PredMCP

Measured conclusion: Deep-tested. L2 outcome: tools_ok.

Polymarket + Hyperliquid + macro for AI agents. 38 tools, signal backtest, SSE streaming. Free tier.

Add to your agent

Copy this into your MCP client config:

{
  "mcpServers": {
    "PredMCP": {
      "url": "https://predmcp.com/mcp",
      "transport": "streamable-http"
    }
  }
}

Measured tools (52)

• create_api_key

  Generate a free PredMCP API key. Requires an email. Returns the key and ready-to-use MCP config. Free tier: 100 calls/day, one key per IP.

  Parameters:

  • email (required) — string — Your email address — used to identify your key and for account recovery

  Hints: read-only no · destructive not declared · idempotent not declared · open-world no

• get_markets read-only

  Live prediction markets from Polymarket and/or HIP-4, sorted by volume. Returns title, YES/NO prices, 24h volume, and expiry.

  Parameters:

  • limit — integer — Number of markets to return (1–100, default: 20)
  • active — boolean — Filter to active/open markets only (default: true)
  • platform — string — Data source: "polymarket", "hip4", or "all" (default)

  Hints: read-only yes · destructive not declared · idempotent not declared · open-world yes

• get_odds read-only

  Current YES/NO prices and implied probability for any Polymarket or HIP-4 market token.

  Parameters:

  • platform (required) — string — Platform the market is on: "polymarket" or "hip4"
  • identifier (required) — string — For Polymarket: the token_id of the YES or NO outcome. For HIP-4: the base asset ticker (e.g. "BTC")

  Hints: read-only yes · destructive not declared · idempotent not declared · open-world yes

• get_orderbook read-only

  Full orderbook depth (bids + asks) for any Polymarket market token. Shows liquidity at each price level.

  Parameters:

  • token_id (required) — string — Polymarket token ID for the YES or NO side of a market

  Hints: read-only yes · destructive not declared · idempotent not declared · open-world yes

• search_markets read-only

  Full-text search across all Polymarket and HIP-4 prediction markets. Returns ranked results with current odds.

  Parameters:

  • query (required) — string — Keywords to search in market names and descriptions, e.g. "bitcoin ETF", "US election", "Fed pivot"
  • limit — integer — Maximum number of results to return (1–50, default: 10)

  Hints: read-only yes · destructive not declared · idempotent not declared · open-world yes

• get_whale_positions read-only

  Positions of a specific Polymarket wallet, optionally filtered to one market. The /positions API requires a user (no public "all holders by market" endpoint), so pass the wallet address of the trader you want to inspect.

  Parameters:

  • user (required) — string — Polygon wallet address (0x…) of the user whose positions you want.
  • condition_id — string — Optional — filter results to a specific market by condition_id.
  • min_size_usdc — number — Minimum position size in USDC to include in results (default: 1,000).

  Hints: read-only yes · destructive not declared · idempotent not declared · open-world yes

• get_movers read-only

  Top prediction markets ranked by 24h volume spike or biggest YES/NO price swing. Surfaces breaking news bets and momentum plays across Polymarket and HIP-4.

  Parameters:

  • limit — integer — Number of top movers to return (1–20, default: 10)

  Hints: read-only yes · destructive not declared · idempotent not declared · open-world yes

• get_markets_near_resolution read-only

  Polymarket markets resolving within the next N hours with a leading probability above threshold. Useful for resolution arbitrage and last-minute positioning.

  Parameters:

  • hours — number — Maximum hours until resolution (default: 24h, max: 168h = 7 days)
  • min_prob — number — Minimum leading outcome probability to include (default: 0.7 = 70%)

  Hints: read-only yes · destructive not declared · idempotent not declared · open-world yes

• get_volume_spikes read-only

  Polymarket markets with abnormal 24h volume vs their 7-day daily average. Volume spikes typically precede news events or informed positioning.

  Parameters:

  • limit — integer — Number of results to return (default: 15)
  • min_ratio — number — Minimum ratio of 24h volume vs 7-day daily average to qualify as a spike (default: 3x)

  Hints: read-only yes · destructive not declared · idempotent not declared · open-world yes

• get_late_game_sports read-only

  Sports prediction markets on Polymarket closing within a few hours with a high-certainty leading outcome. Targets near-certain resolution for late-game positioning.

