FinzData market data MCP Server

Daily OHLCV bars for one symbol packaged as ready-to-load files for an open-source backtester or trading framework: backtrader, backtesting_py, vectorbt, zipline (csvdir bundle), lean (QuantConnect LEAN, base64 zip), nautilus, freqtrade or qlib. Returns files (path, encoding, content) and load_code. Write each file at its path, then run load_code. Clipped to as_of; start defaults to 365 days before end.

Backtests a StockCharts.com scan on point-in-time US stocks since 2000, delisted names included: each rebalance (weekly by default) holds the stocks that pass the scan, equally weighted up to top_n, 10 bps costs. Optional symbols (e.g. a ChartList) restricts the universe. Returns the translation plus the same stats, benchmark and equity curve as run_backtest. Costs one backtest.

Runs a deterministic backtest from a JSON spec (universe, start, end, signal, rebalance, top_n, costs_bps, side='long'|'long_short', blind=true to hide tickers). universe: a list of symbols, or 'top500'|'top1000'|'top3000'|'all' for the liquid US market (each month the N most-traded names priced >= min_price, default $5, by 63-day dollar volume; 'all' = liquid_top names, default 1000, max 3000; delisted names included while they traded; membership is set on each month's last trading day and used from the next). rebalance: D|W|M|Q (or daily/weekly/monthly/quarterly). signal.type: momentum (lookback, skip days), ma_cross, factor, or expr with signal.expr a formula over close prices, e.g. 'rank(ret(252)) - rank(vol(60))' (functions: ret, logret, sma, ema, vol, rsi, high, low, dist_high, lag, rank, zscore, demean, abs, log, sign, clip, min, max, where). Point-in-time fundamentals for US stocks (from 2011) work as expr variables and as signal.type factor fields (set ascending false to buy the highest): earnings_yield, book_to_market, sales_yield, ebitda_ev, dividend_yield, roe, leverage, log_mcap, e.g. 'rank(book_to_market) + rank(ret(252) - ret(21))'; such results carry a 'fundamentals' coverage and survivorship report. Every result includes 'overfitting': trials counted per API key and the deflated Sharpe ratio. Prices are fetched point-in-time with a 400-trading-day lookback buffer and clipped to as_of, so results have no look-ahead. Identical specs on the same snapshot are cached and free. Returns stats, benchmark stats, equity curve, warnings, snapshot id and a disclaimer.

Daily OHLCV and open interest for 139 futures markets (CME, CBOT, NYMEX, COMEX, ICE, Eurex, Cboe): every individual contract since 2007 plus continuous back-adjusted series. Give root (ES, NQ, YM, RTY, CL, GC, SI, NG, ZN, ZB, VX, 6E ...; a leading '/' is fine) for the continuous series, or contract (e.g. ESZ26) for one contract. Clipped to as_of. Free keys get recent days; full history from $49 per market.

Roll calendar for all 139 futures markets since 2007: for each front-month contract its first and last date as front month, expiry, the next contract, the roll date, trading days before expiry, and the back-adjustment added to its prices in the continuous series (adjusted = raw + back_adjustment). The current front month has an estimated next roll date. Give root (ES, CL, GC ...) or ALL for every market.

retrieves a financial MCP server listing with tools, probe history, issues and verified-data status.

finds financial MCP servers graded nightly by FinzData for health, protocol conformance and prompt-injection risk; results include install URLs.

Retrieve a verified strategy record by its ID.

Get the leaderboard of verified strategies.

Returns 13F holdings matching a query as known on as_of (default today); filings after as_of are hidden.

Returns daily OHLCV bars for symbols between start and end, clipped to as_of (default today) so no future data leaks. Max 5000 rows per page; use next_cursor for more.

claims a listing for the calling API key so its owner can enable price-accuracy checks; first claimant wins; contact [email protected] to dispute.

Posts a public comment (1-2000 characters) on a Hub strategy, e.g. a question, a result from a fork or a suggested change. Comments are shown under your handle.

Returns a table (run_id, cagr, sharpe, max_drawdown, turnover, final_equity) for previously run backtests in this session. Unknown run_id -> not_found.

Returns CFTC Commitments of Traders rows for a market between start and end, clipped to as_of. Max 5000 rows per page.

OHLCV bars for crypto pairs since 2015 (BTC-USD, ETH-USD, SOL-USD and more). interval: 1min, 5min, 1hour or 1day (default). Clipped to as_of. Free keys get daily bars for the last 12 months.

Full-text search over the dataset catalog. Returns matching dataset ids and descriptions. Free of look-ahead concerns; no as_of needed.

