mcp server

quant

Quant tools + an NFL fantasy draft assistant for AI agents — Kalshi & Polymarket EV, edge, ADP.

Description as published by the maintainer. Source

• version 1.8.0
• active

active — Most recent push to the repository was 2026-07-27.

What this server can do

23 functions, named and described by the server itself. Parameter names are shown because they say more about what a function does than its name usually does.

adp_market_gaps(limit, scoring, position)

Find the 2026 fantasy players whose Average Draft Position swings most between platforms — consensus vs ESPN, Sleeper, Yahoo, Underdog, etc. A wide gap (e.g. "consensus RB18 but ESPN drafts him RB30") is a platform-specific value: grab him where he goes latest. Free without a key (top 5). A free key unlocks the top 25; Pro unlocks the full per-platform breakdown. Use for "ADP differences by platform", "where is a player cheapest", "ADP arbitrage", "who falls on ESPN vs Sleeper". Filter by position (QB/RB/WR/TE/FLEX).

base_rate_gap(baseRateId, marketPrice, baseRateValue)

Compare a market price against the historical base rate for a class of events and get the gap in percentage points plus a signal and sample-size quality. Pass either a known base-rate id (one of: incumbent_reelected, fed_hold_unemp_below_4, fed_cut_cpi_above_3, recession_called_12mo, sp500_positive_year, bitcoin_above_100k_eoy, gdp_growth_above_2, cpi_above_3, senate_incumbent_wins_primary, vix_below_20_eoy, interest_rate_cut_next_meeting, major_sports_upset) or your own baseRateValue. Use for "how does this price compare to history", "is the market ignoring the base rate", "historical frequency vs market". Required: marketPrice.

bayes_update(prior, evidence)

Update a prior probability with one or more pieces of evidence using Bayes theorem. Given a prior and a list of evidence items (each with P(evidence | true) and P(evidence | false)), returns the posterior probability and the per-step chain. Use for "update my estimate with new information", "posterior probability", "how does this news change the odds". Required: prior, evidence.

best_available(teams, roster, drafted, scoring, platform, pick_number)

Given the current pick number and the players already drafted, return the best players still on the board (2026, any scoring format), each with projection, ADP, and a value flag, plus the biggest model value available. Free without a key (top 3). A free key unlocks the top 10; Pro unlocks the full list plus boom/bust week odds and the positional tier breaks across everyone still on the board. Prefer this mid-draft when the user asks "who is the best available", "who should I take next", "best player left". Input: pick_number, drafted (names already gone). Required: pick_number.

calculate_ev(marketPrice, yourProbability)

Calculate the expected-value edge on a Kalshi or Polymarket prediction-market contract. Given the current market price (in cents, i.e. the implied probability) and your own probability estimate, returns the % edge and a BUY / SELL / SKIP signal with a plain-English read. Use for "is this contract mispriced", "what is my edge", "should I take this position". Required: marketPrice, yourProbability.

combo_edge(legPrices, offeredOdds, trueWinProbability)

Grade a same-game combo (parlay-style multi-leg position) on a prediction market against its fair value. Given each leg price in cents and your correlation-aware estimate of the true joint win probability, returns the fair-value ODDS BAND to grade a quote against. Pass offeredOdds — the price your platform actually quotes for the combo (Kalshi combo RFQ or an SGP product) — to get the expected-value %, a negative-correlation-trap flag, and a 7-tier verdict (SMASH / PLAY / LEAN / RISK / NO_VALUE / PASS / RUN). Without offeredOdds it returns fair value + band only (no verdict) — never grade EV off the product of the leg prices, which no venue pays. Use for "is this combo worth it", "grade my parlay quote", "same-game combo value". Required: legPrices, trueWinProbability.

commodity_edge(tickers, commodity)

Get today's highest-conviction silver or bitcoin trade signal from the PMP edge model — the Kalshi weekly-silver (KXSILVERW) or twice-daily bitcoin (KXBTCD) strike with the largest model edge, as a trade ticket: entry side and price, resolve criterion, model probability, edge in percentage points, confidence tier, and quarter-Kelly sizing. Pro key required. Use for "silver edge today", "bitcoin trade signal", "is there a commodity edge". Pass tickers[] to check specific Kalshi markets — e.g. paste your Kalshi Pro screener watchlist (returns the signal only if it matches the strike PMP is modeling). Required: commodity.

compare_players(players, scoring, platform)

Compare 2–4 players side by side for a 2026 fantasy draft (standard, half-PPR or full-PPR) — projection, floor/ceiling, ADP, draft round, and value flag — and get a pick recommendation plus which one is the best market value. Free, no key. Use for "<A> or <B> in fantasy", "who should I draft, <A> or <B>", "compare <A> and <B>", "start/draft <A> vs <B>". Required: players.

convert_probability(value, format)

Convert between implied probability, American odds, and decimal odds. Give one value and its format and get all three back (American odds carry no commas, e.g. +441 or -200). Use for "what is +150 as a probability", "convert 62% to American odds", "decimal to implied odds". Required: value, format.