  Parameters:

  • hours_max — number — Maximum hours until market closes (default: 6h)
  • certainty_pct — number — Minimum leading outcome probability as percentage, e.g. 85 = 85% (default: 85)

  Hints: read-only yes · destructive not declared · idempotent not declared · open-world yes

• get_funding_rates read-only

  Current funding rates for Hyperliquid perpetuals. Positive rate = longs pay shorts (bearish bias); negative = shorts pay longs (bullish bias).

  Parameters:

  • coins — array — List of asset tickers to fetch, e.g. ["BTC", "ETH"]. Omit to fetch all available assets.

  Hints: read-only yes · destructive not declared · idempotent not declared · open-world yes

• get_whale_trades read-only

  Recent large trades on Hyperliquid perps above a notional threshold. Includes side (long/short), size, price, and timestamp.

  Parameters:

  • coin (required) — string — Asset ticker to fetch whale trades for, e.g. "BTC", "ETH"
  • min_notional_usdc — number — Minimum trade size in USDC to qualify as a whale trade (default: 50,000)

  Hints: read-only yes · destructive not declared · idempotent not declared · open-world yes

• get_top_funding_rates read-only

  Top Hyperliquid perps ranked by absolute funding rate, with OI and annualized yield. Useful for finding the most overcrowded longs/shorts and carry opportunities.

  Parameters:

  • limit — integer — Number of top results to return (default: 10)
  • min_abs_rate — number — Minimum absolute funding rate to include, e.g. 0.0001. Omit to include all.

  Hints: read-only yes · destructive not declared · idempotent not declared · open-world yes

• get_oi_near_cap read-only

  Lists Hyperliquid perps that are currently at the open interest cap — new long positions cannot be opened. Use as a blacklist to avoid getting rejected on entry.

  Hints: read-only yes · destructive not declared · idempotent not declared · open-world yes

• get_orderbook_depth read-only

  Full orderbook depth + slippage estimate for any Hyperliquid perp or HIP-4 market. Returns top of book, spread, cumulative depth at $100/$500/$1k/$5k tiers, and estimated slippage for a given order size. Critical for HIP-4 farming and low-liquidity assets where market orders get destroyed by slippage.

  Parameters:

  • coin (required) — string — Asset ticker (BTC, ETH, SOL) or HIP-4 contract name (e.g. "BTC>81041@20260512-0600")
  • side — string — Order side: "buy" (taker into asks) or "sell" (taker into bids)
  • size_usdc — number — Order size in USDC to estimate slippage for (default: 200)

  Hints: read-only yes · destructive not declared · idempotent not declared · open-world yes

• get_price_summary read-only

  One-call snapshot for an asset: mark price, 24h and 7d returns, 30d high/low, drawdown from high, rally from low, annualized realised volatility. Computed from 30d of HL hourly candles.

  Parameters:

  • asset (required) — string — Asset ticker, e.g. "BTC", "HYPE"

  Hints: read-only yes · destructive not declared · idempotent not declared · open-world yes

• get_basic_macro read-only

  DXY, US10Y yield, S&P 500, gold, VIX — direct from free Yahoo Finance. Raw values + 1d change. Pro adds BTC dominance, ETH/BTC, total crypto mcap, and a RISK_ON/OFF regime classifier.

  Hints: read-only yes · destructive not declared · idempotent not declared · open-world yes

• get_recent_news read-only

  Recent crypto news headlines matching an asset ticker, from CoinDesk + The Block + Decrypt + Cointelegraph RSS feeds. Pro adds the 1h price move that followed each headline.

  Parameters:

  • asset (required) — string — Asset ticker to filter on, e.g. "BTC", "ETH", "HYPE"
  • limit — integer — Max headlines returned (default: 10)
  • hours_back — integer — Lookback window in hours (default: 24, max: 168 = 7 days)

  Hints: read-only yes · destructive not declared · idempotent not declared · open-world yes

• get_news_feed read-only

  Recent headlines across crypto, finance and sports RSS feeds, unfiltered and unclassified. Unlike get_recent_news it does not filter by asset ticker, so it also covers the sports, macro and event markets that make up most of a HIP-4 board. Match the headlines against your own market list.

