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

mcp server

flash-props-api

Player-prop lines, market metadata, and line movement over REST/MCP. 14 sports, CoD projections.

Description as published by the maintainer. Source

  • version 1.3.0
  • active

active — Registry entry last updated 2026-07-15.

What this server can do

13 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.

find_game(away, home, sport)
Translate a matchup (home team + away team) into the eventId needed by get_game_props. Read-only. No side effects. Requires an API key; rate-limited per your tier. Use this when you know the teams playing but don't have the eventId. On success returns: { eventId }. Pass that id straight to get_game_props. On failure returns an error explaining that the game was not found on today's board. If multiple games match the team names (rare), returns the first match sorted by start time. Matching is case-insensitive substring containment against the full team name (e.g. "Yankees" or "New York Yankees" resolve for MLB) — short codes like "NYY" or "NY" do NOT match unless they are literally a substring of the team name. If no game is found, the matchup may not be scheduled for today or the sport may be off-season. When to use: when you know both team names and want the eventId without browsing the full slate. When not to use: use list_games instead when you want to browse all games on the slate. Use get_game_props directly if you already have the eventId. Required: home, away.
find_player_props(name, sport)
Every active prop for one player across today's board for a sport — same rows as scan_props, filtered by name (exact normalized match preferred, case-insensitive contains match as a fallback; see matchType in the response) instead of stat. Use this when you know the player but not which game/event they're in. Required: name.
get_game_props(sport, stats, eventId)
Fetch all player props for one game identified by eventId. Read-only. No side effects. Requires an API key; rate-limited per your tier. Returns: { eventId, sport, homeTeam, awayTeam, startTime, props: Array<{ player, stat, line, overOdds, underOdds, bookCount, gameState?, flashProjection? }>, sources: string[], fetchedAt, delayed }. flashProjection (present for modeled markets, CoD + MLB today, when available) is { value, sampleN, method, marketKey }, the Flash season-baseline projection, never fabricated. overOdds and underOdds are American-format integers (e.g. -110, +115); null when odds are not available. The stats parameter filters to specific markets (e.g. "points,rebounds" for NBA, "strikeouts,hits_allowed" for MLB). Typical workflow: (1) call list_games to get eventIds, (2) call get_game_props with the eventId. Alternatively, call find_game with team names to resolve the eventId when you know the matchup. Event ids are prefixed ud- (Underdog Fantasy source) or bv- (Bovada source). Returns an error when the event id is not found, the game has ended with no active props, or lines have not been posted yet. When to use: when you have an eventId and want all props for that specific game. When not to use: use scan_props instead when you want a cross-game market view (e.g. all strikeout props today). Use find_player_props when you know the player name but not which game they are in. Required: eventId.
get_leaders(stat, limit, sport, metric)
Ranked boards for a sport with a Flash pack. Read-only. No side effects. Pro tier and above (free/starter get a deny message). metric=gap ranks the widest Flash-vs-book edges on the live board (player, market, bookLine, flashLine, gap, gapPct); metric=form ranks players by recent mean vs their Flash Line (delta); metric=sample ranks by baseline size. Returns { sport, metric, stat, count, leaders[], note }. Works for any sport with a pack (CoD and MLB today). No picks -- a ranking of real numbers. When to use: "biggest CoD/MLB edges tonight", "who is trending over their projection". When not to use: for one prop use get_prop_evidence; for raw rows use scan_props.
get_market_metadata(sport)
Return the machine-readable stat vocabulary for a sport: for each live market, its label, family, scope (map1/maps13/full_game), unit, display order, and whether a Flash projection is supported (with a reason when not). Read-only. No side effects. Rate-limited per your tier. Returns { sport, count, markets: Array<{ statKey, label, family, scopeKind, scope, scopeLabel, unit, displayOrder, uiGroup, projection: { supported, reason }, contextSupported, lineOnly, alternateLine }> }. This is what turns a raw stat key like "kills_on_game_1" into "Map 1 Kills" (kills family, map scope, projectable) so you can label and group props without guessing. When to use: after scan_props / get_game_props, to explain or group the raw stat keys you got back. When not to use: if you only need one sport's existence/access, list_sports already carries marketFamilies.
get_player_context(name, sport)
Season context for a player from the sport's Flash pack: per-market baselines, recent form, and sport-native splits (CoD also carries per-mode stats + a map log). Sports with a registered pack (CoD and MLB today) return data; other sports and unmatched players return an honest empty context, never fabricated. Pro tier and above; free/starter keys get a structured tier_required deny. Required: name.
get_prop_evidence(stat, event, sport, player)
Assemble the whole story of a single prop in one call. Read-only. No side effects. Rate-limited per your tier. Pro tier and above; free/starter keys get a structured tier_required deny. No picks, no advice -- a data feed. Returns { found, sport, player, market, event, book:{line,source,odds}, flash:{line,rawBaseline,method,sampleN,sampleStrength,mode}, gap, gapPct, form:{n,recentMean,median,stdev,min,max,hitRateVsBookLine,hitRateVsFlashLine,recent}, splits, modeSplit, opponentSplit, recentMaps, movement:{openedLine,currentLine,delta,series?}, freshness:{contextGeneratedAt,ageHours,stale,observedThrough,observedAgeHours,observedStale,note}, missingReasons, disclaimer }. freshness splits two clocks: ageHours/stale is the pack BUILD age; observedThrough/observedAgeHours/observedStale is the real age of the form data (can be far staler if ingest froze), with `note` a human "Form data through <date>" line. hitRateVsBookLine is how often recent maps went over the POSTED line (what a bettor asks); hitRateVsFlashLine is vs the Flash projection. The movement point series is Pro-only (free gets opened/current/delta). Available for sports with a registered Flash pack (CoD and MLB today); other sports return found:false with a reason, never fake data. Every absent section carries an explicit missingReason instead of being silently dropped. When to use: to explain or justify one prop end-to-end (why the Flash line sits where it does, how the player has trended, whether the line moved). When not to use: for a broad market view use scan_props; for a player overview use get_player_context. Required: player, stat.
