What inputs does screen_universe accept?

ticker (string, optional): If provided, show only this ticker's factor scores (single-entity mode). Omit to screen the full universe. sector (string, optional): Filter to a specific sector (case-insensitive partial match). E.g. 'Technology', 'Healthcare'. sort_by ("roe_rank" | "gross_margin_rank" | "operating_margin_rank" | "net_profit_margin_rank" | "revenue_growth_yoy_rank" | "fcf_to_assets_rank" | "debt_to_equity_rank" | "asset_turnover_rank" | "current_ratio_rank" | "piotroski_f_score_rank" | "composite_rank", optional, default "composite_rank"): Which factor rank to sort by (see the enum). Defaults to composite_rank. An unrecognized column is rejected with INVALID_ARGUMENT (no silent fallback). limit (integer, optional, default 25): Number of results to return (1-100). Defaults to 25. offset (integer, optional, default 0): Zero-based row offset for paging within the requested `limit` window. At most 250 rows are inlined per call; if the response carries a `truncation` envelope, pass its `next_offset` here. Defaults to 0. as_of_date (string, optional): Point-in-time cutoff (YYYY-MM-DD). When set, the screen is reconstructed as of this date via factor_scores.accepted_at — each entity ranked at its latest-knowable period, zero look-ahead, survivorship-free. Omit for the latest snapshot. exclude_outliers (boolean, optional, default false): Optional data-quality guard (default false). When true, additionally drops rows with implausible raw factor values (non-finite, or e.g. asset_turnover > 50x, |FCF/assets| > 10) from shell companies with near-zero denominators. Rows that do not join to a company (null symbol) are ALWAYS omitted in full-universe mode, regardless of this flag.

Which Valuein plans include screen_universe?

Available on every plan, including the free tier with no account. Point-in-time safe via as_of_date filtering.

Screening

PIT-safe

Screen Universe by Factor Scores

screen_universe

Sample and above

Rank companies by cross-sectional factor scores from factor_scores.parquet. Returns the underlying factors (roe, gross_margin, operating_margin, net_profit_margin, revenue_growth_yoy, fcf_to_assets, debt_to_equity, asset_turnover, current_ratio, piotroski_f_score) plus their p...

Example Call

example_call.pypython

# Using the Valuein MCP server from Python (via MCP SDK)# Or call directly from Claude / Cursor after setup result = await client.call_tool(    "screen_universe",    arguments={})print(result)

Direct tool call:screen_universe(sector="Technology", sort_by="composite_rank", limit=10)

Try it now

No token required

Paste this in your terminal — the free tier returns real sample data without authentication.

try-it.shbash

# No auth required — the Sample tier covers a large-cap US benchmark universe with a 5-year window.# Add -H "Authorization: Bearer $VALUEIN_TOKEN" for the full universe and history.curl -X POST https://mcp.valuein.biz/mcp \    -H "Content-Type: application/json" \    -H "Accept: application/json, text/event-stream" \    -d '{        "jsonrpc": "2.0",        "id": 1,        "method": "tools/call",        "params": {          "name": "screen_universe",          "arguments": {            "limit": 3          }        }      }'

Inputs

Parameter	Type	Required	Description
`ticker`	string	optional	If provided, show only this ticker's factor scores (single-entity mode). Omit to screen the full universe.
`sector`	string	optional	Filter to a specific sector (case-insensitive partial match). E.g. 'Technology', 'Healthcare'.
`sort_by`	"roe_rank" \| "gross_margin_rank" \| "operating_margin_rank" \| "net_profit_margin_rank" \| "revenue_growth_yoy_rank" \| "fcf_to_assets_rank" \| "debt_to_equity_rank" \| "asset_turnover_rank" \| "current_ratio_rank" \| "piotroski_f_score_rank" \| "composite_rank"	optional	Which factor rank to sort by (see the enum). Defaults to composite_rank. An unrecognized column is rejected with INVALID_ARGUMENT (no silent fallback).Default: `"composite_rank"`
`limit`	integer	optional	Number of results to return (1-100). Defaults to 25.Default: `25`
`offset`	integer	optional	Zero-based row offset for paging within the requested `limit` window. At most 250 rows are inlined per call; if the response carries a `truncation` envelope, pass its `next_offset` here. Defaults to 0.Default: `0`
`as_of_date`	string	optional	Point-in-time cutoff (YYYY-MM-DD). When set, the screen is reconstructed as of this date via factor_scores.accepted_at — each entity ranked at its latest-knowable period, zero look-ahead, survivorship-free. Omit for the latest snapshot.
`exclude_outliers`	boolean	optional	Optional data-quality guard (default false). When true, additionally drops rows with implausible raw factor values (non-finite, or e.g. asset_turnover > 50x, \|FCF/assets\| > 10) from shell companies with near-zero denominators. Rows that do not join to a company (null symbol) are ALWAYS omitted in full-universe mode, regardless of this flag.Default: `false`

Output Fields

plansort_bysector_filtertickeras_of_datepit_saferesults_returnednotetruncationdatalineage

Paging

limit is the page size and offset is where the page starts. While rows remain, the result carries truncation with next_offset: call again with the same arguments and offset set to truncation.next_offset, until a result has no truncation.

Errors and paging for every tool: the agent contract.

Example Response

Illustrative

response.jsonjson

[  {    "plan": "sp500",    "sort_by": null,    "sector_filter": null,    "ticker": "AAPL",    "as_of_date": null,    "pit_safe": null,    "results_returned": null,    "note": null  }]

Shape only — field names match the live schema; values are placeholders, not real filings. Returns the top 10 Technology companies by composite factor rank.

Notes

Without `as_of_date` the screen ranks the latest factor snapshot; with it, the screen is reconstructed point-in-time from `factor_scores.accepted_at` — each company ranked at its latest-knowable period, with no look-ahead.