Leaderboard/ai.iturri/market-data

MCP ServerScored via MCP protocol probing: initialize handshake, tools/list conformance, and ping + tool invocation performance.

ai.iturri/market-data

iturri.ai↗|v0.2.2

Verified market data for AI trading agents: quality-flagged candles, funding, OI, order flow. x402.

80/100

Operational Score

Score Breakdown

Availability30/30

Conformance30/30

Performance20/40

Key Metrics

Uptime 30d

100.0%

P95 Latency

1,945.7ms

Conformance

Pass

Trend

Stable

What's Being Tested

Availability

HTTP health check to the service endpoint

Responded with HTTP 200 in 1945ms

Conformance

MCP initialize handshake + tools/list

Valid MCP server info returned, tools/list responded

Performance

MCP ping + zero-arg tool invocation benchmarking

P95 latency: 1945ms, task completion: 100%

Improvement Tips

-Reduce response time (currently 1945ms, target <1000ms)

Skills

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 $4). Priced as the SKU.

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

Hourly open interest with per-row quality flags (verified archive + flagged bridge).

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.

Tools

11 tools verified via live probe

verified 1h ago

Server: iturri-dataVersion: 0.1.0Protocol: 2025-06-18

Recent Probe Results

Timestamp	Status	Latency	Conformance	Details
Jul 14, 2026	success	1945.7ms	Pass	-

Source Registries

mcp-registry

First Seen

Jul 14, 2026

Last Seen

Jul 14, 2026

Last Probed

Jul 14, 2026