PredMCP

raviolelabs/predmcp

Connects Claude or any MCP client to live Polymarket and Hyperliquid data through 38 tools. Query prediction market odds, orderbook depth, funding rates, whale positions, and volume spikes without leaving your prompt. The hosted tier gives you 100 calls a day for free. Self-host if you want unlimited. Open source covers the data layer (16 tools wrapping Polymarket and Hyperliquid APIs). The hosted version adds proprietary cross-venue signals and divergence detection. Useful when you're sizing a trade and need to correlate perp funding with on-chain prediction market sentiment in one shot instead of tabbing between dashboards.

tools: 52
auth: Secret needed
transport: HTTP
last updated: May 22, 2026

View on GitHub

Install

From registry metadata

$ npx add-mcp https://predmcp.com/mcp --name predmcp --header 'x-api-key: ${X_API_KEY}'

Run in your terminal. add-mcp asks which agents to add it to, then asks for each value it needs. Add -g to install it for every project.

Review the command, arguments and environment values before installing. MCP servers run with your local permissions.

Other ways

Claude Code

$ claude mcp add --transport http predmcp https://predmcp.com/mcp --header 'x-api-key: YOUR_X_API_KEY'

Run in your terminal. Add --scope user to make it available in every project.

Tools

Verified live · 52 tools

Verified live against the running server on Nov 6, 2026.

create_api_keyGenerate 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.1 params

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* required

email*string

Your email address — used to identify your key and for account recovery

get_marketsLive prediction markets from Polymarket and/or HIP-4, sorted by volume. Returns title, YES/NO prices, 24h volume, and expiry.3 params

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

Parameters* required

activeboolean

Filter to active/open markets only (default: true)default: true

limitinteger

Number of markets to return (1–100, default: 20)default: 20

platformstring

Data source: "polymarket", "hip4", or "all" (default)one of polymarket · hip4 · alldefault: all

get_oddsCurrent YES/NO prices and implied probability for any Polymarket or HIP-4 market token.2 params

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

Parameters* required

identifier*string

For Polymarket: the token_id of the YES or NO outcome. For HIP-4: the base asset ticker (e.g. "BTC")

platform*string

Platform the market is on: "polymarket" or "hip4"one of polymarket · hip4

get_orderbookFull orderbook depth (bids + asks) for any Polymarket market token. Shows liquidity at each price level.1 params

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

Parameters* required

token_id*string

Polymarket token ID for the YES or NO side of a market

search_marketsFull-text search across all Polymarket and HIP-4 prediction markets. Returns ranked results with current odds.2 params

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

Parameters* required

limitinteger

Maximum number of results to return (1–50, default: 10)default: 10

query*string

Keywords to search in market names and descriptions, e.g. "bitcoin ETF", "US election", "Fed pivot"

get_whale_positionsPositions 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.3 params

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* required

condition_idstring

Optional — filter results to a specific market by condition_id.

min_size_usdcnumber

Minimum position size in USDC to include in results (default: 1,000).default: 1000

user*string

Polygon wallet address (0x…) of the user whose positions you want.

get_moversTop prediction markets ranked by 24h volume spike or biggest YES/NO price swing. Surfaces breaking news bets and momentum plays across Polymarket and HIP-4.1 params

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* required

limitinteger

Number of top movers to return (1–20, default: 10)default: 10

get_markets_near_resolutionPolymarket markets resolving within the next N hours with a leading probability above threshold. Useful for resolution arbitrage and last-minute positioning.2 params

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

Parameters* required

hoursnumber

Maximum hours until resolution (default: 24h, max: 168h = 7 days)default: 24

min_probnumber

Minimum leading outcome probability to include (default: 0.7 = 70%)default: 0.7

get_volume_spikesPolymarket markets with abnormal 24h volume vs their 7-day daily average. Volume spikes typically precede news events or informed positioning.2 params

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

Parameters* required

limitinteger

Number of results to return (default: 15)default: 15

min_rationumber

Minimum ratio of 24h volume vs 7-day daily average to qualify as a spike (default: 3x)default: 3

get_late_game_sportsSports prediction markets on Polymarket closing within a few hours with a high-certainty leading outcome. Targets near-certain resolution for late-game positioning.2 params

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* required

certainty_pctnumber

Minimum leading outcome probability as percentage, e.g. 85 = 85% (default: 85)default: 85

hours_maxnumber

Maximum hours until market closes (default: 6h)default: 6

get_funding_ratesCurrent funding rates for Hyperliquid perpetuals. Positive rate = longs pay shorts (bearish bias); negative = shorts pay longs (bullish bias).1 params

