accueil / serveurs / Finance & Paiement / io.tooloracle/predictionguard
io.tooloracle/predictionguard
serveur MCP (Model Context Protocol) · PredictionGuard 1.0.0
Référencé dans l'annuaire. Seul le pentest comportemental fait foi, et il n'a pas encore été exécuté sur ce serveur.
Est-ce que io.tooloracle/predictionguard est sûr ?
Au dernier audit MCP Hub, le serveur MCP « io.tooloracle/predictionguard » est classé « Non encore testé ». Référencé dans l'annuaire. Seul le pentest comportemental fait foi, et il n'a pas encore été exécuté sur ce serveur. Le verdict est réévalué en continu ; consultez la fiche pour l'état à jour.
Méthode : MCP Hub analyse la description de chaque outil (couche 1) et, pour le verdict fort, exécute le serveur dans une micro-VM isolée avec leurres et réseau bloqué (couche 2). On publie des noms et des compteurs, jamais le contenu brut renvoyé par un outil.
Les 41 outils
- pg_adverse_media_entity≈ 158 tokens
Adverse media scan — negative news on fraud, money laundering, corruption, sanctions. Delegates to AMLOracle. Core building block for evidence chains that link a wallet or trader to publicly reported concerns (always cite the source, never attribute).
Paramètres, retour & exemple (3)
Paramètreslang· string · optionnel
Optional language (e.g. en, de)name· string · requis
Person or entity namelimit· integer · optionnel
Max results (default upstream)
Exemple d'appel{"name": "pg_adverse_media_entity", "arguments": {"name": "texte"}}Exemple de retour{"content": [{"type": "text", "text": "…"}]} - pg_classified_keyword_match≈ 224 tokens
Daily compliance triage: scans top Polymarket markets by 24h volume and flags those whose question text matches curated sensitive-keyword categories — military action, regime change, leadership death, diplomacy, intelligence ops, monetary policy, regulatory action. Returns flagged markets with monitoring severity (HIGH/MEDIUM/LOW), matched categories and keywords, and volume. Pair flagged HIGH markets with pg_insider_signal_scan for active surveillance.
Paramètres, retour & exemple (2)
Paramètreslimit· integer · optionnel
Max markets to scan (default 25, max 100)category· string · optionnel
Optional: filter to one category (military_action, regime_change, leadership_death, diplomacy, intelligence, monetary_policy, regulatory_action)
Exemple d'appel{"name": "pg_classified_keyword_match", "arguments": {"limit": 1, "category": "texte"}}Exemple de retour{"content": [{"type": "text", "text": "…"}]} - pg_evidence_bundle_market≈ 127 tokens
Complete forensic dossier for a single Polymarket market: market details + integrity scan + volume anomaly profile + Trust Layer provenance trace — aggregated into one dossier ready for manual review, press inquiry, or as input to a SAR report.
Paramètres, retour & exemple (2)
Paramètresid· string · optionnel
Market id / conditionIdslug· string · optionnel
Market slug
Exemple d'appel{"name": "pg_evidence_bundle_market", "arguments": {"id": "texte", "slug": "texte"}}Exemple de retour{"content": [{"type": "text", "text": "…"}]} - pg_information_advantage_score≈ 218 tokens
Composite A-F rating for whether a wallet appears to have had non-public information on a specific market. Aggregates pg_position_timing_anomaly (50% weight) + pg_insider_signal_scan (30%) plus bonuses for being in top positioners (+10), new to market (+10), and sensitive category (+10). Returns letter grade A-F, composite score 0-100, all component scores, and interpretation guide. Pattern-matches reported cases (Van Dyke, Hyperliquid whale). Statistical signal only — not a legal determination.
Paramètres, retour & exemple (3)
Paramètresid· string · optionnel
Market id / conditionIdslug· string · optionnel
Market slugwallet· string · requis
Wallet to score (0x + 40 hex)
Exemple d'appel{"name": "pg_information_advantage_score", "arguments": {"wallet": "texte"}}Exemple de retour{"content": [{"type": "text", "text": "…"}]} - pg_insider_alert_signed≈ 256 tokens
Issue a cryptographically signed, on-chain anchored integrity alert for a Polymarket market. Combines evidence_anchor + get_signed_fact from FeedOracle Trust Layer. Alerts are anchored on Polygon with an ECDSA signature and are externally verifiable via pg_verify_alert and the JWKS at feedoracle.io/.well-known/jwks.json.
