Weather Markets Edge Desk

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

Kalshi weather markets: daily-high board beside the NWS forecast, live edges, EV, Kelly, base rates.

Add to your agent

Copy this into your MCP client config:

{
  "mcpServers": {
    "Weather Markets Edge Desk": {
      "url": "https://predictionmarketspicks.com/api/mcp-weather/mcp?via=registry",
      "transport": "streamable-http"
    }
  }
}

Measured tools (7)

• weather_board read-only

  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.

  Parameters:

  • day — today · tomorrow · all (default).
  • city — string — City name or series ("nyc", "KXHIGHTBOS"). Omit for all.

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

• edge_alerts read-only

  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.

  Parameters:

  • feed — string — Comma-separated feeds to include: weather, bitcoin, silver, gold, oil, mispricing, sports_arb, nfl. Omit for all.
  • limit — ['number', 'string', 'null'] — Max alerts to return (default 25).
  • since — string — ISO-8601 timestamp — only alerts created after it.
  • min_tier — Minimum confidence tier (returns that tier and above). One of: SPECULATIVE · MODERATE · STRONG.

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

• convert_probability read-only

  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".

  Parameters:

  • value — ['number', 'string'] — The numeric value to convert. Needed for a real answer, with format.
  • format — Format of `value`: probability (0–100 %), american (e.g. -200 / +150), or decimal (e.g. 2.5). One of: probability · american · decimal.

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

• base_rate_gap read-only

  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.

  Parameters:

  • baseRateId — Known base-rate id to look up (includes sample size + source).
  • marketPrice — ['number', 'string'] — Current market price in cents / implied probability % (0–100). Needed for a real answer. Accepts 55, "55%", "55¢", "$0.55", 0.55 or American odds (+120 / -150) — all read as 55%.
  • baseRateValue — number — Your own base rate in % (0–100), used when no baseRateId is given.

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

• bayes_update read-only

  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".

  Parameters:

  • prior — ['number', 'string'] — Prior probability the hypothesis is true, in % (0–100). Needed for a real answer. Accepts 55, "55%", "55¢", "$0.55", 0.55 or American odds (+120 / -150) — all read as 55%.
  • evidence — array — One or more evidence items, applied in order. Each item needs likelihoodIfTrue and likelihoodIfFalse on the 0–100 scale, e.g. [{ "likelihoodIfTrue": 80, "likelihoodIfFalse": 20 }].

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

• calculate_ev read-only

  Use for "is this contract mispriced" and "what is my edge". Give a Kalshi or Polymarket price in cents and your own probability; returns the % expected-value edge and a BUY / SELL / SKIP read.

  Parameters:

  • marketPrice — ['number', 'string'] — Current contract price in cents (1–99), equal to the implied probability in %. Required for a real answer. Accepts 55, "55%", "55¢", "$0.55", 0.55 or American odds (+120 / -150) — all read as 55%.
  • yourProbability — ['number', 'string'] — Your own estimate of the true probability the contract resolves YES, in % (0–100). Required for a real answer. Accepts 55, "55%", "55¢", "$0.55", 0.55 or American odds (+120 / -150) — all read as 55%.

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

• kelly_size read-only

  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".

  Parameters:

  • winProbability (required) — ['number', 'string'] — Your probability the contract resolves YES, in % (0–100). Accepts 55, "55%", "55¢", "$0.55", 0.55 or American odds (+120 / -150) — all read as 55%.
  • marketPrice (required) — ['number', 'string'] — Contract price in cents (1–99). Sets the payout ratio. Accepts 55, "55%", "55¢", "$0.55", 0.55 or American odds (+120 / -150) — all read as 55%.
  • bankroll — ['number', 'string'] — Total bankroll in dollars (e.g. 1000). Optional — omit it and the result is the % of bankroll to stake, without a dollar figure.
  • fraction — Kelly fraction to apply. Half-Kelly is the common sharp-money default. One of: full · half · quarter · eighth.

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

Publisher website Repository

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