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

Parameters* required

coinsarray

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

get_whale_tradesRecent large trades on Hyperliquid perps above a notional threshold. Includes side (long/short), size, price, and timestamp.2 params

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

Parameters* required

coin*string

Asset ticker to fetch whale trades for, e.g. "BTC", "ETH"

min_notional_usdcnumber

Minimum trade size in USDC to qualify as a whale trade (default: 50,000)default: 50000

get_top_funding_ratesTop Hyperliquid perps ranked by absolute funding rate, with OI and annualized yield. Useful for finding the most overcrowded longs/shorts and carry opportunities.2 params

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* required

limitinteger

Number of top results to return (default: 10)default: 10

min_abs_ratenumber

Minimum absolute funding rate to include, e.g. 0.0001. Omit to include all.default: 0

get_oi_near_capLists 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.

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.

No parameters. Call it with no arguments.

get_orderbook_depthFull 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 g...3 params

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 g...

Parameters* required

coin*string

Asset ticker (BTC, ETH, SOL) or HIP-4 contract name (e.g. "BTC>81041@20260512-0600")

sidestring

Order side: "buy" (taker into asks) or "sell" (taker into bids)one of buy · selldefault: buy

size_usdcnumber

Order size in USDC to estimate slippage for (default: 200)default: 200

get_price_summaryOne-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.1 params

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* required

asset*string

Asset ticker, e.g. "BTC", "HYPE"

get_basic_macroDXY, 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.

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.

No parameters. Call it with no arguments.

get_recent_newsRecent 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.3 params

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* required

asset*string

Asset ticker to filter on, e.g. "BTC", "ETH", "HYPE"

hours_backinteger

Lookback window in hours (default: 24, max: 168 = 7 days)default: 24

limitinteger

Max headlines returned (default: 10)default: 10

get_news_feedRecent 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...3 params

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...

Parameters* required

categorystring

Restrict to one feed category (default: all).one of crypto · finance · sports · alldefault: all

hours_backinteger

Lookback window in hours (default 24, max 168).default: 24

limitinteger

Max headlines returned (default 40, max 100).default: 40

get_simple_ivBTC 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.1 params

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* required

asset*string

Underlying — Deribit free feed supports BTC and ETH.one of BTC · ETH

get_outcome_fair_valueOptions/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 verdic...6 params

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 verdic...

Parameters* required

asset*string

Underlying ticker, e.g. "BTC", "ETH", "SOL", "HYPE". BTC/ETH use the Deribit IV smile; others use Hyperliquid realized vol.

comparator*string

Market shape: above/below a strike, inside a range [strike, strike_high], or touches the strike before expiry.one of above · below · range · touch

expiry_iso*string

Market resolution time as an ISO 8601 string, e.g. "2026-08-21T06:00:00Z".

market_yes_pricenumber

Current on-chain YES price (0..1) to compute the edge against fair value.

strike*number

The market's strike / threshold price, e.g. 70000.

strike_highnumber

Upper bound for range markets (must be > strike). Ignored otherwise.

get_outcome_edgesOne-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 = (impli...3 params

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 = (impli...

Parameters* required

limitinteger

Max markets to return (default 30, max 100).default: 30

min_edge_ptnumber

Only return markets whose |edge| in probability points is at least this (default 0 = the whole board).default: 0

underlyingstring

Filter to one underlying ticker, e.g. "BTC".

get_market_edgeUniversal 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/spo...9 params

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/spo...

Parameters* required

comparatorstring

Price-market shape.one of above · below · range · touch

expiry_isostring

Resolution time (ISO 8601) for price markets.

is_tradedboolean

Explicit attestation that the YES price comes from a real traded book. Alternative to vol_24h.

question*string

The market question, e.g. "BTC above $70,000 at Aug 21 06:00 UTC?" or "Will Fed cut rates in September?"

strikenumber

Strike/threshold for price markets.

strike_highnumber

Upper bound for range price markets.

underlyingstring

Underlying ticker for price markets, e.g. "BTC".

vol_24hnumber

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.

yes_pricenumber

Current on-chain YES price (0..1). Edge is only computed for a real traded price (0.5 exactly is treated as synthetic/untraded).

get_market_edgesOne-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 b...3 params

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 b...

Parameters* required

limitinteger

Max markets to return (default 30, max 100).default: 30

methodstring

Filter to markets resolved via one anchor method. Passing "news" also enables the (slower) news lean.one of options · polymarket · odds · news

min_edge_ptnumber

Only return markets whose |edge| in probability points is at least this (default 0 = whole board).default: 0

get_news_signalsNews → 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 d...4 params

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 d...