Paramètres, retour & exemple (5)
Paramètresclaim· string · requis
Short human-readable claim being assertedsignals· array · optionnel
List of integrity signals triggeredwallets· array · optionnel
Optional list of related wallet addressesseverity· string · optionnel · LOW | MEDIUM | HIGH | CRITICAL
Alert severitymarket_slug· string · requis
Polymarket market slug
Exemple d'appel{"name": "pg_insider_alert_signed", "arguments": {"claim": "texte", "market_slug": "texte"}}Exemple de retour{"content": [{"type": "text", "text": "…"}]} - pg_insider_signal_scan≈ 252 tokens
Real-time insider-trading signal scan for a single Polymarket market. Aggregates 5 signals: (1) very large pre-event positions, (2) high ratio of wallets new to this market, (3) coordinated minute-bucket timing clusters, (4) one-sided positioning, (5) sensitive-keyword category match (military/regime/intel). Returns a 0-100 score (CLEAN/LOW/MEDIUM/HIGH/CRITICAL), triggered signals with evidence, top 5 positioners with new-wallet flag, and full methodology for audit. Default window = 72h before market end.
Paramètres, retour & exemple (4)
Paramètresid· string · optionnel
Market id / conditionIdslug· string · optionnel
Polymarket market slugwindow_hours· integer · optionnel
Pre-event window to analyze (default 72h)min_position_usd· number · optionnel
Min notional to flag (default $1000)
Exemple d'appel{"name": "pg_insider_signal_scan", "arguments": {"id": "texte", "slug": "texte", "window_hours": 1, "min_position_usd": 1}}Exemple de retour{"content": [{"type": "text", "text": "…"}]} - pg_kalshi_conflict_of_interest_check≈ 255 tokens
CFTC Rule 5.17(z) conflict-of-interest pre-trade check. Analyzes a Kalshi market's metadata to detect whether trading it would expose decision-makers (election candidates, government officials, athletes, regulators) to insider-trading liability. Pattern-matches against the Kalshi April 2026 disciplinary cases (Moran/Klein/Enriquez) and the CFTC Van Dyke complaint. Returns ALLOW/MONITOR/WARN/BLOCK recommendation + 0-100 score + reference cases. Cannot identify actual trader identity (Kalshi public API anonymizes users) — pair with internal surveillance for full enforcement.
Paramètres, retour & exemple (3)
Paramètresticker· string · optionnel
Kalshi market tickerevent_ticker· string · optionnel
Or event_ticker for the whole eventcandidate_name· string · optionnel
Optional: specific person's name to match against title (e.g. 'Mark Moran')
Exemple d'appel{"name": "pg_kalshi_conflict_of_interest_check", "arguments": {"ticker": "texte", "event_ticker": "texte", "candidate_name": "texte"}}Exemple de retour{"content": [{"type": "text", "text": "…"}]} - pg_kalshi_market_details≈ 167 tokens
Detailed Kalshi market or event info. Pass 'ticker' for a single market (returns yes/no bids+asks, last price, volume, OI, spread, hours until close) or 'event_ticker' for all markets in an event (multi-outcome). Includes the rules_primary text (Kalshi's settlement criteria) which is critical for understanding resolution risk.