  Parameters:

  • limit — integer — Max headlines returned (default 40, max 100).
  • category — string — Restrict to one feed category (default: all).
  • hours_back — integer — Lookback window in hours (default 24, max 168).

  Hints: read-only yes · destructive not declared · idempotent not declared · open-world yes

• get_simple_iv read-only

  BTC or ETH options snapshot via free Deribit public feed: ATM implied volatility, total OI, 24h volume. Pro adds put-call skew + full term structure parsing.

  Parameters:

  • asset (required) — string — Underlying — Deribit free feed supports BTC and ETH.

  Hints: read-only yes · destructive not declared · idempotent not declared · open-world yes

• get_outcome_fair_value read-only

  Options/vol-implied fair value for a HIP-4 binary/range/touch PRICE market ("<asset> above $X at time T?"). Returns the risk-neutral probability the market resolves YES, and — if you pass market_yes_price — the signed edge in probability points and a YES cheap/rich/fair verdict. BTC/ETH price off the live Deribit IV smile (interpolated to strike + DTE); ANY other asset falls back to Hyperliquid 30d realized vol. iv_source labels which was used (smile/term_interp/skew_adj/atm/realized_vol). The touch case uses the correct drifted first-passage formula. Approximations are listed in caveats.

  Parameters:

  • asset (required) — string — Underlying ticker, e.g. "BTC", "ETH", "SOL", "HYPE". BTC/ETH use the Deribit IV smile; others use Hyperliquid realized vol.
  • strike (required) — number — The market's strike / threshold price, e.g. 70000.
  • expiry_iso (required) — string — Market resolution time as an ISO 8601 string, e.g. "2026-08-21T06:00:00Z".
  • comparator (required) — string — Market shape: above/below a strike, inside a range [strike, strike_high], or touches the strike before expiry.
  • strike_high — number — Upper bound for range markets (must be > strike). Ignored otherwise.
  • market_yes_price — number — Current on-chain YES price (0..1) to compute the edge against fair value.

  Hints: read-only yes · destructive not declared · idempotent not declared · open-world yes

• get_outcome_edges read-only

  One-call mispricing scanner for autonomous agents: every live HIP-4 PRICE market, each priced against its options/vol-implied fair value and ranked by |edge|. BTC/ETH use the Deribit IV smile; other assets use Hyperliquid realized vol (iv_source labels which). edge_pt = (implied_prob - yes_price)*100, computed only where a real traded YES price exists (synthetic/untraded 0.5 placeholders return edge_pt:null so no fake edge is surfaced). Filter with min_edge_pt / underlying. The whole board without looping.

  Parameters:

  • limit — integer — Max markets to return (default 30, max 100).
  • underlying — string — Filter to one underlying ticker, e.g. "BTC".
  • min_edge_pt — number — Only return markets whose |edge| in probability points is at least this (default 0 = the whole board).

  Hints: read-only yes · destructive not declared · idempotent not declared · open-world yes

• get_market_edge read-only

  Universal fair-value anchor for ONE market of ANY category. Pass the question (+ optional strike/comparator/expiry/underlying for price markets, + yes_price). Dispatches to the best anchor: options/vol fair value (crypto price), a confident Polymarket twin (events/politics/sports), or a soft news lean. Returns { method, confidence, anchor_prob, hip4_yes, edge_pt, verdict, source_ref, note }. edge_pt = (anchor_prob - hip4_yes)*100; positive = YES cheap; null for untraded/synthetic prices.

  Parameters:

  • question (required) — string — The market question, e.g. "BTC above $70,000 at Aug 21 06:00 UTC?" or "Will Fed cut rates in September?"
  • strike — number — Strike/threshold for price markets.
  • vol_24h — number — 24h traded volume of the market. REQUIRED for an edge/verdict: absent (or 0) the YES price is treated as untraded and only the anchor is returned.
  • is_traded — boolean — Explicit attestation that the YES price comes from a real traded book. Alternative to vol_24h.
  • yes_price — number — Current on-chain YES price (0..1). Edge is only computed for a real traded price (0.5 exactly is treated as synthetic/untraded).
  • comparator — string — Price-market shape.
  • expiry_iso — string — Resolution time (ISO 8601) for price markets.
  • underlying — string — Underlying ticker for price markets, e.g. "BTC".
  • strike_high — number — Upper bound for range price markets.