Parameters* required

event_typestring

Filter to one event type.one of depeg · hack_exploit · delisting · listing · unlock · outage

hoursinteger

Lookback window for headlines (default 24h, max 72h).default: 24

limitinteger

Max signals to return (default 20, max 50).default: 20

min_confidencestring

Minimum confidence to include (default: low).one of low · medium

get_recent_signalsServer-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 co...3 params

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 co...

Parameters* required

coinstring

Filter to one coin, e.g. "BTC"

limitinteger

Max events (free tier cap: 20)default: 20

since_idinteger

Cursor from a previous call — returns only events with id > since_id. Omit on first call.

get_oi_historyOpen-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/li...2 params

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/li...

Parameters* required

coin*string

Coin, e.g. "BTC" (top ~30 by OI are tracked)

hoursinteger

Lookback window in hours (free tier max: 24)default: 24

get_market_regimeOne-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 ch...

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 ch...

No parameters. Call it with no arguments.

get_market_contextUnified 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.1 params

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* required

query*string

Topic, asset, or keyword to look up — e.g. "BTC", "Iran", "Fed rate cut", "Trump"

get_pm_hl_divergencesMarkets 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.2 params

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* required

limitinteger

Number of divergences to return (default: 15)default: 15

min_pctnumber

Minimum divergence percentage between PM implied probability and HL pricing to flag (default: 10%)default: 10

get_hip4_vs_pm_arbFinds 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.1 params

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* required

min_spread_pctnumber

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

get_funding_outliersHyperliquid perps whose current funding rate deviates significantly from their 7-day average. A spike vs baseline is a stronger signal than raw rate.2 params

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* required

daysinteger

Historical window in days to compute the baseline average (default: 7)default: 7

min_deviation_factornumber

Minimum ratio of |current_rate| / |avg_rate| to qualify as outlier (default: 2x)default: 2

get_liquidation_clustersEstimated 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.1 params

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* required

coin*string

Asset ticker to analyze, e.g. "BTC", "ETH", "SOL"

get_signal_backtestFind 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.6 params

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* required

asset*string

Asset ticker, e.g. "BTC", "HYPE"

lookback_daysinteger

How many days of history to scan (default: 90, max: 180)default: 90

min_abs_ratenumber

For funding_extreme: minimum absolute funding rate (default: 0.0005 = 0.05%)default: 0.0005

min_separation_hoursinteger

Cluster consecutive triggers — at least N hours apart (default: 8h)default: 8

signal_type*string

Which signal to backtest. funding_outlier = funding >= z×baseline; funding_extreme = abs(funding) >= threshold.one of funding_outlier · funding_extreme

z_scorenumber

For funding_outlier: minimum deviation factor vs the rolling mean (default: 3×)default: 3

get_conviction_scoreAggregates 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.3 params

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* required

asset*string

Asset ticker to analyze, e.g. "BTC", "ETH", "HYPE"

min_whale_notional_usdcnumber

Whale trade threshold in USDC (default: 25,000)default: 25000

whale_window_minutesinteger

Lookback window for whale trades (default: 60min)default: 60

get_funding_curve_anomalyTerm-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.1 params

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* required

asset*string

Asset ticker, e.g. "BTC", "HYPE"

get_setup_qualityExecution-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.3 params

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* required

asset*string

Asset ticker, e.g. "BTC", "HYPE"

direction*string

Trade direction you are consideringone of long · short

size_usdcnumber

Order size in USDC to evaluate slippage for (default: 200)default: 200

get_upcoming_catalystsLists 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).2 params

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* required

asset*string

Asset ticker, e.g. "ARB", "SOL", "BTC"

horizon_hoursinteger

Horizon in hours (default: 168 = 7 days, max: 720 = 30 days)default: 168

get_macro_contextLive 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.

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.

No parameters. Call it with no arguments.

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

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.

No parameters. Call it with no arguments.

get_cex_outflowsNet 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.2 params

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* required

exchangestring

Filter to a single exchange or aggregate all (default: all)one of Binance · Coinbase · OKX · Kraken · Bitfinex · alldefault: all

window_hoursnumber

Lookback window in hours (default: 24h, max: 7d)default: 24

get_news_correlationRecent 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.2 params

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* required

asset*string

Asset ticker, e.g. "BTC", "ETH", "HYPE"

hours_backinteger

Lookback window for headlines (default: 24h, max: 7d)default: 24

get_portfolio_riskRisk 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.1 params

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* required

positions*array

Array of positions: { asset, side, notional_usd }. Max 20.

