mcp server

Lumify Sports Intelligence

Schedules, scores, odds, splits & explainable AI bet confidence — 8+ sports, free instant key.

Description as published by the maintainer. Source

• version 1.0.1
• active

active — Most recent push to the repository was 2026-08-04.

What this server can do

18 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.

batch_get_events(bookmaker, event_ids, include_odds, include_intelligence)

Get multiple events by id in one call — for agents that already have a list of ids and want full detail for each without one call per event. Max 25 ids. Returns full detail for every id that exists plus a not_found list for any that don't (never billed). Use get_event for a single id, or list_events / query_events to discover ids first. Required: event_ids.

estimate_cost(calls)

Estimate the credit cost of one or more planned tool calls before making them — no credits are spent. Costs are data-dependent (e.g. odds/intelligence/splits not yet ingested for an event are free, and batch_get_events ids that don't exist cost nothing), so this returns a [min_credits, max_credits] range per call rather than a single number. Pass the exact tool name and arguments you're considering, e.g. {"tool": "get_event", "arguments": {"event_id": 123, "include_odds": true}}. Required: calls.

get_event(event_id, bookmaker, include_odds, include_intelligence)

Get a single event with participants and venue. Optionally inline current odds and/or bet intelligence (+1 credit each, only charged when that data is actually available). Raises a not-found error if event_id doesn't exist. Use list_events / query_events to discover ids first, or batch_get_events to fetch several ids in one call. Required: event_id.

get_intelligence(event_id, bookmaker)

Get AI bet intelligence for an event. Branch on sport/league and on the presence of probability (probability model) vs. confidence_score (points model). Probability customer surface (MLB, soccer/MLS, tennis): probability, interval, fair_price, market, edge, tier, plus Price fair/edges_by_book/best — framework plumbing (p_model, p_market, blend_w, sufficiency, phase, model_version, drivers, alignment) is omitted. edge/tier null and has_recommend false today — fair-price + line-shopping, not picks; price gap ≠ EV. Predictive MLB may also return a Search-backed match_overview + top-level rationale[] (context overlay, not a pick) generated on first request and reused after — distinct from bets[].rationale on points sports. Points model (NFL, NCAAF, unmigrated soccer): confidence scores, signals, bets[].rationale, narratives. Match-level tokens (OVER, UNDER, ML_DRAW) have null player_role/player_id/team_id/player_name. bookmaker defaults to pinnacle and is a no-op for probability-model sports. Returns available:false with no charge if intelligence hasn't been computed yet. Required: event_id.

get_live_score(event_id)

Get a lightweight live score snapshot for an event: status, period, clock, per-participant score and period-by-period scores, and last-updated time. Cheaper and faster than get_event when you only need the score, not participants or venue. Raises a not-found error if event_id doesn't exist. Required: event_id.

get_odds(event_id, bookmaker)

Get current betting odds for an event: per-bookmaker lines and last-updated time. bookmaker defaults to pinnacle (1 credit). Use 'all' or a comma-separated list for multiple books (2 credits). Returns available:false with no charge if odds aren't posted for this event yet. Use get_odds_history for line movement over time. Required: event_id.

get_odds_history(limit, event_id, bookmaker)

Get line-movement history for an event: a list of past odds snapshots (movements), each with its own timestamp, up to limit entries. bookmaker defaults to pinnacle. Use get_odds instead if you only need the current line. Required: event_id.

get_player(player_id)

Get a single player profile: name, sport, country, position/handedness, physical stats, current team, and tennis ranking if applicable. Raises a not-found error if player_id doesn't exist. Resolve ids via search_players. Required: player_id.

get_player_events(to, from, limit, status, after_id, player_id)

List a player's events (schedule/results), paginated by id (after_id). Defaults to ±30 days around today when no date filter is given. Resolve player_id via search_players first. Required: player_id.

get_splits(event_id)

Get public betting splits (bets% and handle%) for an event: a consensus split plus a per-bookmaker breakdown (bookmakers[].bookmaker uses the same odds slugs as get_odds, e.g. draftkings — not upstream short keys like dk), with a captured_at timestamp. Available for MLB, NBA, NHL, and NFL. Not available for tennis, soccer, or NCAAF (upstream does not expose splits). Returns available:false with no charge if splits haven't been captured for this event yet or the sport is unsupported. Required: event_id.

get_stats(event_id)