  Hints: read-only yes · destructive not declared · idempotent not declared · open-world yes

• get_market_edges read-only

  One-call universal mispricing scanner across ALL HIP-4 market types (crypto price, sports, politics, macro, events). Resolves every market to its best anchor (options / Polymarket twin / news lean / none) and ranks by |edge|. Filter with method / min_edge_pt / limit. Returns by_method counts + ranked markets. Superset of get_outcome_edges.

  Parameters:

  • limit — integer — Max markets to return (default 30, max 100).
  • method — string — Filter to markets resolved via one anchor method. Passing "news" also enables the (slower) news lean.
  • min_edge_pt — number — Only return markets whose |edge| in probability points is at least this (default 0 = whole board).

  Hints: read-only yes · destructive not declared · idempotent not declared · open-world yes

• get_news_signals read-only

  News → markets recommender: pulls recent crypto headlines, classifies each event type (depeg/hack_exploit/listing/delisting/unlock/regulatory/partnership/outage/hype/fud/macro), extracts the assets, maps to affected HIP-4 markets, and assigns a directional lean (YES up / YES down). Heuristic, low/medium confidence, NOT financial advice; war/hard-politics excluded. Powers a live "event → affected markets → lean" feed. Filter with hours / event_type / min_confidence / limit.

  Parameters:

  • hours — integer — Lookback window for headlines (default 24h, max 72h).
  • limit — integer — Max signals to return (default 20, max 50).
  • event_type — string — Filter to one event type.
  • min_confidence — string — Minimum confidence to include (default: low).

  Hints: read-only yes · destructive not declared · idempotent not declared · open-world yes

• get_recent_signals read-only

  Server-detected events from the last hour: funding outliers (≥3x 7d baseline), whale trades (≥$100k), OI caps reached. Cursor-based — pass next_cursor back as since_id to receive only new events. The polling equivalent of the /sse/signals stream. Pro tool get_signal_history covers 7 days with forward-return outcomes.

  Parameters:

  • coin — string — Filter to one coin, e.g. "BTC"
  • limit — integer — Max events (free tier cap: 20)
  • since_id — integer — Cursor from a previous call — returns only events with id > since_id. Omit on first call.

  Hints: read-only yes · destructive not declared · idempotent not declared · open-world yes

• get_oi_history read-only

  Open-interest time series for a coin over the last 24h, from our continuous 5-min collector. Hyperliquid has NO OI-history endpoint — this data exists only on predmcp. Includes price + funding at each point. Pro tool get_oi_divergence classifies price-vs-OI regimes (squeeze/liquidation/new positioning) across all coins.

  Parameters:

  • coin (required) — string — Coin, e.g. "BTC" (top ~30 by OI are tracked)
  • hours — integer — Lookback window in hours (free tier max: 24)

  Hints: read-only yes · destructive not declared · idempotent not declared · open-world yes

• get_market_regime read-only

  One-call market regime classifier: RISK_ON_TRENDING / RISK_OFF / SQUEEZE_RISK / CHOP_LOW_VOL / MIXED. Combines BTC trend + realized vol, Deribit IV premium, funding breadth, and OI-weighted crowding across the top 50 perps. Call this FIRST each session to condition strategy choice.

  Hints: read-only yes · destructive not declared · idempotent not declared · open-world yes

• get_market_context read-only

  Unified intelligence snapshot for any topic, asset, or keyword: all matching Polymarket and HIP-4 prediction markets combined with live Hyperliquid perp data (price, funding, OI). One call replaces 3+ separate lookups.

  Parameters:

  • query (required) — string — Topic, asset, or keyword to look up — e.g. "BTC", "Iran", "Fed rate cut", "Trump"

  Hints: read-only yes · destructive not declared · idempotent not declared · open-world yes

• get_pm_hl_divergences read-only

  Markets where Polymarket implied probability diverges from Hyperliquid perpetual funding direction — e.g. PM prices bullish outcome but HL funding shows crowded longs (bearish pressure). The hardest signal to compute manually.

