AWS Bedrock Data Automation vs training
AWS Bedrock Data Automation is an MCP server published by awslabs. Marketplaces we read that list it: 1 (Docker MCP Catalog). training is a plugin bundle for AI coding tools published by jmagly. Marketplaces we read that list it: 1 (Community GitHub marketplaces). As of our marketplace pass on 2026-10-26. This pair was picked by a reader, not by our comparison rule, so search engines are asked not to index the page.
Where each is published
| Marketplace |  AWS Bedrock Data Automation |  training |
|---|---|---|
| Docker MCP Catalog | Listed Version: sha256:ca5c8e3d1bf0 Forks (GitHub): 1 827 Pulls (Docker Hub): 14 632 Stars (Docker Hub): 0 Stars (GitHub): 9 830 Not marked · First seen |
Not listed |
| Community marketplace jmagly/aiwg | Not listed | Listed Version: 1.0.0 Forks (GitHub): 1 Stars (GitHub): 1 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 | AWS Bedrock Data Automation | training |
|---|---|---|
| Marketplaces that list it | 1 | 1 |
| Stars (GitHub) (differs) | 9 830 (better) | 1 (worse) |
| Pulls (Docker Hub) (differs) | 14 632 | No figure on Docker Hub |
| Forks (GitHub) (differs) | 1 827 (better) | 1 (worse) |
| Last release | Not published | Not published |
| Where it runs (differs) | On your machine (mcp/aws-bedrock-data-automation-mcp-server) | Installs as a plugin bundle |
| Transport (differs) | stdio | Not stated |
| Tools it declares (differs) | 3 | Not published |
| Environment variables it asks for (differs) | 3, secrets among them: 0 | Not published |
| Parts of the bundle (differs) | Not a bundle | 24 |
| Licence (differs) | Apache-2.0 | MIT |
| Repository (differs) | github.com/awslabs/mcp | github.com/jmagly/aiwg-training |
| Changes in the last 7 days (differs) | 0 | 2 |
| First seen (differs) | 2026-10-11 | 2026-10-23 |
Lines where the two differ have a tinted background and bold values. Where the data itself says which value is better (more marketplaces, a larger figure of the same marketplace, a fresher release, a verified mark on a marketplace that lists both), the better one is also marked green with ▲ and the worse one red with ▼. Where it runs, the transport, the tools, the settings, hooks, the bundle's parts, the licence and the week's changes are marked only as different: more or fewer is not better in itself.
What each says it does
AWS Bedrock Data Automation
Analyze documents, images, videos, and audio.
training
Corpus-to-dataset pipeline for AI training data curation. Ingests sources, synthesizes examples, generates DPO/KTO preference pairs, applies decontamination, and exports to Alpaca/ShareGPT/ChatML/JSONL/Parquet with provenance. Optional Python runtime (aiwg-training CLI) for scale.
How to run each
AWS Bedrock Data Automation As a local MCP server: Docker image
claude mcp add --transport stdio aws-bedrock-data-automation -- docker run -i --rm mcp/aws-bedrock-data-automation-mcp-servertraining As a Claude Code plugin
/plugin marketplace add jmagly/aiwg
/plugin install training@aiwgCommands built only from what the marketplaces declare; the full set for every client is on each card.
Tools each declares
The marketplaces of training publish no list of tools, so we do not compare tools.
Settings each asks for
The marketplaces of training publish no settings it asks for, so we do not compare settings.
What it can do: AWS Bedrock Data Automation · What it can do: training · Compare two other plugins
Data comes from the Docker MCP Catalog (desktop.docker.com/mcp/catalog) and Docker Hub. Data comes from public marketplace files in GitHub repositories of their authors. Figures come from our own regular passes over the marketplaces, last read on . We publish no contact details for plugin publishers.