tabh2o vs Welt
tabh2o is no longer listed on any marketplace we read: these are its last known data, as of 2026‑10‑22.
tabh2o is a plugin bundle for AI coding tools published by h2oai. No marketplace we read lists it any more. Welt is an MCP server published by welt.ergodic.dev. Marketplaces we read that list it: 1 (Official MCP Registry). As of our marketplace pass on 2026-11-13. A plugin in this pair is no longer listed on any marketplace we read, so search engines are asked not to index the page.
Where each is published
| Marketplace |  Welt | |
|---|---|---|
| Community marketplace h2oai/tabh2o | Removed on 2026-10-22 Version: not stated Forks (GitHub): 1 Stars (GitHub): 7 Not marked · First seen |
Not listed |
| Official MCP Registry | Not listed | Listed Version: 1.0.0 No figure published Not marked · First seen |
Each figure is the marketplace's own and is never added up across marketplaces. A marketplace that publishes no figure shows none: no number is not zero.
The facts side by side
| Fact | tabh2ono longer listed · | Welt |
|---|---|---|
| Marketplaces that list it (differs) | 0 | 1 |
| Stars (GitHub) (differs) | 7 | No figure on GitHub |
| Forks (GitHub) (differs) | 1 | No figure on GitHub |
| Last release | Not published | Not published |
| Where it runs (differs) | Installs as a plugin bundle | Remote server (welt.ergodic.dev/mcp) |
| Transport (differs) | Not stated | Streamable HTTP |
| Tools it declares | Not published | Not published |
| Environment variables it asks for | Not published | Not published |
| Parts of the bundle (differs) | 1 | Not a bundle |
| Licence | Not stated | Not stated |
| Repository (differs) | github.com/h2oai/tabh2o | Not stated |
| Changes in the last 7 days | 0 | 0 |
| First seen (differs) | 2026-10-20 | 2026-10-19 |
| Endpoint at the last check (differs) | no remote endpoint we check | Responded 2 h ago |
Lines where the two differ have a tinted background and bold values. No value is marked better or worse: a plugin no marketplace lists any more is shown with its last known data, which we do not rank against current figures.
What to use instead of tabh2o
Plugins still listed whose own names, descriptions, tools and skills are closest in meaning to it. Comparable, not endorsed.
-
Train AutoML models on CSV files and run predictions from Claude and other MCP clients.
-
Self-hosted MCP server for time-series forecasting and tabular ML via foundation models.
-
Forecast time series in CSV files: deterministic skforecast workflows and the script that ran.
-
Give your AI a research team. Forecast, score, classify, or research every row of a dataset.
-
DataRobot skills for AI/ML workflows — model training, deployment, predictions, feature engineering, monitoring, explainability, data preparation, App Framework CI/CD, and…
-
Forecasting Engineer — Time series forecasting — demand prediction, trend analysis, seasonal decomposition
What each says it does
tabh2o
Makes predictions on tabular data using the TabH2O foundation model API. Supports classification, regression (including timeseries forecasting), clustering, missing value imputation, and anomaly detection, with optional global feature importance for classification and regression. Send data as JSON or CSV, get results back.
Welt
Run Welt's tabular, causal and forecasting models on your data. Hosted; OAuth sign-in.
How to run each
tabh2o
No data for an automatic command: what its marketplaces declare does not say unambiguously how to connect it.
Welt As a remote MCP server
claude mcp add --transport http welt https://welt.ergodic.dev/mcpCommands built only from what the marketplaces declare; the full set for every client is on each card.
Only Welt has a remote endpoint we check. How we check endpoints
Tools each declares
Neither one's marketplaces publish a list of tools, so there is nothing to compare.
Settings each asks for
Neither one's marketplaces publish the settings it asks for.
What it can do: tabh2o · What it can do: Welt · Compare two other plugins
Data comes from public marketplace files in GitHub repositories of their authors. Data comes from the Official MCP Registry (registry.modelcontextprotocol.io), CC0 1.0. Figures come from our own regular passes over the marketplaces, last read on . We publish no contact details for plugin publishers.