Paramètres, retour & exemple (2)
Paramètresticker· string · optionnel
Kalshi market ticker (e.g. KXG7LEADEROUT-45JAN01-DJT)event_ticker· string · optionnel
Kalshi event ticker (returns all child markets)
Exemple d'appel{"name": "pg_kalshi_market_details", "arguments": {"ticker": "texte", "event_ticker": "texte"}}Exemple de retour{"content": [{"type": "text", "text": "…"}]} - pg_kalshi_orderbook_analysis≈ 171 tokens
Forensic orderbook analysis for one Kalshi market. Detects manipulation-vulnerable patterns: (1) wide spread (>$0.10), (2) shallow depth (<10 contracts), (3) few price levels, (4) single-order dominance (>80% in top level), (5) penny-wall pattern (large bids at ≤$0.005, commonly used to fake depth). Returns 0-100 score, severity, and full level-by-level data. Kalshi returns bids only — implied asks computed via yes_bid + no_bid = $1 reciprocity.
Paramètres, retour & exemple (1)
Paramètresticker· string · requis
Kalshi market ticker
Exemple d'appel{"name": "pg_kalshi_orderbook_analysis", "arguments": {"ticker": "texte"}}Exemple de retour{"content": [{"type": "text", "text": "…"}]} - pg_kalshi_resolution_calendar≈ 176 tokens
Compliance briefing: which Kalshi markets resolve in the next N hours? Bucketed by 6h, 24h, 48h, 1 week. Flags markets in CFTC-sensitive categories (Elections, Politics). Use for daily surveillance prep — markets near resolution have highest insider-trading risk window.
Paramètres, retour & exemple (3)
Paramètrescategory· string · optionnel
Optional category filterhours_ahead· integer · optionnel
Look-ahead window (default 48h, max 168h)min_open_interest· number · optionnel
Only markets with at least this OI
Exemple d'appel{"name": "pg_kalshi_resolution_calendar", "arguments": {"category": "texte", "hours_ahead": 1, "min_open_interest": 1}}Exemple de retour{"content": [{"type": "text", "text": "…"}]} - pg_kalshi_search≈ 220 tokens
Search Kalshi prediction markets (CFTC-regulated event contracts). Returns events ranked by aggregate 24h volume across all markets in the event. Kalshi categories include Elections, Politics, Economics, Climate, Sports, Entertainment, Financials. Public data, no auth needed. Each event has one or more child markets (mutually exclusive or yes/no).
Paramètres, retour & exemple (4)
Paramètreslimit· integer · optionnel
Max events to return (default 25, max 100)query· string · optionnel
Keyword search in title, sub_title, event_tickerstatus· string · optionnel · open | closed | settledcategory· string · optionnel
Optional category filter (Elections, Politics, Economics, ...)
Exemple d'appel{"name": "pg_kalshi_search", "arguments": {"limit": 1, "query": "texte", "status": "open", "category": "texte"}}Exemple de retour{"content": [{"type": "text", "text": "…"}]} - pg_kalshi_thin_market_alert≈ 158 tokens
Scan all open Kalshi markets and flag those that are manipulation-vulnerable: closing soon (<24h), low open interest, low liquidity, wide spread, low volume. Daily triage tool. Returns markets ranked by risk_score (≥30 threshold). Best paired with pg_kalshi_resolution_calendar for full compliance briefing.
Paramètres, retour & exemple (2)
Paramètrescategory· string · optionnel
Optional category filtermax_results· integer · optionnel
Max flagged markets (default 25, max 50)
Exemple d'appel{"name": "pg_kalshi_thin_market_alert", "arguments": {"category": "texte", "max_results": 1}}Exemple de retour{"content": [{"type": "text", "text": "…"}]} - pg_kalshi_trending≈ 130 tokens
Top trending Kalshi events ranked by aggregate 24h volume across child markets. Filterable by category. Daily-briefing-ready output. Includes the highest-volume sub-market per event.
Paramètres, retour & exemple (2)
Paramètreslimit· integer · optionnel
Max events to return (default 25, max 50)category· string · optionnel
Optional category filter (Elections, Politics, ...)
Exemple d'appel{"name": "pg_kalshi_trending", "arguments": {"limit": 1, "category": "texte"}}Exemple de retour{"content": [{"type": "text", "text": "…"}]} - pg_known_cases≈ 156 tokens
Registry of publicly reported prediction-market integrity cases (Théo / French whale, Hyperliquid whale, Venezuela, Iran strikes, Nuclear, UMA Ukraine). Filter by category or minimum AML relevance (low/medium/high). Summaries only — no accusations against named parties.
