Kalshi weather markets: daily-high board beside the NWS forecast, live edges, EV, Kelly, base rates.
Scored across 8 tools
Each tool has a clearly delimited job: base rates, Bayesian updating, EV, unit conversion, Kelly sizing, alerts feed, market board, and settlement tracking. The only soft overlaps are around the 'edge' concept (calculate_ev vs. edge_alerts vs. base_rate_gap) and weather_board vs. weather_settlement, but the descriptions sharply separate 'price data' from 'settlement/observation data' and 'your own probability' from 'model feed'.
All names are snake_case and readable, but the conventions are mixed: verb_noun (calculate_ev, convert_probability), noun_verb (base_rate_gap, bayes_update, kelly_size), and bare noun phrases (edge_alerts, weather_board, weather_settlement). It is not chaotic, but an agent cannot infer the action pattern from the name alone.
Eight tools is a tight, well-scoped set for a weather prediction-market edge desk: four analytical primitives, two data feeds, one signal feed, and one conversion utility. Nothing looks redundant or bolted on.
The surface covers the full analytical chain from base rate through posterior, EV, sizing, and settlement verification, with live board and alert data. Gaps are minor: no explicit tool to enumerate supported venues/cities/baseRateIds, and no position or bankroll tracking across trades, which agents would have to carry themselves.
Use for "how does this price compare to history" and "is the market ignoring the base rate". Compares a market price with the historical base rate for a class of events: the gap in pp, a signal, and sample-size quality. Pass a known baseRateId (the parameter lists them) or your own baseRateValue.
Inputs: baseRateId, marketPrice, baseRateValue.
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".
Inputs: prior, evidence.
Use for "is this contract mispriced" and "what is my edge". Give a Kalshi, Polymarket US or Novig price in cents and your own probability; returns the % expected-value edge and a BUY / SELL / SKIP read, with that venue's fee.
Inputs: venue, marketPrice, novigMarket, venuePrices, +1 more. Returns: signal, edge_pp, sources, edge_pct, +8 more
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".
Inputs: value, format. Returns: sources, tell_user, timestamp, needs_input, +5 more
Use for "any edge on Kalshi", "where is the edge today" and "weather trade signals". Our model alerts on Kalshi — weather, bitcoin/silver/gold/oil, mispricings — with feed, tier, side, price, model probability, edge and link. Real time with Pro; free is delayed 24h without the thesis. One identical, impersonal feed for every subscriber; filters only select. Informational, not investment advice.
Inputs: feed, limit, since, min_tier.
Compute the optimal Kelly position size for a Kalshi, Polymarket US or Novig 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".
Inputs: venue, bankroll, fraction, marketPrice, +2 more. Returns: rating, sources, tell_user, timestamp, +6 more
Use for "Kalshi NYC high temperature odds". Every open Kalshi daily-high strike in 13 cities: YES price, settlement station and source, the strict-comparison rule, close time, and the NWS forecast high beside it. Pass city ("nyc", "KXHIGHCHI"). Market data only.
Inputs: day, city. Returns: rule, as_of, cities, sources, +5 more
Use for "what will the Kalshi NYC high settle at", "has LAX already hit 75" and "which Polymarket temperature bucket is winning". Per station: the running max under each venue's settlement rule (Kalshi and Polymarket US on the NWS Climate Report; Polymarket.com on routine METARs), the observation that set it, the next report countdown, the strikes already decided and the official high once it lands. Pass station ("la", "KLAX"). Settlement data only, no picks.
Inputs: station. Returns: as_of, rules, sources, stations, +5 more
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
groundhog.markets: free weather forecasts in one call, plus Kalshi and Polymarket market rules.
Live Kalshi and Polymarket data: EV edges, cross-venue arbitrage, markets, and whale trades.
Independent quant layer: fee-adjusted edge, Kelly, combos, best price: Kalshi, Polymarket US, Novig
Kalshi macro: Fed rate odds, gold, silver, oil and bitcoin edges, 15-min markets, Kelly sizing.
Add one secure layer between your agents and this server.