get_prop_history(stat, event, limit, sport, player)
Chronological line/odds history for a player prop, with opened/current/movement. Pro tier and above — free/starter keys get a deny message pointing at the upgrade. History accrues from when archiving started, so early results may be short. Required: player.
get_strategy_doc
Returns the Flash Odds Automation OS strategy document (2026-07-17). 14 sections covering: current architecture map, automation scorecard (26/70), event model, state machine, social operating strategy, live automation maturity ladder, competitive differentiation thesis, proprietary analytics catalog, product experience, prioritized roadmap, and a concrete build-now engineering spec for the CDL result-provider adapter. Use this to understand how Flash Odds is built, what is and is not automated, what to build next, and the core design invariants (frozen claims, no fabrication, approval-gated X posts, Chamber loopback-only). Read-only. No side effects. No API key required.
list_games(sport)
Return today's games that have player props available for a sport. Read-only. No side effects. Requires an API key; rate-limited per your tier. Returns: { sport, count, games: Array<{ id, sport, homeTeam, awayTeam, startTime, live, source }> }. id is the eventId to pass to get_game_props (prefixed ud- for Underdog or bv- for Bovada); live is true when the game is in progress; source is "underdog" or "bovada". Live games sort first; scheduled games follow. Typical workflow: call list_games to discover eventIds, then pass an eventId to get_game_props. If sport is omitted the server selects the active in-season league automatically. Returns count=0 with an empty games array (not an error) when no props are posted yet for the day. When to use: to browse all games on the slate or to find an eventId before calling get_game_props. When not to use: if you already have the eventId, skip this and call get_game_props directly. Use find_game instead when you know the team names but want a single-game eventId without browsing the full slate.
list_sports
List every sport supported by Flash Props API with its live status and how deep the Flash model goes. Read-only. No side effects. Rate-limited per your tier. Returns { sports: Array<{ id, name, category, enabled, status, activeGames, activeProps, projectedProps, projectionCapability, effectiveProjection, contextCapability, marketFamilies, supportedMarkets, sources, lastFetchedAt, cacheAgeSeconds, shapeCanaryTripped, legalLine, notes }> }. id is what you pass as the sport parameter to other tools. status: "live" = props posted now, "idle" = in-season but none posted, "offseason" = out of season. projectionCapability tells you WHERE the depth is: "advanced_context" (CoD: projections + form + splits + map logs) and "flash_projection" (MLB: real season baselines + form + splits) vs "posted_lines_only" (everything else today). contextCapability "deep" means get_player_context returns data; "none" means it will be empty. enabled=false means the sport is outside your tier. When to use: to discover valid sport ids, or to check which sport actually has projections/context before asking for them. When not to use: if you already know the sport id and just want its props.
scan_movers(stat, limit, since, sport)
Props whose line moved most within a lookback window (default 24h, max 7d), sorted by absolute movement. Pro tier and above — free/starter keys get a deny message pointing at the upgrade.
scan_props(stat, limit, sport)
Flatten every active player prop across all of today's games for a sport into a single list. Read-only. No side effects. Requires an API key; rate-limited and row-capped per your tier (free: 25 rows, starter: 100, pro+: 500). Returns: { sport, stat, count, rows: Array<{ player, stat, line, overOdds, underOdds, bookCount, gameState?, flashProjection?, eventId, sport, homeTeam, awayTeam, startTime, source, fetchedAt }> }. Each row is a player prop merged with its event context — there is no team or opponent field; use homeTeam/awayTeam instead. overOdds/underOdds are American-format integers; null when odds unavailable. Use scan_props when you need a broad cross-game market view — e.g. every player with a strikeouts prop today, all passing-yards lines for the slate, or which players have the most active markets. Returns count=0 with an empty rows array (not an error) when no props are posted for the day yet. When to use: broad market discovery across all games for a sport. When not to use: use get_game_props instead when you already have an eventId and want one game only — it is faster and not row-capped. Use find_player_props instead when you want all markets for one player by name.

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

Endpoint status observed on . Source: https://api.flashodds.live/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 1.3.0 Latest version string the maintainer published to the registry. as of fetch Model Context Protocol
Registry record last updated 2026-07-15 When the registry record was last updated by its maintainer. point in time Model Context Protocol
First listed in the MCP Registry 2026-07-15 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 13 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 api.flashodds.live
mcp endpoint status ok The server listed 13 functions when asked. as of probe api.flashodds.live

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