SCRIPTMASTERLABS — PRO-LO MCP Server

PRO-LO Coherence Gate: multi-path consensus for one ticker across PRO-LO's independent real directional signals (trade-engine composite, daily SMA20/50 trend, SqueezeOS graded picks, SML Triple-Trigger). Returns each path with direction (long/short/flat) and confidence, the coherence score, and pass/block gate. Same formula as the SML mcp-x402 Coherent Gate. Jev (TypeSafe) review is not run over MCP.

Paid (x402, 0.25 RLUSD) read-only decision product: computes PRO-LO multi-path coherence for a ticker — coherence = |Σ w·d| / Σ w across the signal paths (paths that cannot answer abstain and never vote) — and adds a Jev (TypeSafe AI) review. Verdict is PASS when consensus is non-flat, coherence >= 0.6, at least 2 paths agree, and the agreeing paths span at least 2 distinct data families (the trade composite and daily trend share the price series = one family); otherwise DENY, with a family-blocked DENY naming that reason. Jev review reports status unavailable when TYPESAFE_API_KEY is not configured — never simulated.

Real squeeze-pressure score from real chain-derived GEX and SEC fails-to-deliver pressure via the SqueezeOS FTD oracle — a disclosed proxy for short-selling pressure, not true short interest.

Real implied-volatility surface grid built directly from a real fetched options chain across several real expirations — every grid point is a real listed contract, not an interpolated/fabricated one.

Compares real fundamental signals (P/E, real reference data) against a disclosed, real-price-derived momentum/volatility proxy for narrative intensity. Real fundamental/social sentiment data is not currently wired — narrative-side scoring is disclosed as a proxy, not literal sentiment measurement.

Real dealer gamma exposure (GEX) computed from a real fetched options chain (Tradier/Polygon), and Reg SHO threshold-list status from the SEC fails-to-deliver record via the SqueezeOS FTD oracle.

Paid (x402, 0.25 RLUSD) pre-earnings coherence gate: four paths across three data families — SEC EDGAR insider Form 4 open-market direction, SEC fails-to-deliver pressure (SqueezeOS FTD oracle), front-expiration options flow imbalance, and dealer gamma-exposure structure (flow and structure are measured from one chain snapshot = one family) — vote into the fleet coherence formula coherence = |Σ w·d| / Σ w. Verdict is PASS when consensus is non-flat, coherence >= 0.6, at least 2 paths agree, and the agreeing paths span at least 2 distinct data families; otherwise DENY. Paths that cannot answer abstain and are named in the output — they never vote. Includes a Jev (TypeSafe AI) review (status unavailable when not configured — never simulated). SHADOW posture: decision_eligible is false; the gate executes nothing.

Invokes Google Gemini with real, live-fetched market data as grounding context — no invented inputs are passed to the model.

Generates a disclosed-heuristic BUY/SELL/HOLD verdict and selects real, currently-listed option contracts (real strike, real expiration, real bid/ask/greeks) nearest a target delta band from a real fetched chain — never an invented contract.

Real wide-market scan (Polygon grouped-daily aggregates across the real US equity universe, not a fixed short symbol list, no pinned symbols) fused with the real per-symbol GEX/Hurst/IV-surface engines above.

Real Rescaled-Range Hurst exponent computed from real historical bars at each real timeframe (15M/1H/4H/1D/1W). Reports real excess kurtosis of the real return series. Does not compute a true Hölder singularity spectrum (requires tick-level history this build does not ingest) — abstains rather than fabricating one.

Runs a disclosed hypothetical shock scenario (from a static, pre-defined scenario catalog) against a real live quote. The projected impact is an explicit heuristic model applied to a real spot price, not a claimed prediction.