ZBS Index What actually exists in applied AI, with the source next to it

mcp server

skipodds

Fair sports win probabilities - bookmaker consensus, de-vigged to sum to 100%. 13 sports, 69+ books.

Description as published by the maintainer. Source

  • version 1.0.0
  • active

active — Registry entry last updated 2026-07-17.

What this server can do

5 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.

get_fixture(id, sport)
One fixture in full: fair probability and fair odds for every outcome, how many bookmakers were surveyed, and when the consensus last updated. Use when you already have a fixture id; call list_fixtures first if you do not. Use get_fixture_movement instead when you need how the price CHANGED rather than where it stands now. Read-only. An id that is unknown or has rolled off the board returns a fixture_not_found error rather than an empty fixture, and a low bookmaker count means a thin market rather than a failure. Required: id.
get_fixture_movement(id, hours, sport)
Time series of how one fixture's fair probabilities moved — timestamped consensus snapshots, oldest first. Use to spot line movement, steam or drift, and to answer "has this shortened since yesterday". Use get_fixture instead for the current price alone. Read-only. An unknown id returns a fixture_not_found error; a series with only one or two snapshots means the fixture was surveyed recently, not that the request failed. Required: id.
list_fixtures(limit, sport, competition)
Upcoming and recent fixtures with fair win probabilities: every surveyed bookmaker price averaged and stripped of its margin (de-vigged), so probabilities sum to exactly 100%. 13 sports, 69+ bookmakers. START HERE — the fixture ids returned are what get_fixture and get_fixture_movement require. Use get_fixture instead when you already hold an id, and list_tournament_outrights for who-wins-the-competition rather than individual matches. "recent" means a kickoff within the last 6 hours for soccer and tennis, 8 hours for basketball, baseball, hockey, American football, MMA and boxing, and 12 hours for cricket and rugby; anything older has rolled off the board. Outright/tournament-winner markets exist for soccer and golf only — every other sport is fixture-level. Read-only. Returns an empty list, not an error, when nothing is scheduled in range.
list_golf_tournaments(tournament_key)
Golf outright-winner probabilities, normalised across the priced field. Call with NO arguments to list the tournaments currently priced together with their tournament_key values; call again passing tournament_key to get that one tournament with its full player field. GOLF ONLY — use list_tournament_outrights for soccer competitions. Read-only. Between tournaments the no-argument call returns an empty list, which means nothing is currently priced rather than an error; an unrecognised tournament_key returns a tournament_not_found error.
list_tournament_outrights(competition)
Outright winner probabilities for a soccer competition, normalised across the teams that can still win — eliminated teams are dropped, so the field sums to 100% of the live market. Use for "who wins the league/cup"; use list_fixtures for individual matches. SOCCER ONLY — call list_golf_tournaments for golf. The other eleven sports have no outright market in this API at all, so for them list_fixtures is the only option; say so rather than retrying with a sport argument. Read-only. An unrecognised competition slug returns an empty field rather than an error.

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

Endpoint status observed on . Source: https://skipodds.com/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.

Signal Value What it measures Window Observed Source
Latest published version 1.0.0 Latest version string the maintainer published to the registry. as of fetch Model Context Protocol
Registry record last updated 2026-07-17 When the registry record was last updated by its maintainer. point in time Model Context Protocol
First listed in the MCP Registry 2026-07-17 Date this server was first published to the official MCP Registry. Not a usage or quality measure. point in time Model Context Protocol
mcp tools declared 5 tools Number of functions the server itself declared when asked to list them. This is what the server offers an agent, not a measure of how well any of them work. as of probe skipodds.com
mcp endpoint status ok The server listed 5 functions when asked. as of probe skipodds.com

Where to get it

This record as data

Every field on this page, with its source and observation date, is in the catalog JSON. Fetch the whole kind at once instead of parsing this HTML.

GET /api/v1/entries/mcp_server.json

Sources

  1. Official MCP Registry — Model Context Protocol, observed , trust tier 1.
  2. Tools declared by the MCP server at https://skipodds.com/mcp — skipodds.com, observed , trust tier 4.