Paramètres, retour & exemple (2)
Paramètrescategory· string · optionnel
Optional category substring (e.g. 'geopolitical', 'oracle')min_aml_relevance· string · optionnel · low | medium | high
Minimum AML relevance
Exemple d'appel{"name": "pg_known_cases", "arguments": {"category": "texte", "min_aml_relevance": "low"}}Exemple de retour{"content": [{"type": "text", "text": "…"}]} - pg_kyc_bundle_entity≈ 116 tokens
Full KYC bundle for a named entity: sanctions + PEP + adverse media + country risk in a single call. Delegates to AMLOracle.kyc_bundle.
Paramètres, retour & exemple (3)
Paramètresname· string · requiscountry· string · optionnel
ISO country codeentity_type· string · optionnel
'person' or 'organization'
Exemple d'appel{"name": "pg_kyc_bundle_entity", "arguments": {"name": "texte"}}Exemple de retour{"content": [{"type": "text", "text": "…"}]} - pg_market_details≈ 99 tokens
Full market info: outcomes, outcome prices, volume, liquidity, best bid/ask, spread, resolution source, conditionId. Provide 'slug' or 'id'.
Paramètres, retour & exemple (2)
Paramètresid· string · optionnel
Market id / conditionIdslug· string · optionnel
Market slug
Exemple d'appel{"name": "pg_market_details", "arguments": {"id": "texte", "slug": "texte"}}Exemple de retour{"content": [{"type": "text", "text": "…"}]} - pg_market_integrity_scan≈ 112 tokens
Multi-signal integrity scan: combines thin-book flag, spread, low liquidity, geopolitical-term pattern, end-date proximity, and 24h volume concentration. Returns score 0-100, level HIGH/MEDIUM/LOW/CLEAN, triggered signals, and an operational recommendation.
Paramètres, retour & exemple (2)
Paramètresid· string · optionnelslug· string · optionnel
Exemple d'appel{"name": "pg_market_integrity_scan", "arguments": {"id": "texte", "slug": "texte"}}Exemple de retour{"content": [{"type": "text", "text": "…"}]} - pg_market_search≈ 137 tokens
Search Polymarket markets by keyword (e.g. 'election', 'fed', 'bitcoin'). Returns question, slug, 24h volume, liquidity, end date.
Paramètres, retour & exemple (3)
Paramètreslimit· integer · optionnel
Max results (default 10, max 50)query· string · requis
Keyword to searchactive_only· boolean · optionnel
Only active / non-closed markets
Exemple d'appel{"name": "pg_market_search", "arguments": {"query": "texte"}}Exemple de retour{"content": [{"type": "text", "text": "…"}]} - pg_market_trades≈ 324 tokens
Raw trade access for a Polymarket market via the Polymarket Data API. Supports client-side filters: time range (from/to, ISO 8601), side (BUY/SELL), minimum trade size, or a specific wallet. Paginates server-side (max 25 pages × 1000 trades). Returns compact records with wallet, pseudonym, side, size, price, notional USD, outcome, timestamp, tx_hash.
Paramètres, retour & exemple (9)
Paramètresid· string · optionnel
Market id / conditionIdto· string · optionnel
Only include trades up to this ISO timestampfrom· string · optionnel
Only include trades from this ISO timestampside· string · optionnel · BUY | SELL
Only trades on this sideslug· string · optionnel
Polymarket market sluglimit· integer · optionnel
Max trades to return after filtering (default 100, max 5000)wallet· string · optionnel
Filter to a single wallet addressmin_size· number · optionnel
Minimum trade size (shares)max_pages· integer · optionnel
How many pages of 1000 to fetch (default 2, max 25)
Exemple d'appel{"name": "pg_market_trades", "arguments": {"id": "texte", "to": "texte", "from": "texte", "side": "BUY", "slug": "texte", "limit": 1}}Exemple de retour{"content": [{"type": "text", "text": "…"}]} - pg_market_volume_profile≈ 91 tokens
Volume anomaly heuristic: compares 24h volume vs average daily volume since market start (z-like ratio) and flags thin-book situations where 24h volume >> on-book liquidity.
