference.

  • drop_featurewrite action

    Remove a column from the feature draft.

  • evaluate_stability

    Score a new dataset against the fitted carver: PSI, chi2 drift, rank inversions.

  • feature_distribution

    Show a column's modality distribution, target rate, and rare-modality flags.

  • list_columns

    List every column with its dtype, cardinality, missingness and suggested feature kind.

  • load_dataset

    Load a .csv/.parquet file as the working dataset; optionally name the target column.

  • preview_features

    Return the current feature draft as {column: spec}.

  • profile_column

    Profile one column: cardinality, missingness, quantiles (numeric) or top modalities.

  • run_carverwrite action

    Build Features from the draft and carve them against the target; return the summary.

  • save_carver

    Save the fitted carver and its carved features to a .json file (run run_carver first).

  • set_feature

    Set/override a column's feature kind in the draft (numerical/categorical/ordinal/datetime/nested/ignore).

  • suggest_features

    Fill the feature draft with dtype-based suggestions (skips the target).

  • validate_nesting

    Check that a finest column rolls cleanly into coarser parent columns (many-to-one).

Public scan report

scanner v0.1.5 · 2026-09-19 · same rubric, same numbers if you re-run it

no findings
  • Code scan96 source files scanned; 96 source files scanned25/25
  • –Live reliabilityno gateway calls yet and no remote to proben/a
  • –Tool poisoningtools not inspected (local package is not executed); not countedn/a
  • Auth qualitylocal package, no credentials required12/15
  • Maintenancelast push 5 days ago15/15
  • Maintainer identityregistry namespace matches repository owner; GitHub account older than a year8/10
Overall 92/100. Components that don't apply are left out of the denominator. Any critical finding is an F.RubricAppeal a findingJSON

What the publisher says

From the Autocarver repository's README, as published. We do not edit it. Read it on GitHub

<!-- mcp-name: io.github.mdefrance/autocarver -->

AutoCarver turns raw numeric, categorical, and ordinal columns into optimal, drift-robust, human-readable bins in a few lines of code. Stop losing model performance to suboptimal manual binning — and stop discovering overfit bins in production monitoring.

  • Provably optimal — exhaustive search: for a fixed minfreq, maxn_mod and metric (Tschuprow's T by default, or Cramér's V), no other admissible bin combination scores higher. It checked them all so you don't have to.
  • Robust by construction — every candidate grouping is vetoed unless it holds on a held-out dev set (and optional CV folds), at fit time rather than in monitoring.
  • Define → carve → model — declare your Features, fit a carver, transform: the whole feature set is carved in one supervised pass, not one notebook per feature. One carver per target type — BinaryCarver, MulticlassCarver, OrdinalCarver, ContinuousCarver (regression) — all with the identical API.
  • AI-assisted — a local MCP server lets your LLM assistant qualify and carve columns through tool calls, fully on your machine.

On the Titanic quick start, Fare collapses from 72 pre-carving modalities to 2 bins while its association with survival rises: Tschuprow's T 0.18 raw → 0.29 carved.

Built for credit scoring, fraud detection, and risk modeling.

🆕 What's New

📊 Cross-validated robustness. fit now accepts a cv argument for extra held-out robustness views on top of (or instead of) a dev set: carver.fit(X, y, cv=5). Accepts an int, any scikit-learn splitter, or explicit index pairs, resolved via sklearn.modelselection.checkcv — folds veto over-fit combinations but never reorder them (ranks stay anchored to the full train set). See Cross-validation folds.

Shortened. The full README is on GitHub.

Nothing above is checked by us. What we check is on the safety report.

Install directly

claude mcp add autocarver -- uvx autocarver
Add to Cursor

Autocarver: common questions

Is Autocarver MCP server safe?
Yes, by our scan: it is graded A (92/100). Read the Autocarver safety report
How do I install Autocarver?
It runs on your machine. Copy the Claude Code, Claude Desktop or Cursor config from the install section.
Does Autocarver need an API key?
Not as far as the registry entry and our scan can tell: no credentials are declared or required.
Is Autocarver maintained?
The last commit was 6 days ago (2026-09-15). The latest release is v7.8.0.

More from mdefrance →