  Parameters:

  • limit — integer — Number of divergences to return (default: 15)
  • min_pct — number — Minimum divergence percentage between PM implied probability and HL pricing to flag (default: 10%)

  Hints: read-only yes · destructive not declared · idempotent not declared · open-world yes

• get_hip4_vs_pm_arb read-only

  Finds the same underlying market priced on both HIP-4 (on-chain Hyperliquid) and Polymarket, flagging spreads above threshold. A spread means one venue is mispriced relative to the other.

  Parameters:

  • min_spread_pct — number — Minimum spread between HIP-4 and Polymarket YES prices to flag (percentage points, default: 3)

  Hints: read-only yes · destructive not declared · idempotent not declared · open-world yes

• get_funding_outliers read-only

  Hyperliquid perps whose current funding rate deviates significantly from their 7-day average. A spike vs baseline is a stronger signal than raw rate.

  Parameters:

  • days — integer — Historical window in days to compute the baseline average (default: 7)
  • min_deviation_factor — number — Minimum ratio of |current_rate| / |avg_rate| to qualify as outlier (default: 2x)

  Hints: read-only yes · destructive not declared · idempotent not declared · open-world yes

• get_liquidation_clusters read-only

  Estimated price levels where mass liquidations concentrate for a given Hyperliquid perp, computed from mark price and standard leverage multiples. Higher nearby orderbook liquidity = stronger support/resistance.

  Parameters:

  • coin (required) — string — Asset ticker to analyze, e.g. "BTC", "ETH", "SOL"

  Hints: read-only yes · destructive not declared · idempotent not declared · open-world yes

• get_signal_backtest read-only

  Find historical instances of a signal type on an asset over the last N days and compute forward returns (1h/4h/24h), win rate, and Sharpe. Lets an agent reason about EV before trading. Killer feature: turns predmcp from data API into edge-proven intelligence.

  Parameters:

  • signal_type (required) — string — Which signal to backtest. funding_outlier = funding >= z×baseline; funding_extreme = abs(funding) >= threshold.
  • asset (required) — string — Asset ticker, e.g. "BTC", "HYPE"
  • z_score — number — For funding_outlier: minimum deviation factor vs the rolling mean (default: 3×)
  • min_abs_rate — number — For funding_extreme: minimum absolute funding rate (default: 0.0005 = 0.05%)
  • lookback_days — integer — How many days of history to scan (default: 90, max: 180)
  • min_separation_hours — integer — Cluster consecutive triggers — at least N hours apart (default: 8h)

  Hints: read-only yes · destructive not declared · idempotent not declared · open-world yes

• get_conviction_score read-only

  Aggregates funding outlier, whale imbalance, OI/volume ratio, and momentum into a single directional score (-100 short ↔ +100 long) plus a 0-100 strength score. One call replaces 6+ lookups, returns a clean number for LLM decisions.

  Parameters:

  • asset (required) — string — Asset ticker to analyze, e.g. "BTC", "ETH", "HYPE"
  • whale_window_minutes — integer — Lookback window for whale trades (default: 60min)
  • min_whale_notional_usdc — number — Whale trade threshold in USDC (default: 25,000)

  Hints: read-only yes · destructive not declared · idempotent not declared · open-world yes

• get_funding_curve_anomaly read-only

  Term-structure analysis of Hyperliquid funding for an asset: current vs 8h avg vs 24h avg vs 7d baseline. Flags spikes, regime shifts, sign contradictions. More nuanced than raw funding rate.

  Parameters:

  • asset (required) — string — Asset ticker, e.g. "BTC", "HYPE"

  Hints: read-only yes · destructive not declared · idempotent not declared · open-world yes

• get_setup_quality read-only

  Execution-quality score (0-100, A-F grade) for entering a position right now: spread, slippage at desired size, orderbook depth, volatility regime, trend alignment, support/resistance proximity. Different from conviction (direction) — this scores ENTRY conditions.