Paramètres, retour & exemple (2)
Paramètresid· string · optionnelslug· string · optionnel
Exemple d'appel{"name": "pg_market_volume_profile", "arguments": {"id": "texte", "slug": "texte"}}Exemple de retour{"content": [{"type": "text", "text": "…"}]} - pg_overview≈ 68 tokens
PredictionGuard platform overview: covered platforms, tool inventory, Polymarket Gamma API ping, Polygon RPC ping (Ankr-backed), known-case count.
Paramètres, retour & exemple (0)
Exemple d'appel{"name": "pg_overview", "arguments": {}}Exemple de retour{"content": [{"type": "text", "text": "…"}]} - pg_pep_check_entity≈ 112 tokens
Politically Exposed Person (PEP) check via Wikidata. Delegates to AMLOracle. Relevant for prediction markets where reported traders overlap with political figures.
Paramètres, retour & exemple (2)
Paramètresname· string · requis
Person namecountry· string · optionnel
Optional ISO country code
Exemple d'appel{"name": "pg_pep_check_entity", "arguments": {"name": "texte"}}Exemple de retour{"content": [{"type": "text", "text": "…"}]} - pg_position_timing_anomaly≈ 206 tokens
Statistical timing analysis of a single wallet's position on a specific market. Checks: (1) how close to resolution the wallet entered (<6h=35pts, <24h=25pts, <72h=10pts), (2) position size vs market average (>20× avg=25pts, >5× avg=10pts), (3) single-bet pattern (≤3 trades=10pts, no historical trading rationale). Returns 0-100 score, first-trade timestamp, total notional, and methodology. Pair with pg_information_advantage_score for full assessment.
Paramètres, retour & exemple (3)
Paramètresid· string · optionnel
Market id / conditionIdslug· string · optionnel
Market slugwallet· string · requis
Wallet to analyze (0x + 40 hex)
Exemple d'appel{"name": "pg_position_timing_anomaly", "arguments": {"wallet": "texte"}}Exemple de retour{"content": [{"type": "text", "text": "…"}]} - pg_pre_event_flow_analysis≈ 227 tokens
Analyze pre-resolution positioning on a Polymarket market. For the N days before the market's endDate, aggregates trades by wallet, classifies wallets new to the market in that window, detects volume concentration, timing clusters (minutes where ≥5 distinct wallets trade in sync), and pre-event volume spikes vs historical average. Returns a 0–100 risk score (CRITICAL/HIGH/MEDIUM/LOW/CLEAN) with triggered signals, top 10 positioners, and top 10 new wallets. Default window = 7 days.
Paramètres, retour & exemple (4)
Paramètresid· string · optionnelslug· string · optionnelmax_pages· integer · optionnel
Trade pagination depth (default 10, max 25)days_before_end· number · optionnel
Pre-event window size in days (1–90, default 7)
Exemple d'appel{"name": "pg_pre_event_flow_analysis", "arguments": {"id": "texte", "slug": "texte", "max_pages": 1, "days_before_end": 1}}Exemple de retour{"content": [{"type": "text", "text": "…"}]} - pg_prediction_market_integrity_gate≈ 333 tokens
Pre-trade integrity gate for AI agents and compliance teams. ONE call returns ALLOW/WARN/BLOCK decision + risk_level (0-100) + signed evidence receipt. Aggregates orderbook analysis, resolution-window risk, CFTC Rule 5.17(z) conflict-of-interest check, and (Polymarket) insider signal scan. Supports both Polymarket (slug) and Kalshi (ticker). Optional inputs: wallet (Polymarket-side checks), candidate name (Kalshi Rule 5.17(z) name match), amount_usd (amplifies risk for large bets on thin markets). Returns hashable + ECDSA-signed receipt for audit. Designed for x402 paywall pre-trade calls — agent pays once, gets binary go/no-go.
