Niches · Financial market data

Get a price history for a ticker

Four or more companies' docs show a full fit.

5companies, full fit
6companies, fit with a limit
13companies carry the tag
17share of the category's work
8first-hand accounts

What counts as done

Bars for the full range at the asked interval, labelled adjusted or raw, with no missing sessions, returned in a form the agent can pass to code (CSV or a file) rather than into its context, in at most three calls.

Measured, for our own tests: a year of daily bars under 5,000 tokens, or delivered as a file. No docs we read state these figures, so they don't count against a listing here.

How agents ask for it: get a year of daily closes for AAPL, five-minute candles for SPY today, plot NVDA since 2020, historical implied volatility for my watchlist

Does the job 5

The docs show it meets the test above, and nothing we read says otherwise.

ListingWhy
Alpha Vantage E
Alpha Vantage Inc.
TIME_SERIES_DAILY and TIME_SERIES_DAILY_ADJUSTED return 20+ years in one call with outputsize=full and datatype=csv; intraday takes month=YYYY-MM back to 2000. Raw and adjusted are separate functions, so the label is explicit. source
EODHD C
Unicorn Data Services
GET /eod/{SYMBOL}.{EXCHANGE} with from, to, period and fmt=csv returns 30+ years of daily bars in one call, each row with close and adjusted_close; intraday 1m, 5m and 1h by from and to. Free plan: one year only. source
Intrinio C
Intrinio, Inc.
GET /securities/{id}/prices takes start_date, end_date and frequency daily to yearly, and every row carries raw open, high, low, close and adj_ fields adjusted for splits and dividends; page_size over 100 is limited to one a second on paid plans. source
Tiingo D
Tiingo Inc.
GET /tiingo/daily/<ticker>/prices takes startDate, endDate, resampleFreq, format=csv and columns=, and returns raw and CRSP-method adjusted OHLCV side by side with splitFactor, so a year of daily closes is one CSV call. source
Twelve Data BB
Twelve Data Pte. Ltd.
/time_series takes interval, start_date and end_date, outputsize 1 to 5,000, format=CSV and adjust all, splits, dividends or none (default splits), so a year of daily closes is one labelled CSV call. source

Does the job, with a limit 6

It does the job, but something in the docs or a user's account will get in an agent's way. The limit is named in each row.

ListingWhy
Benzinga D
Benzinga
GET bars takes symbols, from, to, interval 1m to 1M and session, so a year of daily bars is one call; the docs don't say whether bars are split or dividend adjusted, and output is JSON only. source
Databento C
Databento, Inc.
timeseries.get_range with schema ohlcv-1d or ohlcv-1m, start, end, limit and csv or dbn encoding writes to a file in one call; bars are raw, and adjusting means joining the separate adjustment factors dataset. acc-02 saw an MCP wrapper flood the context. source
Eulerpool Financial Data API D
Eulerpool Research Systems Pte. Ltd.
GET /equity/quotes/{isin} takes startdate and enddate in milliseconds and returns JSON; there is no interval, CSV or adjustment parameter, so whether closes are adjusted is not stated. source
Financial Datasets C
Financial Datasets, Inc.
GET /prices takes ticker, interval day, week, month or year, start_date and end_date, paged by cursor; there is no intraday interval, no CSV, and no adjusted or raw label. x402 and lower plans reach only 365 days. source
Finnhub D
Finnhub
/stock/candle (premium) takes resolution, from and to; daily bars are split-adjusted, intraday unadjusted and one month per call. acc-27 got a bare 403 on a free key and acc-29 reports missing one-minute rows, both open. source
Massive (formerly Polygon.io) BB
Massive.com, Inc.
Custom Bars take multiplier, timespan, from and to with adjusted=true by default (false for raw) and limit up to 50,000, so a year of daily bars is one call; acc-31 reports specific one-minute bars missing on Stocks Basic (open). source

Couldn't check 1

The docs were closed to us, or silent. These carry no mark either way.

ListingWhy
Financial Modeling Prep D
Financial Modeling Prep
site.financialmodelingprep.com answered 403 to robots.txt, so no FMP docs were opened; no account covers price history.

2 listings in the category were added after this reading and aren't marked yet.

What stops agents finishing

  • intraday endpoint answers 403 on the free key with no reason
  • bars missing on the cheaper plan
  • the whole range lands in the model context

Around it

Before: market-data.resolve-ticker, chat.user-question. After: code-sandboxes.run-analysis, spreadsheets.write-table.

Where this comes from

Weight 17 of 100 in Financial market data: 8 of 46 accounts (8 of 48 mentions); token blow-ups, missing bars and adjustment questions across Databento, Finnhub, Massive and Tiingo

The same as data: /api/v1/use-cases/market-data.price-history.json, or the MCP tool get_use_case with id market-data.price-history. Other jobs in this category: /api/v1/niches?category=market-data.

Draft, read 2026-11-15 from public docs and first-hand accounts, not yet reviewed by a person. A mark says what the docs show, not what a run measured.

For companies

Do agents find, use and choose your tools?

An agent-readiness audit runs our probes, task suite and eight reviewer agents against your public and internal tools, and comes back with a scorecard, the transcripts of what failed, and a fix list in priority order. From $2,500, re-run included. We never take payment to move a rank. We do help companies earn one.