What inputs does get_earnings_signals accept?

ticker (string, required): Stock ticker symbol, e.g. AAPL, MSFT — or a CIK (SEC identifier), e.g. '0000320193'. as_of_date (string, optional): Point-in-time filter: only return signals with accepted_at on or before this date. Use for backtesting to avoid look-ahead bias. limit (integer, optional, default 8): Maximum number of periods to return (1–40), most recent first. Defaults to 8 — covers 2 years of quarterly signals plus their TTM equivalents. earnings_signals.parquet currently emits one row per (entity, period_end); older rows surface here as more historical periods are published.

Which Valuein plans include get_earnings_signals?

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

Signals

PIT-safe

Earnings Signals

get_earnings_signals

Sample and above

Reported earnings results and a model-derived earnings-trend signal for a company, by fiscal period: actual reported EPS, a trailing-trend EPS estimate (`eps_trend_est`), the deviation of actual vs that trend (`eps_surprise_pct`), reported revenue, and year-over-year revenue g...

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(    "get_earnings_signals",    arguments={    "ticker": "EXAMPLE"})print(result)

Direct tool call:get_earnings_signals(ticker="TSLA", as_of_date="2024-01-01")

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": "get_earnings_signals",          "arguments": {            "ticker": "AAPL",            "limit": 3          }        }      }'

Inputs

Parameter	Type	Required	Description
`ticker`	string	required	Stock ticker symbol, e.g. AAPL, MSFT — or a CIK (SEC identifier), e.g. '0000320193'.
`as_of_date`	string	optional	Point-in-time filter: only return signals with accepted_at on or before this date. Use for backtesting to avoid look-ahead bias.
`limit`	integer	optional	Maximum number of periods to return (1–40), most recent first. Defaults to 8 — covers 2 years of quarterly signals plus their TTM equivalents. earnings_signals.parquet currently emits one row per (entity, period_end); older rows surface here as more historical periods are published.Default: `8`

Output Fields

tickerplanas_of_dateperiods_returnednoteestimate_basisdata

Example Response

Illustrative

response.jsonjson

[  {    "ticker": "AAPL",    "plan": "sp500",    "as_of_date": null,    "periods_returned": null,    "note": null,    "estimate_basis": null,    "data": null  }]

Shape only — field names match the live schema; values are placeholders, not real filings. Returns Tesla's quarterly reported EPS, a trailing-trend EPS estimate (`eps_trend_est`) and the surprise against that trend (`eps_surprise_pct`), as of Jan 2024 — not a Wall Street consensus beat or miss.

Notes

`eps_surprise_pct` is a fraction (0.067 = 6.7%) measured against the company's own trailing EPS trend, never analyst consensus. It is null when `eps_trend_est` is missing or near zero (|estimate| ≤ 0.001, to avoid division instability) — filter IS NOT NULL for momentum screens.