QSIG Intelligence MCP Server

QSIG geopolitical theme board. For each theme (HORMUZ_OIL, IRAN, LEVANT, RUSSIA_UKRAINE, CHINA_TAIWAN, FED, CRYPTO): the Polymarket crowd stress index and its 24h / 7d change on the same markets, tracked whale positions and 24h flows (aggregates only, no wallet addresses), the news-event count against its same-window baseline, and the top 3 markets. theme is an optional key; omit it for all themes. as_of is an optional ISO 8601 UTC timestamp such as "2026-10-05T12:00:00Z"; the latest hourly snapshot at or before it is returned. History begins 2026-09-29. Themes with coverage.sufficient = false are returned but should not be read as meaningful. stress_index is a direction and change gauge, not a probability: read change_24h and change_7d. This is a MEASURED STATE, not a forecast. Paid route: $0.02 USDC via x402. Call list_geo_themes first (free) to see keys and coverage before paying.

Free. Theme keys, labels, linked assets, coverage (qualifying markets, whale USD held, sufficient flag), method version and field notes for get_geo_themes. Use it to decide whether a paid call is worth making.

QSIG gold macro context in one call, point-in-time correct. Returns: regime (trend-state label: ranging, trending or mixed, with since and hours_in_regime), positioning_cot (CFTC managed-money and commercials net, weekly change, share of open interest, extreme flag, with report_date and the official released_at), rates (FRED 10-year real yield and breakeven inflation with 30-day change), geo (QSIG GeoRisk score and gold-linked Polymarket theme stress) and analogs (the 5 most similar past gold episodes and what followed them over 24h and 72h). as_of is an optional ISO 8601 UTC timestamp such as "2026-09-01T12:00:00Z". The hourly snapshot at or before it is returned AS IT WAS KNOWABLE THEN: a COT report counts only after its Friday release, analogs use a 7-day embargo so every outcome had closed. Use it for backtests without look-ahead. History begins 2026-07-14. asset accepts only "gold" in v1. Every block carries status (ok, stale or missing) and knowable_at. recorded=true rows were written live; recorded=false rows were filled from stored history. Analog outcomes are history, not a forecast. This is a MEASURED STATE, not a forecast. No prices, no direction. Paid route: $0.02 USDC via x402. Call get_gold_context_fields first (free) for field definitions and the available history range.

Free. Field definitions, units, knowability rules and the available history range (earliest, latest, row counts) for get_gold_context. Use it to decide whether a paid call is worth making.

QSIG geopolitical risk score (0-100, higher = more risk), with 24h change, 30/90-day percentile rank, regime label and event count. Returns the current score, or a historical one if as_of is given. as_of is an ISO 8601 UTC timestamp such as "2026-09-15T12:00:00Z"; the most recent observation at or before it is returned, with match_offset_seconds showing how far back the match was. History begins 2026-09-09 and is sampled every ~15 minutes, so earlier timestamps return an error rather than a score. This is a MEASURED STATE, not a forecast. No directional or predictive claim is made. Paid route: $0.02 USDC via x402. Call get_track_record first if you want to evaluate the service before paying.

Free. What QSIG sells - the georisk score, the geopolitical theme board (get_geo_themes) and the point-in-time gold macro context (get_gold_context) - what each does and does not claim, pricing, and the payment network.

Free. QSIG's published validation policy: which products are live, what validation each carries, and which models were KILLED for failing the pre-registered criterion (walk-forward AUC < 0.55), with reasons. Use this to judge whether the paid data is worth buying.