Next free-source huntWe check for new free data every weekday.
FinancialMCP serverFirst audited Nov 13, 2026

ai.iturri/market-data

Verified market data for AI trading agents: quality-flagged candles, funding, OI, order flow. x402.The vendor's description, from its MCP Registry listing.

Passed, with 1 warningAudited Nov 13, 2026
  • Warning: 22 of 22 tools do not say whether they can change things.

Nothing failed, but there is something to know or fix. Public audit: we connect as an AI client would, list the tools and check what they say. We do not run them. How we audit

Does it work?
YesConnected in 200 ms.
Sign-up?
None neededIt answered without any account or key.
Can it change things?
Doesn't sayIts tools do not say whether they only read, so treat them as able to change things.
Endpointhttps://iturri.ai/mcp

Source code Website Streamable HTTP · protocol 2025-06-18 · server version 0.1.0

What we checked, the evidence, and the tools it offers.

What we checked

Security

  • Passed: Connections are encrypted (HTTPS).

  • Passed: No hidden instructions found in tool text.

Safety labels

  • Warning: 22 of 22 tools do not say whether they can change things.

    MCP lets a server label each tool as read-only or destructive, so clients can ask the user before risky calls. Unlabelled tools are treated as able to change things.

    • describe_catalog
    • get_bars
    • get_features
    • build_bundle
    • get_regime_label
    • get_funding
    • get_open_interest
    • get_long_short
    • and 14 more

Tools

  • Passed: 22 tools listed.

  • Passed: Every tool describes its inputs with a valid schema.

Protocol

  • Note: Protocol version 2025-06-18.

  • Passed: The MCP handshake works (Streamable HTTP).

  • Passed: Unknown requests are refused.

Connection

  • Passed: The server responds.

Tools (22)

As the server describes them. The labels are the server's own: it says whether each tool only reads or can change things.

  • describe_catalogFree discovery: symbols, timeframes, ranges, pricing, quality legend.Doesn't say
  • get_barsQuality-flagged OHLCV candles. Priced per 1,000 candles.Doesn't say
  • get_featuresDocumented leakage-safe feature matrix rows. Priced per call.Doesn't say
  • build_bundleSigned 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…Doesn't say
  • get_regime_labelDescriptive market-state label (trend/range × calm/vol quadrant) for the most recent completed bar at or before a timestamp. Not a prediction.Doesn't say
  • get_fundingPerp funding-rate settlement history from listing date (checksummed archive).Doesn't say
  • get_open_interestOpen 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).Doesn't say
  • get_long_shortPositioning 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. Ran…Doesn't say
  • get_contextContext series: fear_greed_1d, VIX_1d, DXY_1d, TNX_1d, DJI_1d.Doesn't say
  • get_eventsCurated macro/crypto events (FOMC w/ surprise, halvings, incidents) in a range.Doesn't say
  • get_orderflowTaker buy/sell imbalance, trade counts, quote volume (1h/1d via API; denser tiers in packs). buy_ratio 0.5 = balanced.Doesn't say
  • validate_backtest_dataQuality report for a dataset spec before you backtest on it: coverage, per-bar quality distribution, gaps, and concrete warnings.Doesn't say
  • audit_my_dataFREE: 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_…Doesn't say
  • lookahead_checkFREE: 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).Doesn't say
  • survivorship_checkFREE: 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.Doesn't say
  • get_fundamentalsPoint-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).Doesn't say
  • get_insiderSEC Form 4 insider transactions as filed (80 symbols, since 2016): officer/director trades with shares, price, post-trade holdings.Doesn't say
  • get_institutionalQuarterly 13F institutional aggregates (81 symbols): holders, shares, value + QoQ deltas from SEC DERA structured tables.Doesn't say
  • get_funding_spreadHourly CEX-vs-DEX funding spread (67 symbols): Hyperliquid funding vs Binance 1h-equivalent, from HL genesis 2023-05.Doesn't say
  • get_market_pulseFREE 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.Doesn't say
  • get_whats_newFREE: what the daily refresh changed — dataset windows extended vs ~7 days ago, new symbols and sections, freshness per asset class.Doesn't say
  • get_quality_receiptsFREE public scoreboard: last 30 daily fresh-data audits (cross-venue in-band vs Coinbase, 1m->1h rebuild exactness, depth sanity) — failures included, not hidden.Doesn't say

Audit history

  1. Nov 13Warnings

What we sent

Every request in this audit, with the answer and how long it took. We never send credentials and never call a tool.

RequestAnswerTime
initializeHTTP 200200 ms
initializedHTTP 20261 ms
tools/listHTTP 200107 ms
unknown-methodHTTP 20070 ms

Run this server, or disagree with the result?

Fix the issue and it shows in the next weekly audit, or email us to ask for a re-audit or to dispute a finding. Read how we audit for what each check means.