draft_board(limit, teams, scoring, platform, position)

The PredictionMarketsPicks 2026 fantasy football draft board (standard, half-PPR or full-PPR) — every player ranked, blending our projection model with consensus ADP, showing projected points, ADP, draft round, and a SLEEPER / BUST value flag. Filter by position (QB/RB/WR/TE/FLEX). Free without a key (top 12 of the board). A free key unlocks the top 50; Pro unlocks the full board plus boom/bust week odds per player and positional tier breaks. Use for "fantasy football rankings 2026", "who are the top RBs", "draft board", "best available by position".

edge_alerts(feed, limit, since, min_tier)

Read the edge alerts our models generate on Kalshi — weather, bitcoin/silver/gold/oil, and mispricings — as a live feed. Each alert carries feed, tier (SPECULATIVE/MODERATE/STRONG), side, price in cents, model probability, edge in percentage points, and a Kalshi market link. A Pro key returns the feed in real time; without a key you get the same feed delayed 24 hours with the thesis stripped. Every subscriber receives the identical, impersonal feed at the same time — the signals are not tailored to any individual. Filters (feed, min_tier, since) SELECT which alerts you see; they never change the signal content. Use for "any edge on Kalshi", "weather trade signals", "latest mispricings". Impersonal market analysis for informational purposes only, not investment advice. Trade responsibly.

explain_player(player, scoring, platform)

Explain WHY the 2026 draft board ranks a player where it does, factor by factor: projection, floor/ceiling band, boom/bust week shape, and the three separate ranks a board row carries — our model's own positional rank, the market's ADP, and the published blend between them — plus the edge between model and market. Also states what the projection does NOT model (injuries, camp news, schedule). Free, no key. Use for "why do you have <player> there", "explain <player> ranking", "what's driving <player>'s projection", "why is <player> a sleeper/bust". For a plain outlook or a verdict rather than the reasoning, use player_outlook. Required: player.

find_arbitrage(minGap)

Scan for cross-platform price gaps between Kalshi and Polymarket on the same sports contract (NBA, NHL, MLB, World Cup). Returns each game where the two venues disagree on the implied probability, the gap in percentage points, the WATCH/ARB signal, and which venue is cheaper. Free without a key: the single largest gap on the board, in full detail. A free key returns the top 3; Pro returns the whole board. Use for "where is the arbitrage", "cross-platform price gaps", "Kalshi vs Polymarket mispricing".

kelly_size(bankroll, fraction, marketPrice, winProbability)

Compute the optimal Kelly position size for a prediction-market contract. Given your win probability, the market price (which sets the payout), your bankroll, and a Kelly fraction (full / half / quarter / eighth), returns the dollar stake and a risk rating. Use for "how much should I stake", "what is my position size", "Kelly sizing for this trade". Required: winProbability, marketPrice.

market_pulse(topic)

The US macro-health composite (0–100) and regime plus the six category scores (growth, labor, inflation, rates, liquidity, sentiment). The composite and the regime call are free without a key, always, along with 2 category scores; a free key returns 4 and Pro returns all six. Use for "how is the US economy", "macro regime", "risk-on or risk-off". (NFL edges moved to the dedicated nfl_edge tool.)

nfl_edge(limit, market, minEdge, tickers)

Where the PredictionMarketsPicks NFL model disagrees with live Kalshi prices — the actionable edge across every NFL market: game moneylines this week, season win-total futures, MVP, and championship (playoff / conference / Super Bowl) odds. Returns model probability, Kalshi price, edge in percentage points, and the side, biggest edges first. Pro key required. Use for "which NFL games are mispriced on Kalshi", "NFL win total edges", "NFL MVP value", "Super Bowl odds edge", "NFL prediction market picks". Pass tickers[] to check specific Kalshi markets — e.g. paste your Kalshi Pro screener watchlist (applies to the futures / mvp / championship markets, which are ticker-addressable).

nfl_power_ratings(team, tier, limit)

The PredictionMarketsPicks NFL power ratings — the Gridiron Edge Rating (GER) for all 32 teams, a defense-adjusted power number expressed as expected points vs an average team, with each team's rank and tier. Free, no key. Use for "best NFL teams by power rating", "NFL power rankings 2026", "is Baltimore overrated", "how good is Kansas City", "NFL team ratings".

nfl_prop_edge(limit, minEdge, propType)

NFL player-prop edges — the PredictionMarketsPicks projection vs the Kalshi prop line for passing yards, rushing yards, receiving yards, receptions, and anytime touchdown. Returns the model projection, model probability, Kalshi price, edge, and side. Live in-season (opens NFL Week 1). Pro key required. Use for "NFL player prop edges", "best NFL props today", "passing yards over under", "receiving yards prop value".

nfl_win_probability(total, spread, awayTeam, homeTeam)

Turn an NFL point spread and game total into win probability, projected score, cover probability, and over/under probability — using the PredictionMarketsPicks scoring-margin model. Provide the spread (home-favored = negative, e.g. -6.5) and optional total, OR two team abbreviations to auto-derive the spread from the power ratings. Free, no key. Use for "NFL win probability from the spread", "what does a -7 spread mean", "who wins Chiefs vs 49ers", "NFL score prediction".

