Screen 28,000+ names for your thesis in seconds

Screen the index as it stood on a date, using only fields known on that date, then open any result to its filing.

Find the names that fit your idea — deleveraging, margin-inflecting, buyback-heavy — before the trade is crowded.

The pain

Idea generation dies in spreadsheets. By the time you've pulled fundamentals for a few hundred names, you've biased your search to what you already know — and missed the thesis hiding in the long tail.

“My screen gives a different answer every week.”
Moving index membership and overwritten history make results hard to reproduce.
“I wrote 80 lines of SQL for a simple ratio filter.”
Reaching the latest annual value per company is where the time goes.
“I cannot tell if a screen result is stale.”
A name can pass on a figure that is years old.

The solution

1
Express the thesis as a screen
screen_universe filters the full universe on standardized fundamentals and pre-computed factor ranks — combine growth, margin, leverage, and value conditions in one call.
2
Rank, don't just filter
get_financial_ratios exposes the cross-sectional factor scores so you sort by composite rank, not arbitrary cutoffs.
3
Hand the shortlist to deeper work
The screen_and_shortlist playbook hands each survivor to the equity_research_brief — so a universe screen becomes a stack of IC-ready briefs without manual hand-off.

Copy this

Real code and a ready prompt. Each block says what it needs before it runs.

APython SDK

No token needed: runs on the free sample

screen-the-universe.pypython

from valuein_sdk import ValueinClient with ValueinClient() as client:  # no key: the free sample    # The S&P 500 as it stood on 2024-12-31, keeping only names priced above $10.    # Every field is read as it was known on that date: no look-ahead.    screen = client.screen("2024-12-31", universe="SP500", min_price=10)    print(screen.describe())     # Screens are lazy. collect() runs it and returns the result.    result = screen.collect()    print(result)

Runs on the free sample with no token; paid plans widen the range.

pip install valuein-sdk

BPrompt for Claude or ChatGPT

Works without a token on the free sample; your token unlocks your plan

prompt.txttext

Use screen_universe to shortlist companies with high return on equity and low debt to equity, then get_financial_ratios on the top five. Show the values exactly as returned, with the period each one is for.

Tools it uses: screen_universe, get_financial_ratios

CConnect your AI client

No token? Delete the headers block and it runs on the free sample

mcp configjson

{  "mcpServers": {    "valuein": {      "url": "https://mcp.valuein.biz/mcp",      "headers": {        "Authorization": "Bearer YOUR_VALUEIN_TOKEN"      }    }  }}

What you get

You surface the whole opportunity set — including names you'd never have thought to pull — and go from idea to shortlist in one step.

A reproducible shortlist: same date, same rules, same answer.
Ratios with the period and the filing they come from.
A starting point you can save as a Watchlist.

Backtests that can't see the futureSee how Find the mispricing with a reverse-DCFSee how Follow the smart money — 13F flows and insider clustersSee how

Frequently asked

How big is the universe?

28,000+ active and delisted US entities on Pro and Institutional (the free Benchmark tier covers the S&P 500). Screens run across the whole set, not a sample.

Can I screen on point-in-time data?

Yes — combine screening with the PIT universe so a historical screen reflects only what was knowable on that date, for honest backtests of the screen itself.

Try it on your own ticker.

The free sample needs no token and no card. One token works across your AI agent, your code and the Workspace.

Start free — no card See pricing