Paramètres, retour & exemple (5)
Paramètreswallet· string · optionnel
Optional: Polygon wallet address (Polymarket only)platform· string · requis · polymarket | kalshi
Which prediction marketcandidate· string · optionnel
Optional: candidate name for Kalshi Rule 5.17(z) name matchmarket_id· string · requis
Polymarket slug or Kalshi ticker/event_tickeramount_usd· number · optionnel
Optional: bet size for risk amplification
Exemple d'appel{"name": "pg_prediction_market_integrity_gate", "arguments": {"platform": "polymarket", "market_id": "texte"}}Exemple de retour{"content": [{"type": "text", "text": "…"}]} - pg_resolution_risk_score≈ 154 tokens
Multi-signal resolution-risk score (0–100, CLEAN/LOW/MEDIUM/HIGH/CRITICAL) for a Polymarket market. Combines category priors (geopolitical/election/sanctions patterns from pg_known_cases), resolution-phase proximity, market volume, resolution-source sanity check (is the UMA adapter a real deployed contract), UMA global dispute ratio, and thin-book flag. Returns triggered signals with point deductions for full auditability.
Paramètres, retour & exemple (2)
Paramètresid· string · optionnelslug· string · optionnel
Exemple d'appel{"name": "pg_resolution_risk_score", "arguments": {"id": "texte", "slug": "texte"}}Exemple de retour{"content": [{"type": "text", "text": "…"}]} - pg_sanctions_screen_entity≈ 154 tokens
Screen a named entity against global sanctions lists (OFAC SDN, EU FSF, UN SC, Interpol). Delegates to AMLOracle. Use after resolving a wallet/trader to a real name via public reporting or known-case registry.
Paramètres, retour & exemple (3)
Paramètresname· string · requis
Person or entity namethreshold· number · optionnel
Optional fuzzy-match threshold (0..1)entity_type· string · optionnel
Optional: 'person' or 'organization'
Exemple d'appel{"name": "pg_sanctions_screen_entity", "arguments": {"name": "texte"}}Exemple de retour{"content": [{"type": "text", "text": "…"}]} - pg_sar_report≈ 640 tokens
Generate a draft Suspicious Activity Report (SAR/STR) from structured inputs. Supports EU_GENERIC (FATF-aligned STR, default), US_FINCEN (Form 111 structure), and DE_goAML (German FIU draft). Takes subject, market, activity window, integrity signals, and evidence references — auto-classifies the primary suspicious activity type, generates a narrative, and renders regulator-style markdown. Output is marked draft_for_review; PredictionGuard does not submit SARs directly.
Paramètres, retour & exemple (8)
Paramètresfiler· object · optionnel
Information about the preparing institution.market· object · optionnel
Optional. Polymarket market context.signals· array · optionnel
Integrity signals (strings or objects with 'term'/'reason'/'layer'). Pass the 'triggered_signals' array from pg_market_integrity_scan or pg_resolution_risk_score directly.subject· object · requis
Required. The subject of the report.activity· object · optionnel
Activity window and amounts.evidence· object · optionnel
References to prior evidence.narrative_addendum· string · optionnel
Optional free-text addendum from the analyst.filing_jurisdiction· string · optionnel · EU_GENERIC | US_FINCEN | DE_goAML
Report format. Default EU_GENERIC.
Exemple d'appel{"name": "pg_sar_report", "arguments": {"subject": {}}}Exemple de retour{"content": [{"type": "text", "text": "…"}]} - pg_trending_markets≈ 92 tokens
Top Polymarket markets by 24h volume. Useful for daily compliance triage / catching news catalysts before they land in mainstream coverage.
Paramètres, retour & exemple (1)
Paramètreslimit· integer · optionnel
Max results (default 10, max 25)
Exemple d'appel{"name": "pg_trending_markets", "arguments": {"limit": 1}}Exemple de retour{"content": [{"type": "text", "text": "…"}]} - pg_uma_market_resolution≈ 149 tokens
Resolution source and phase for a specific Polymarket market. Fetches market metadata from Gamma, extracts the resolutionSource address, verifies it's a deployed contract on Polygon, and classifies the resolution phase (active_trading / approaching_resolution / imminent_resolution_window / past_end_awaiting_resolution / resolved).