player_outlook(player, scoring, platform)

A single player's 2026 fantasy outlook (standard, half-PPR or full-PPR): projected points and per-game, floor/ceiling range, boom/bust odds, consensus ADP and draft round, our positional rank, and whether the model tags him a SLEEPER or a BUST vs the market, with a one-line thesis. Free, no key. Use for "is <player> a sleeper", "<player> fantasy outlook 2026", "should I draft <player>", "<player> projection". Required: player.

scan_mispricings(limit, minEdge)

Scan Polymarket contracts for mispricings against the PMP model (a probability swarm). Returns each market where the model disagrees with the price, the direction to take, the edge in percentage points, and quarter-Kelly sizing, sorted by absolute edge. Pro key required. Use for "where is the edge today", "mispriced markets", "what should I trade".

sleepers_and_busts(round, teams, scoring, platform, position)

The biggest gaps between the PredictionMarketsPicks model and consensus ADP for 2026 (standard, half-PPR or full-PPR): SLEEPERS the model ranks well above their draft cost, and BUSTS it ranks below. Filter by position or draft round. Free without a key (3 sleepers + 3 busts). A free key unlocks 10 of each; Pro unlocks the full board. Use for "fantasy sleepers 2026", "draft busts to avoid", "undervalued players", "overrated fantasy players", "late-round sleepers".

who_do_i_draft(teams, roster, scoring, platform, pick_number)

Recommend the single best player to draft right now given the roster already on the user's team and their pick number, weighing positional need against the best value available (2026, any scoring format). The pick itself is always free, no key. A free key adds 2 alternatives; Pro adds the full reasoning. Prefer this mid-draft when the user asks "who should I take", "who do I draft", "what do I need". Input: roster (names on their team), pick_number. Returns one pick + a one-line reason. Required: roster, pick_number.

Last successful function declaration observed on 2026-08-13. Source: https://predictionmarketspicks.com/api/mcp/mcp. We list what the server declared; we do not call any of these functions.

Endpoint status observed on 2026-08-13. Source: https://predictionmarketspicks.com/api/mcp/mcp.

Signals

These are separate measurements of different things. They are deliberately not combined into one score, because a popularity number that mixes website traffic with saves and stars cannot be checked or acted on.

Where to get it

• Repository — https://github.com/predictionmarketspicks/mcp
• Website — https://predictionmarketspicks.com/mcp
• Remote endpoint (streamable-http) — https://predictionmarketspicks.com/api/mcp/mcp

Related, by what their authors tagged them

• Flaim Fantasy — last commit 2026-08-06, shares fantasy-football
  Read-only fantasy analysis for ESPN, Yahoo, and Sleeper leagues via MCP
• ClearMarket — last commit 2026-08-06, shares kalshi, polymarket, prediction-markets
  Reference data for prediction markets: graded resolution clarity, cross-venue links, provenance.
• Simmer — last commit 2026-08-05, shares kalshi, polymarket, prediction-markets
  Trade prediction markets with AI agents — skill discovery, autoresearch, and execution.
• CoinRithm Agent Trading — last commit 2026-08-06, shares kalshi, polymarket, prediction-markets
  Keyless prediction-market data across 12 venues plus paper-trading of crypto spot, futures, and PM.
• stat-api — Sports Data — last commit 2026-07-07, shares nfl, prediction-markets
  NFL/NBA/MLB/NHL/PGA + DFS and prediction-market data. Browse free; query with a free API key.
• Kalshi Prediction Markets — last commit 2026-08-05, shares kalshi, prediction-markets
  MCP server for Kalshi prediction markets: native RSA-PSS auth, rate limiting, demo/prod safety.
• CPZAI — last commit 2026-07-31, shares quant
  Build, backtest, and deploy quantitative trading strategies from your AI agent.
• AlgoVault — Crypto Quant Trade Calls — last commit 2026-08-06, shares quant
  The Brain Layer for AI Trading Agents — quant calls + cross-venue arb across perp venues via MCP.
• VARRD — Statistically Validated Trading Edges + AI Research Engine — last commit 2026-05-04, shares quant
  Validated trading edges across futures, equities, crypto. Live signals, full audit trail.
• io.github.ebrunet001/mcp-server-espn — last commit 2026-07-05, shares nfl
  Real-time ESPN sports data: live scores, standings, boxscores, odds & stats for 25+ leagues

These share tags the maintainers applied themselves, such as fantasy-football, kalshi, polymarket, prediction-markets. Common tags like "mcp" or "ai" are ignored for this: agreeing with six hundred other projects is not a similarity.

This is not a recommendation and not a test result. It is a map of what the authors said their work is about.

How the author describes it

Topics the maintainer set on GitHub: ai-agents, claude, fantasy-football, kalshi, llm-tools, mcp, mcp-server, model-context-protocol, nfl, polymarket, prediction-markets, quant.