get_options_ivBTC 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.1 params

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* required

asset*string

Underlying — Deribit only supports BTC and ETH for the free public feed.one of BTC · ETH

get_whale_labelLook 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.1 params

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* required

address*string

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

get_signal_historyServer-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.5 params

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* required

coinstring

Filter to one coin, e.g. "BTC"

hours_backinteger

Lookback window in hours (default 24, max 168 = 7d)default: 24

limitinteger

Max events (default 50)default: 50

signal_typesarray

Filter to specific signal types

since_idinteger

Cursor — only events with id > since_id

get_signal_performanceHit 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.3 params

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* required

coinstring

Filter to one coin, e.g. "BTC"

daysinteger

Lookback window (default 30, max 90)default: 30

signal_typestring

Filter to one signal type (default: all)one of funding_outlier_new · whale_trade · oi_cap_reached

get_oi_divergencePrice-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.2 params

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* required

coinstring

One coin (e.g. "BTC") — omit to scan all tracked coins

hoursinteger

Lookback window in hours (default 24, max 90d)default: 24

get_whale_flowCumulative 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).3 params

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* required

coin*string

Coin, e.g. "BTC" (top ~10 by OI are taped)

hoursinteger

Lookback window in hours (default 24)default: 24

min_notional_usdcnumber

Threshold for the sample trades list (tape floor: $25k)default: 100000

get_position_sizeTurn 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_s...8 params

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_s...

Parameters* required

asset*string

Asset, e.g. "BTC"

bankroll_usdc*number

Total capital available in USDC

direction*string

Trade directionone of long · short

kelly_fractionnumber

Fraction of full Kelly to use (default 0.25 — quarter Kelly)default: 0.25

leveragenumber

Intended leverage (default 3x)default: 3

max_slippage_pctnumber

Max acceptable slippage % — caps size by orderbook depthdefault: 0.3

payoff_rationumber

Avg win / avg loss ratio (default 1.5)default: 1.5

win_rate_pctnumber

Estimated win probability % (use get_signal_performance or get_signal_backtest to ground this)default: 55

get_carry_scannerFunding 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.2 params

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* required

size_usdcnumber

Intended position size in USDC — costs are computed at this sizedefault: 10000

top_ninteger

How many candidates to fully cost out (default 8 — each costs an orderbook call)default: 8

get_cross_venue_fundingPredicted 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.2 params

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* required

limitinteger

Max rows (default 15)default: 15

min_spread_annual_pctnumber

Minimum annualized funding spread between venues to report (default 5%)default: 5

Readme

PredMCP

Safe, read-only market data for AI trading agents.

44 MCP tools that cross Polymarket prediction markets, Hyperliquid perps, and HIP-4 native predictions. Plug your agent into live trading data — without ever giving it the ability to execute orders.

Live, hosted, free during early access: predmcp.com

Why read-only matters

The #1 worry when wiring an LLM to a trading venue is the same in every conversation: "and it can't actually trade, right?" PredMCP is built so that question has a single answer.

No execution endpoint. Zero order-placement code exists in this codebase. Not gated, not commented out — not implemented. There is nothing to enable.
No private keys touched. We use the public Hyperliquid Info API and Polymarket Gamma API. Your wallet, your seed phrase, your accounts — never seen, never asked for.
44 tools, all queries. Markets, orderbooks, funding rates, whale activity, signals. Every tool is a read. Your agent reasons about markets; you stay the only one who can act on them.

What's in the box

View the full README on GitHub

Details

Repository: github.com/raviolelabs/predmcp
Category: Media & Entertainment
Transport: HTTP
Auth: Required
Registry: MCP registry, active
Tools verified: Nov 6, 2026

Related Media & Entertainment MCP servers

View all

AI Image Editor MCProcnubie/aiimageeditor-mcpBest Image AI Editor free online. Free AI photo editor for picture & image editing.0stars

Deep Anime AI MCProcnubie/deepanime-mcpDeep Anime helps you turn a photo into anime, build character art, and refine scene ideas with0stars

FlowMusicAI MCProcnubie/flowmusicai-mcpFlow Music AI is a free AI music generator that turns one prompt into a finished royalty-free track0stars

SeedanceAI MCProcnubie/seedanceai-mcpCreate AI videos with SeedanceAI by text to video, text to image, image editing, and image to0stars

ShowMeStepBySteprt1966/showmestepbystepSearch, browse, and cite 409 step-by-step how-to tutorials (steps, tools, video credit).0stars

Scenetrascenetra/scenetra-mcpBuild and run AI image & video boards with 50+ models, routed to the lowest price.0stars