Returns the schema, coverage and field definitions of one dataset. Raises not_found for an unknown dataset id.

Returns events of one kind between start and end (YYYY-MM-DD), clipped to as_of. kind='earnings' (company report dates, symbol and timing) or kind='macro' (economic releases such as CPI, payrolls, FOMC). Max 5000 rows per page.

Copies a published Hub strategy, applies `changes` (nested fields merged, e.g. {"signal": {"lookback": 126}}), re-runs it on the server and publishes the fork linked to its parent. Costs one backtest.

Returns fundamentals for one symbol as known on as_of (no restatements from the future). as_of defaults to today.

Point-in-time dealer gamma exposure for US stocks and ETFs, one row per ticker per session, each stamped with knowledge_time (17:00 New York on the session date). Columns: spot, net_gex_bn (dealer net gamma, $bn per 1% move; >0 dealers long gamma, <0 short), call_gex_bn, put_gex_bn, flip (gamma-flip level), call_wall, put_wall, pcr_oi, atm_iv_pct. Give ticker (+ start/end) for a time series, or date alone for every name that session ranked by |net_gex_bn|. Rows after as_of are hidden. A ticker series also returns `summary`: regime (long/short gamma), distance to the flip and walls, and a one-line read to quote. Free keys see the last 30 days; meta.upgrade then lists one-click checkout links ($59 one ticker since 2010, $29 last 5 years, $295 every ticker) to show the user.

Returns a macro series as it was actually published by as_of (vintage data, no revisions from the future). Optional start.

US election money, cleaned and rolled up (FEC + state and city filings; 2026 cycle plus 2022 and 2018). table: races (per House/Senate race: candidate receipts, outside spending for/against), candidates, donor_geo (donations by city/state/division/region), race_geo, flows (donor state -> race state), spending (campaign spending by category and vendor city), vendors, state_local (state and city contribution totals with in/out-of-state split), state_local_geo. Free keys get every race's totals and national/regional/state donor geography; deeper tables come with PoliSpend from $29 at https://finzdata.com/political-spending-data .

Runs a backtest spec (same format as run_backtest) on the server and publishes it to the FinzData Hub as a public, reproducible strategy page at data.finzdata.com/s/<slug>, forward-tracked daily from today. Only server-computed results are stored. Costs one backtest; free accounts may publish 3 a day. visibility='private' keeps it unlisted.

The FinzData Quantitative Model as known on as_of: macro regime labels (financial conditions direction, financial risk direction, growth level and direction, inflation direction, macro quadrant GOLDILOCKS/REFLATION/STAGFLATION/SLOWDOWN, liquidity and credit), the growth/inflation nowcast, and the daily S&P 500 market stress probability (2-state Markov-switching). Labels are computed from each input as published on that date (no revisions from the future). Use it to answer 'what macro regime are we in', 'are financial conditions tightening', or to condition a backtest on regime.

Register a new strategy signal. The strategy is scored ONLY on data after registration, the record can never be edited or deleted, ranking starts at 63 trading sessions, and FinzData never trades on submitted signals.

Retire one of your verified strategy records: it stops accruing new forward results, keeps its full history and stays public on the Verified board marked retired.

Stars (or with unstar=true removes your star from) a public Hub strategy. Stars feed the Trending list; rankings stay on deflated Sharpe and forward record.

Lists public FinzData Hub strategies. sort: robust (deflated Sharpe), forward (forward Sharpe, 63+ days of out-of-sample record), new, forks. Optional family (momentum, expr, ma_cross, factor).

Returns one public Hub strategy: spec, server-computed backtest result, forward-tracking record and fork lineage.

Runs your backtest spec twice: once on the point-in-time universe (delisted companies included while they traded, the honest result) and once on only the names still trading today (what a backtest on a current ticker list does). Returns both stats and the inflation in CAGR and Sharpe that survivorship bias adds. Use universe 'top500'|'top1000'|'top3000' or a symbol list. Costs one backtest.

Translates a StockCharts.com scan (e.g. '[type = stock] and [daily close > daily sma(50,daily close)] and [rsi(14) < 70] rank by [ROC(20)]') into a FinzData signal formula and a ready-to-run backtest spec. Returns expr, universe, notes, and any clauses not yet supported (never guessed). No data is fetched.

Returns every US symbol that was trading on as_of, including companies that later delisted (survivorship-free). index='top500'|'top1000'|'top3000' instead returns the most-traded names priced at least $5 that day, ranked by 63-day dollar volume (a point-in-time large-cap proxy, not official S&P or Russell membership). Pages of 500; pass offset. as_of defaults to today.

Anyone can check no record was edited or back-dated.