  Parameters:

  • asset (required) — string — Asset ticker, e.g. "BTC", "HYPE"
  • direction (required) — string — Trade direction you are considering
  • size_usdc — number — Order size in USDC to evaluate slippage for (default: 200)

  Hints: read-only yes · destructive not declared · idempotent not declared · open-world yes

• get_upcoming_catalysts read-only

  Lists upcoming market catalysts for an asset within a horizon: token unlocks, governance votes (Tally), ETF/SEC deadlines, FOMC dates. Helps agents avoid blind trades into known events. Free data sources (Tally + curated DB).

  Parameters:

  • asset (required) — string — Asset ticker, e.g. "ARB", "SOL", "BTC"
  • horizon_hours — integer — Horizon in hours (default: 168 = 7 days, max: 720 = 30 days)

  Hints: read-only yes · destructive not declared · idempotent not declared · open-world yes

• get_macro_context read-only

  Live macro snapshot: DXY, US10Y yield, S&P 500, gold, VIX (Yahoo Finance free) + BTC dominance, ETH/BTC, total crypto market cap (CoinGecko free). Plus a coarse RISK_ON / RISK_OFF / MIXED regime.

  Hints: read-only yes · destructive not declared · idempotent not declared · open-world yes

• get_macro_liquidity read-only

  Fiat-to-crypto liquidity gauge: BTC + ETH spot ETF flows (Farside) plus on-chain USDT + USDC mint/burn (Etherscan). Net inflow = bullish for risk assets.

  Hints: read-only yes · destructive not declared · idempotent not declared · open-world yes

• get_cex_outflows read-only

  Net ETH outflows across known CEX hot wallets (Binance, Coinbase, OKX, Kraken, Bitfinex) over a window. Outflow = bullish (BTC moving to cold storage). Inflow = distribution pressure. Etherscan free tier.

  Parameters:

  • exchange — string — Filter to a single exchange or aggregate all (default: all)
  • window_hours — number — Lookback window in hours (default: 24h, max: 7d)

  Hints: read-only yes · destructive not declared · idempotent not declared · open-world yes

• get_news_correlation read-only

  Recent crypto news headlines mentioning an asset (CoinDesk, The Block, Decrypt, Cointelegraph) paired with the 1h price move that followed each. Lets agents filter news bias.

  Parameters:

  • asset (required) — string — Asset ticker, e.g. "BTC", "ETH", "HYPE"
  • hours_back — integer — Lookback window for headlines (default: 24h, max: 7d)

  Hints: read-only yes · destructive not declared · idempotent not declared · open-world yes

• get_portfolio_risk read-only

  Risk analytics for a list of positions: per-position beta to BTC and ETH, sector concentration, pairwise correlation matrix, portfolio annualized volatility, 1-day 95% parametric VaR. Uses 14d of 1h Hyperliquid candles.

  Parameters:

  • positions (required) — array — Array of positions: { asset, side, notional_usd }. Max 20.

  Hints: read-only yes · destructive not declared · idempotent not declared · open-world no

• get_options_iv read-only

  BTC or ETH options snapshot via free Deribit feed: ATM implied volatility, put-call skew, term structure, total OI and 24h volume. Useful as a sentiment gauge — IV high = market expects big moves; skew indicates direction of hedging.

  Parameters:

  • asset (required) — string — Underlying — Deribit only supports BTC and ETH for the free public feed.

  Hints: read-only yes · destructive not declared · idempotent not declared · open-world yes

• get_whale_label read-only

  Look up an Ethereum address against our curated label DB (CEX hot wallets, known market makers, suspected funds). Lets agents distinguish mechanical MM flow from alpha-generating activity.

  Parameters:

  • address (required) — string — Ethereum address to look up (0x-prefixed, 40 hex chars).

  Hints: read-only yes · destructive not declared · idempotent not declared · open-world no

• get_signal_history read-only

  Server-detected signal events over up to 7 days (funding outliers, whale trades ≥$100k, OI caps), each joined with its measured forward returns (1h/4h/24h) once mature. Cursor-based. "What happened last time funding spiked on HYPE — and did it matter?" in one call.