Paramètres, retour & exemple (2)
Paramètresid· string · optionnel
Market id / conditionIdslug· string · optionnel
Market slug
Exemple d'appel{"name": "pg_uma_market_resolution", "arguments": {"id": "texte", "slug": "texte"}}Exemple de retour{"content": [{"type": "text", "text": "…"}]} - pg_uma_status≈ 168 tokens
Global UMA Optimistic Oracle health on Polygon. Scans event logs from OOv2 (and optionally OOv1) over a configurable window, tallies events by type (RequestPrice / ProposePrice / DisputePrice / Settle), computes per-hour rate, and derives a dispute/propose ratio — a leading indicator of oracle-level contention.
Paramètres, retour & exemple (2)
Paramètresinclude_v1· boolean · optionnel
Also scan UMA OOv1 (legacy, default false)blocks_back· integer · optionnel
Blocks to scan back (default 5000 ≈ 3h, max 20000)
Exemple d'appel{"name": "pg_uma_status", "arguments": {"include_v1": true, "blocks_back": 1}}Exemple de retour{"content": [{"type": "text", "text": "…"}]} - pg_verify_alert≈ 119 tokens
Verify a previously issued signed alert (JWS or content-hash). Delegates to Trust Layer verify_signature. Returns validity, signer, and timestamp. JWKS at feedoracle.io/.well-known/jwks.json.
Paramètres, retour & exemple (2)
Paramètresjws· string · optionnel
Full JWS stringcontent_hash· string · optionnel
SHA-256 content hash (alternative to JWS)
Exemple d'appel{"name": "pg_verify_alert", "arguments": {"jws": "texte", "content_hash": "texte"}}Exemple de retour{"content": [{"type": "text", "text": "…"}]} - pg_wallet_correlation_match≈ 203 tokens
Find wallets that co-trade across multiple sensitive Polymarket markets with a target wallet. Given a wallet and 2-10 market slugs, returns: which markets the target traded, top 20 cotraders ranked by overlap count, and an aggregate severity score (≥3 shared markets = MEDIUM, ≥5 = HIGH). Use case: detect coordinated trading rings, shared-info syndicates, or wallet clusters that consistently bet on the same sensitive events.
Paramètres, retour & exemple (2)
Paramètreswallet· string · requis
Target wallet address (0x + 40 hex)markets· array · requis
2-10 market slugs to check for co-trading overlap
Exemple d'appel{"name": "pg_wallet_correlation_match", "arguments": {"wallet": "texte", "markets": []}}Exemple de retour{"content": [{"type": "text", "text": "…"}]} - pg_wallet_entity_resolve≈ 140 tokens
Resolve a Polygon address to a known entity via PredictionGuard's Wallet Registry (Polymarket core contracts, major stablecoins, known CEX hot wallets), falling back to on-chain heuristic classification for unknown addresses. Returns entity name, type, category, AML relevance, confidence, and source-of-record URL.
Paramètres, retour & exemple (1)
Paramètresaddress· string · requis
Polygon address (0x + 40 hex chars)
Exemple d'appel{"name": "pg_wallet_entity_resolve", "arguments": {"address": "texte"}}Exemple de retour{"content": [{"type": "text", "text": "…"}]} - pg_wallet_lookup≈ 112 tokens
Polygon wallet base profile via JSON-RPC (Ankr-backed when RPC_POLYGON is set, public fallback otherwise). Returns MATIC balance, outbound tx count, contract-vs-EOA detection, and a lightweight risk heuristic.
Paramètres, retour & exemple (1)
Paramètresaddress· string · requis
Polygon address (0x + 40 hex chars)
Exemple d'appel{"name": "pg_wallet_lookup", "arguments": {"address": "texte"}}Exemple de retour{"content": [{"type": "text", "text": "…"}]} - pg_wallet_risk_profile≈ 147 tokens
Aggregated A–F risk profile for a Polygon wallet. Combines on-chain behavior (pg_wallet_lookup), entity resolution (pg_wallet_entity_resolve), and — where the entity can be screened — AML bundle (sanctions + PEP + adverse media via AMLOracle). Grade A = clean, F = blocked. Includes triggered flags with points deductions for full auditability.
