servers / ai-iturri-market-data
ai.iturri/market-data MCP server
communitystreamable_httpremoteverifiedhealthy
Verified market data for AI trading agents: quality-flagged candles, funding, OI, order flow. x402.
01Tools · 11
How to read this: tool names here are observed from a live tools/list handshake. The Risk label is a heuristic inferred from the tool name (write/destructive verbs), not from executing the tool — a conservative guess, not a verified capability. We never escalate risk from a description. Found one that's wrong? Tell us — we fix on report.
| Tool | Risk | Side effects | Approval |
|---|---|---|---|
| describe_catalog Free discovery: symbols, timeframes, ranges, pricing, quality legend. | read | false | unknown |
| get_bars Quality-flagged OHLCV candles. Priced per 1,000 candles. | read | false | unknown |
| get_features Documented leakage-safe feature matrix rows. Priced per call. | read | false | unknown |
| 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 $4). Priced as the SKU. | read | false | unknown |
| 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. | read | false | unknown |
| get_funding Perp funding-rate settlement history from listing date (checksummed archive). | read | false | unknown |
| get_open_interest Hourly open interest with per-row quality flags (verified archive + flagged bridge). | read | false | unknown |
| get_context Context series: fear_greed_1d, VIX_1d, DXY_1d, TNX_1d, DJI_1d. | read | false | unknown |
| get_events Curated macro/crypto events (FOMC w/ surprise, halvings, incidents) in a range. | read | false | unknown |
| get_orderflow Taker buy/sell imbalance, trade counts, quote volume (1h/1d via API; denser tiers in packs). buy_ratio 0.5 = balanced. | read | false | unknown |
| validate_backtest_data Quality report for a dataset spec before you backtest on it: coverage, per-bar quality distribution, gaps, and concrete warnings. | unknown | unknown | unknown |
02Install & source
https://iturri.ai/mcp
remote_url- repohttps://github.com/iturri-ai/iturri-mcp
- homepagehttps://iturri.ai/mcp
- licenseMIT
- adoption0 stars · 0 forks
05Provenance & freshness
sourcesOfficial MCP Registry [p1]
last_checked2026-07-13 03:50Z
next_check2026-07-14 08:38Z
cadenceevery 29h
verifiedtools_list:passed handshake:passed metadata:passed
index_statusindex — 8 unique facts >= 5
06Badge
Add the “as seen on MCPExplorer” badge to your README. 
[](https://mcpexplorer.com/servers/ai-iturri-market-data)
Next step
This is one server. A loadout combines the right servers, governance, and proven plays for a whole job — assembled deliberately, not tool-dumped.
Explore loadouts →