  Parameters:

  • coin — string — Filter to one coin, e.g. "BTC"
  • limit — integer — Max events (default 50)
  • since_id — integer — Cursor — only events with id > since_id
  • hours_back — integer — Lookback window in hours (default 24, max 168 = 7d)
  • signal_types — array — Filter to specific signal types

  Hints: read-only yes · destructive not declared · idempotent not declared · open-world yes

• get_signal_performance read-only

  Hit rates and average forward returns per signal type, measured on OUR actually-emitted production signals (not a backtest reconstruction). Use this to ground win_rate inputs for get_position_size. Sample sizes included — treat n < 10 as anecdotal.

  Parameters:

  • coin — string — Filter to one coin, e.g. "BTC"
  • days — integer — Lookback window (default 30, max 90)
  • signal_type — string — Filter to one signal type (default: all)

  Hints: read-only yes · destructive not declared · idempotent not declared · open-world yes

• get_oi_divergence read-only

  Price-vs-OI regime per coin from our continuous snapshots: NEW_LONGS / SHORT_SQUEEZE / NEW_SHORTS / LONG_LIQUIDATION. Scan all tracked coins or analyze one. Impossible without OI history, which no public API provides — only predmcp records it.

  Parameters:

  • coin — string — One coin (e.g. "BTC") — omit to scan all tracked coins
  • hours — integer — Lookback window in hours (default 24, max 90d)

  Hints: read-only yes · destructive not declared · idempotent not declared · open-world yes

• get_whale_flow read-only

  Cumulative whale buy/sell imbalance over hours-to-days from the durable trade tape (≥$25k trades persisted continuously, restart-proof). Returns imbalance ratio (-1..+1), BUY/SELL_DOMINANT verdict, and the largest recent prints. Longer horizons than get_whale_trades (1h buffer).

  Parameters:

  • coin (required) — string — Coin, e.g. "BTC" (top ~10 by OI are taped)
  • hours — integer — Lookback window in hours (default 24)
  • min_notional_usdc — number — Threshold for the sample trades list (tape floor: $25k)

  Hints: read-only yes · destructive not declared · idempotent not declared · open-world yes

• get_position_size read-only

  Turn a signal + bankroll into a concrete position: fractional-Kelly size capped by orderbook liquidity, ATR-based stop, liquidation price at chosen leverage, funding carry cost, and % bankroll at risk. Warns when liquidation sits inside the stop. Ground win_rate_pct with get_signal_performance or get_signal_backtest first.

  Parameters:

  • asset (required) — string — Asset, e.g. "BTC"
  • direction (required) — string — Trade direction
  • bankroll_usdc (required) — number — Total capital available in USDC
  • leverage — number — Intended leverage (default 3x)
  • payoff_ratio — number — Avg win / avg loss ratio (default 1.5)
  • win_rate_pct — number — Estimated win probability % (use get_signal_performance or get_signal_backtest to ground this)
  • kelly_fraction — number — Fraction of full Kelly to use (default 0.25 — quarter Kelly)
  • max_slippage_pct — number — Max acceptable slippage % — caps size by orderbook depth

  Hints: read-only yes · destructive not declared · idempotent not declared · open-world yes

• get_carry_scanner read-only

  Funding carry NET of costs: annualized funding minus (spread + 2x slippage at your size), with break-even holding period and a 7d funding-stability score from our snapshots. get_top_funding_rates shows gross — nobody trades gross.

  Parameters:

  • top_n — integer — How many candidates to fully cost out (default 8 — each costs an orderbook call)
  • size_usdc — number — Intended position size in USDC — costs are computed at this size

  Hints: read-only yes · destructive not declared · idempotent not declared · open-world yes

• get_cross_venue_funding read-only

  Predicted funding spreads between Hyperliquid, Binance, and Bybit per asset (from HL's predictedFundings feed). Surfaces delta-neutral carry: long the venue with lowest funding, short the highest, collect the spread. Sorted by annualized spread.

  Parameters:

  • limit — integer — Max rows (default 15)
  • min_spread_annual_pct — number — Minimum annualized funding spread between venues to report (default 5%)

  Hints: read-only yes · destructive not declared · idempotent not declared · open-world yes

Repository

Measured by MCPYP probing. Untested fields are omitted, never estimated. Listing is always free; MCPYP never proxies calls or stores user tokens.