Metadata-Version: 2.4
Name: mcptoolshop-rnd-newsletter
Version: 1.30.0
Summary: The research newsletter of mcp-tool-shop: every published issue as data.
Author: mcp-tool-shop
License-Expression: MIT
Project-URL: Homepage, https://mcp-tool-shop-org.github.io/rnd/newsletter/
Project-URL: Source, https://github.com/mcp-tool-shop-org/rnd
Project-URL: Hugging Face, https://huggingface.co/datasets/mcp-tool-shop/rnd-newsletter
Project-URL: npm, https://www.npmjs.com/package/@rnd-news/newsletter
Keywords: newsletter,research,machine-learning,dataset
Classifier: Programming Language :: Python :: 3
Classifier: Topic :: Scientific/Engineering :: Artificial Intelligence
Requires-Python: >=3.10
Description-Content-Type: text/markdown
License-File: LICENSE
Dynamic: license-file

# Research and Development: the newsletter

The research newsletter of mcp-tool-shop: what we measured, and what it means. Each issue reports the studio's experiments
in plain language, with the numbers, the charts, what held up and what didn't.

This package mirrors the published issues and is updated automatically after each issue goes live on the site.
It holds 28 issues. The newest is issue 30, 2026-10-25: [25 October: a crash test, a lab for tests with proven answers, and our Colab cards measured](https://mcp-tool-shop-org.github.io/rnd/newsletter/issue-30/).

- **Read it on the web:** https://mcp-tool-shop-org.github.io/rnd/
- **RSS:** https://mcp-tool-shop-org.github.io/rnd/newsletter/rss.xml
- **Source:** [mcp-tool-shop-org/rnd](https://github.com/mcp-tool-shop-org/rnd), where each issue is
  `site/src/content/docs/newsletter/issue-NN.md`.

## Files

- `data/issues.jsonl`: one row per issue, with `issue`, `date`, `title`, `description`, `highlights` (HTML
  strings), `url` and `body_markdown` (the issue's Markdown, with site links made absolute).
- `issues/issue-NN.md`: each issue as a Markdown file with its front matter.

Charts are linked from the site, not copied here.

## Load it

```python
import rnd_newsletter

rnd_newsletter.latest()        # the newest issue, a dict
rnd_newsletter.issue(30)       # one issue by number
rnd_newsletter.issues()        # every issue, oldest first
```

No dependencies; Python 3.10 or newer. The same data is on Hugging Face as [mcp-tool-shop/rnd-newsletter](https://huggingface.co/datasets/mcp-tool-shop/rnd-newsletter) and on npm as `@rnd-news/newsletter`.

## Licence and author

MIT, the licence of the rnd repository the issues are published from. Author: mcp-tool-shop.