Paramètres, retour & exemple (1)
Paramètresaddress· string · requis
Polygon address (0x + 40 hex chars)
Exemple d'appel{"name": "pg_wallet_risk_profile", "arguments": {"address": "texte"}}Exemple de retour{"content": [{"type": "text", "text": "…"}]} - pg_whale_add≈ 218 tokens
Add a Polygon wallet to the PredictionGuard watchlist. Takes an initial baseline snapshot so subsequent pg_whale_scan calls can detect movement. Set alert_threshold_matic to tune sensitivity (default 100 MATIC). Tags are free-form.
Paramètres, retour & exemple (5)
Paramètrestags· array · optionnel
Free-form tags (e.g. ['polymarket','pre-election','whale'])alias· string · optionnel
Optional human-readable labelnotes· string · optionnel
Free-form notesaddress· string · requis
Polygon address (0x + 40 hex)alert_threshold_matic· number · optionnel
Balance delta threshold in MATIC for alerts (default 100)
Exemple d'appel{"name": "pg_whale_add", "arguments": {"address": "texte"}}Exemple de retour{"content": [{"type": "text", "text": "…"}]} - pg_whale_alerts≈ 154 tokens
Retrieve alerts from the watchlist audit log. Filter by address, severity (LOW/MEDIUM/HIGH/CRITICAL), and/or ISO timestamp 'since'. Default returns the 50 most recent alerts across the whole watchlist.
Paramètres, retour & exemple (4)
Paramètreslimit· integer · optionnel
Max results (max 500)since· string · optionnel
ISO 8601 timestamp (e.g. 2026-04-20T00:00:00Z)address· string · optionnelseverity· string · optionnel · LOW | MEDIUM | HIGH | CRITICAL
Exemple d'appel{"name": "pg_whale_alerts", "arguments": {"limit": 1, "since": "texte", "address": "texte", "severity": "LOW"}}Exemple de retour{"content": [{"type": "text", "text": "…"}]} - pg_whale_list≈ 97 tokens
List all watched wallets with their alias, threshold, tags, notes, and last snapshot. Optionally filter by tag.
Paramètres, retour & exemple (2)
Paramètrestag· string · optionnel
Optional tag filterlimit· integer · optionnel
Max results (max 500)
Exemple d'appel{"name": "pg_whale_list", "arguments": {"tag": "texte", "limit": 1}}Exemple de retour{"content": [{"type": "text", "text": "…"}]} - pg_whale_remove≈ 116 tokens
Remove a wallet from the watchlist. By default keeps historical snapshots and alerts (for audit trail). Set keep_history=false to purge everything for this address.
Paramètres, retour & exemple (2)
Paramètresaddress· string · requiskeep_history· boolean · optionnel
Keep snapshot + alert history (default true)
Exemple d'appel{"name": "pg_whale_remove", "arguments": {"address": "texte"}}Exemple de retour{"content": [{"type": "text", "text": "…"}]} - pg_whale_scan≈ 154 tokens
Scan one or all watched wallets against Polygon RPC. Compares current balance + nonce to the last snapshot, writes a new snapshot, and emits an alert when the delta exceeds the wallet's configured threshold. Severity is MEDIUM / HIGH / CRITICAL by delta size. Omit 'address' to scan the entire watchlist. Designed to be called periodically via SchedulerOracle or a systemd timer.
Paramètres, retour & exemple (1)
Paramètresaddress· string · optionnel
Optional — scan a single address. Omit to scan the whole list.
Exemple d'appel{"name": "pg_whale_scan", "arguments": {"address": "texte"}}Exemple de retour{"content": [{"type": "text", "text": "…"}]}
C'est votre serveur ?
Revendiquez-le sur l'espace créateur (preuve GitHub, domaine ou npm) pour afficher le badge « propriétaire vérifié » et lancer un pentest comportemental à la demande afin d'obtenir le badge « Vérifié ».