KalshiSpy

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

What Kalshi's top-earning traders won and hold: settled wins free, live markets with an API key.

Add to your agent

Copy this into your MCP client config:

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

Measured tools (5)

• search_markets read-only

  Find Kalshi markets by title or keywords, the way the KalshiSpy app's search works: fuzzy title matching finds the market series (so a team, a nickname or an approximate title works), and keyword matching runs against market titles. WITHOUT an API key it returns SETTLED WINS ONLY: settled markets where KalshiSpy's roster of ID-verified, high-profit Kalshi traders held the winning side (wins only, never a hit rate). WITH an Elite or Lifetime API key the same call also returns OPEN markets in `open_markets`: roster positions from the live feed and named traders' recent trades on still-open markets, and it costs 1 unit of the daily quota. Always read `data.access`: it says which answer you got and, when a key was refused, why; relay that sentence rather than guessing. Call this first whenever the user names a market in words, send the words under the argument name this tool's own schema gives, and cite each market's kalshi_url. An empty list is never evidence that Kalshi has no such market. For more wins, follow `settled_wins.more`, which carries ready-made search_settled_wins arguments.

  Parameters:

  • query (required) — string — Market title or keywords, e.g. "super bowl", "fed rate" or "bitcoin". Terms of 2+ characters, at most 8. Keyword matching ANDs them as substrings of the title, outcome and tickers (settled wins also match the event title); the full text is also fuzzy-matched to market series.
  • limit — integer — Maximum items in each list (settled wins, roster markets, recently traded markets).

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

• search_settled_wins read-only

  Search KalshiSpy's archive of settled Kalshi markets where its roster of ID-verified, high-profit Kalshi traders held the WINNING side with positive net realized profit. Parameter and field names call these traders "whales" (whale_count, min_whales, sort=whales); in prose, call them the roster or the verified traders. Wins only: losses are not archived, so present results as "what this roster got right on markets like this", never as a hit rate. Use this BEFORE answering about any current or upcoming Kalshi market: search the same series_ticker (e.g. KXFED, KXNBA) or category and cite the comparable past wins — titles, settlement dates, trader counts and realized profit. Each result carries the Kalshi URL and a kalshispy.com detail URL you can cite. Default window is the last 90 days; widen with `from`/`to` (max 366 days). No API key needed.

  Parameters:

  • to — string — End of the settlement window (inclusive). Default: now.
  • from — string — Start of the settlement window. Default: 90 days before `to`. Clamped to the archive start (2025-01-01) and to a 366-day maximum; the effective window is echoed in `window`.
  • sort — string — recent = newest settlement first; profit = largest net profit first; whales = most whales on the winning side first.
  • limit — integer — Page size.
  • query — string — Free-text search. Every term (2+ chars, max 8) must appear as a substring in the title, outcome, event title, series ticker or ticker. Example: "fed rate" or "lakers".
  • cursor — string — Opaque cursor from a previous response (`page.next_cursor`). Send it with the SAME filters; changing the query invalidates it.
  • category — string — Category key from listCategories (e.g. sports, politics, economics).
  • min_whales — integer — Only wins with at least this many roster traders on the winning side.
  • event_ticker — string — Kalshi event ticker, e.g. KXFED-26SEP.
  • series_ticker — string — Kalshi series ticker, e.g. KXFED, KXNBA. The best way to find "markets like this one".

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

• get_settled_win read-only

  Full record of one settled Kalshi market this roster won: outcome, consensus, every roster trader on the winning side with their realized profit and picture, close and expiration times, keywords, and `hints.similar` — comparable wins in the same series to judge it against. Returns 404 when the ticker is not an archived win (the roster was not on it, or was on the losing side); the 404 carries a hint to search the series instead. No API key needed.

  Parameters:

  • ticker (required) — string — Kalshi market ticker.

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

• list_categories read-only

  Every category that has at least one archived win, with win count, net profit and the last settlement time. Use the `key` value as the `category` filter of searchSettledWins. No API key needed.

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

• get_stats read-only

  Aggregate figures for the settled-wins archive: markets won, net and winners' realized profit, first and last settlement, a per-category breakdown and the highest-profit traders in the archive. Use it for "how has this roster done overall" context, always with the wins-only caveat. `available:false` means the archive has not been published yet. No API key needed.

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

Publisher website

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