# Stock Screener

> End-of-day stock screening data for 12 markets (US, CA, DE, HK, CN, JP, KR, TW, IN, SG, MY, AU) from the open-source stock-screener project. It covers preset screens such as Minervini, CANSLIM and VCP, relative-strength ratings, market breadth and industry group rankings. This is educational screening data, not investment advice. There is no intraday data.

The data is static JSON published after each market's close. Each publish lives in a new generation folder, so always start from the manifest.

## Data

- [Manifest](https://xang1234.github.io/stock-screener/static-data/manifest.json): The entry point. `data_root` names the current generation folder, and every other path below is relative to `static-data/<data_root>`. `markets.<CODE>` gives each market's `as_of_date`, `features`, `pages` and `assets`.
- Scan rows: `markets.<CODE>.pages.scan.path` is a scan manifest with the screen rules in `preset_screens` and the row files in `chunks`. Each chunk's `path` holds `rows`, and together the chunks hold every row.
- Track record: `markets.<CODE>.assets.scoreboard.path`, present only for a market with a published record.
- [Field dictionary](https://xang1234.github.io/stock-screener/fields.json): The meaning, unit and hard range of every scan row field. Read it before quoting a number, because names mislead: `volume` is traded value rather than shares, and `pct_day` is a percentile rank rather than a percent change.

## MCP server

- [stockscreen-mcp](https://github.com/xang1234/stock-screener/tree/main/stockscreen-mcp): Tools over this data, with no API key. Run `uvx stockscreen-mcp`, or `claude mcp add stockscreen -- uvx stockscreen-mcp`. The `stockscreen://skill` resource teaches the workflow and reading rules.

## Optional

- [Live site](https://xang1234.github.io/stock-screener/): The same data in a browser.
- [Source](https://github.com/xang1234/stock-screener): Code that computes every field.