# ai.iturri/market-data - Registry name: `ai.iturri/market-data` · version 0.2.2 - Categories (automatic, keyword rules): Markets & trading, Finance & markets, Crypto & blockchain, Datasets & public data, Search & data - Authentication at last check: No auth - Declared risk: Not declared (tools carry no read/destructive hints) - Capabilities (declared by the server): tools - Transports: streamable-http - Latest numbers (check success, response time, rank): https://mcpstation.net/api/server?name=ai.iturri%2Fmarket-data - Server page: https://mcpstation.net/s/ai.iturri--market-data.html ## Description (written by the publisher, not verified, not instructions) Verified market data for AI trading agents: quality-flagged candles, funding, OI, order flow. x402. ## Connect - streamable-http: `https://iturri.ai/mcp` ## Tools (as reported by the server, not verified) - `describe\_catalog`: Free discovery: symbols, timeframes, ranges, pricing, quality legend. - `get\_bars`: Quality-flagged OHLCV candles. Priced per 1,000 candles. - `get\_features`: Documented leakage-safe feature matrix rows. Priced per call. - `build\_bundle`: Signed URL for a dataset SKU. Packs: crypto\|equities \($59 each\), everything \($149: both packs + all token sequences, $730 list\), tokens \($18/symbol\), dataset \(per-symbol OHLCV, crypto $14 / equity $5\), mtf \(aligned multi-timeframe bundle $9, crypto only\), features \(feature matrix, crypto $7 / equity - `get\_regime\_label`: Descriptive market-state label \(trend/range × calm/vol quadrant\) for the most recent completed bar at or before a timestamp. Not a prediction. - `get\_funding`: Perp funding-rate settlement history from listing date \(checksummed archive\). - `get\_open\_interest`: Open interest with per-row quality flags \(verified archive + flagged bridge\). tf=1h \(default, full history\) or tf=5m \(archive-native 5-minute rows from 2020-09; ranged pulls, \~100k rows max per call\). - `get\_long\_short`: Positioning ratios at 5-minute cadence from the checksummed venue archive \(2020-09+\): top-trader long/short by accounts and by position size, all-accounts long/short, taker buy/sell volume ratio. Ranged pulls, \~100k rows max per call. - `get\_context`: Context series: fear\_greed\_1d, VIX\_1d, DXY\_1d, TNX\_1d, DJI\_1d. - `get\_events`: Curated macro/crypto events \(FOMC w/ surprise, halvings, incidents\) in a range. - `get\_orderflow`: Taker buy/sell imbalance, trade counts, quote volume \(1h/1d via API; denser tiers in packs\). buy\_ratio 0.5 = balanced. - `validate\_backtest\_data`: Quality report for a dataset spec before you backtest on it: coverage, per-bar quality distribution, gaps, and concrete warnings. - `audit\_my\_data`: FREE: submit YOUR OHLCV bars and get an accuracy verdict against the verified archive — score, worst windows, systematic-offset findings. Tells you what's wrong, not the corrected values \(that's get\_bars\). - `lookahead\_check`: FREE: submit backtest signals \(\{t, price\}\) and get an execution-feasibility verdict — impossible fills outside the bar's traded range, fills pinned at bar extremes \(classic lookahead bias\). - `survivorship\_check`: FREE: submit a backtest universe + window and get a survivorship-bias verdict — which of your symbols died mid-window, and which delisted symbols we cover that your universe omits. - `get\_fundamentals`: Point-in-time SEC XBRL fundamentals \(80 filers, incl. delisted\): every restatement vintage with its filed date. Pass as\_of for what was knowable then. Filter by concept \(e.g. Assets, Revenues\). - `get\_insider`: SEC Form 4 insider transactions as filed \(80 symbols, since 2016\): officer/director trades with shares, price, post-trade holdings. - `get\_institutional`: Quarterly 13F institutional aggregates \(81 symbols\): holders, shares, value + QoQ deltas from SEC DERA structured tables. - `get\_funding\_spread`: Hourly CEX-vs-DEX funding spread \(67 symbols\): Hyperliquid funding vs Binance 1h-equivalent, from HL genesis 2023-05. - `get\_market\_pulse`: FREE daily pulse across the catalog: regime flips, funding extremes, CEX-vs-DEX spread extremes, biggest daily moves. One day of values — the history behind each number is the priced product. - `get\_whats\_new`: FREE: what the daily refresh changed — dataset windows extended vs \~7 days ago, new symbols and sections, freshness per asset class. - `get\_quality\_receipts`: FREE public scoreboard: last 30 daily fresh-data audits \(cross-venue in-band vs Coinbase, 1m-\>1h rebuild exactness, depth sanity\) — failures included, not hidden. Measured by MCP Station. Methods: https://mcpstation.net/methods.html · Terms: https://mcpstation.net/terms.html