Get raw, deterministic team/player and match statistics for a soccer, MLB, tennis, NFL, NCAAF, NBA, NCAAB, or NHL event — no market/odds data (use get_odds for that) and no scoring, weighting, confidence, or narrative attached; use get_intelligence for Lumify's judgment layer. The payload shape is sport-specific — soccer/MLB/NFL/NCAAF/NBA/NCAAB/NHL use teams.home/away; tennis uses players.player_1/player_2 + match.scoreboard; never share field names across sports. Soccer: team strength (league-table PPG or FIFA rank), recent form, head-to-head history, rest days, home/away splits, and boxscore rates (shots/SoT for & against, possession, corners, cards, saves/save rate, plus Phase 1C offsides/tackles/interceptions/blocked_shots/assists — team assists is summed from ESPN's per-player goalAssists, since ESPN has no team-level assists stat) over explicit windows rates_l5/rates_season. Shot location is not on ESPN's team box — not exposed. MLB: season-to-date W/L record + run differential, recent form (runs scored/allowed), H2H, rest days, team batting/pitching rates (rates_l5/rates_season — AVG/OBP/SLG/OPS/ERA/WHIP/K9/BB9 plus RBI/TB/triples), starting pitcher's own season ERA/WHIP/K9/BB9 once the post-final box lineup lands (pregame probable SP stays on get_intelligence), and lineup from completed-game box scores. Tennis (main-draw singles only): Stage-1 FlashLive history (match context, rankings, set scoreboard, rest days, recent/surface form, tour lookback record, H2H) plus Stage-2 career_rates / career_surface from persisted Tennis API aggregates (serve/return, break points, match-surface W/L) — request path is DB-only. NFL Stage-1: season W/L + point differential, recent form (points scored/allowed), H2H, rest days, and team offense/defense rates (total/passing/rushing yards, attempts, turnovers, third_down_pct) from persisted ESPN team boxes — no per-player block on this endpoint (player game stats are persisted for a future player-props surface). NCAAF Stage-1: same football-native shape as NFL (season W/L + point differential, form, H2H, rest, offense/defense rates from ESPN college-football team boxes) — scoped to sport=ncaaf so rates never mix with NFL. NBA Stage-1: season W/L + point differential, recent form (points scored/allowed), H2H, rest days, and team box rates (rebounds/assists/steals/blocks/turnovers/fouls per game plus fg_pct/three_point_pct/free_throw_pct as ratio-of-sums over persisted made/attempt pairs) — no per-player block, same player-props deferral as NFL. NCAAB Stage-1: same basketball-native shape as NBA from ESPN mens-college-basketball team boxes — scoped to sport=ncaab. NHL Stage-1: season W/L + goal differential (OT/shootout losses count as losses), recent form (goals scored/allowed), H2H, rest days, and team box rates (shots_on_goal/hits/penalty_minutes/power_play_goals/giveaways/takeaways/blocked_shots per game) from the NHL Web API boxscore endpoint — no per-skater/goalie block, same player-props deferral as NFL/NBA. NFL/NCAAF/NBA/NCAAB preseason games are excluded from form/rates/record/H2H via lumify_events.season_type; NHL never ingests preseason games at all, so no filter is needed there. Form/record/rest/H2H count status final/complete only (walkovers excluded as unplayed; retirements count). Returns available:false with no charge if participants haven't resolved, or tennis draw_type is not exactly 'singles' (doubles and qualifying are out of scope, same as the tennis predictive stack). Required: event_id.

get_team(team_id)

Get a single team profile with its home venue. Raises a not-found error if team_id doesn't exist. Resolve ids via list_teams. Required: team_id.

list_events(to, date, from, sort, limit, sport, league, status, team_id, after_id, season_id, has_recommend, include_scores)

List events (schedules and live scores), paginated by id (after_id). Filter by sport, league, status, date range, season, or team_id (resolve teams via list_teams / get_team). Returns event id, name, sport/league, start time, status, and venue for each; pass include_scores to also inline participants + scores (intended for small result sets — use get_event for one event's full detail, or query_events for free-text/natural-language filters instead of structured params).

list_seasons(sport, current_only)

List seasons per sport/league. By default returns only currently active seasons; pass current_only=false to include historical seasons. Optionally filter by sport. Returns each season's id, year, phase, start/end dates, and whether it is_current. Use list_sports for just each sport's current season.

list_sports(active_only)

List supported sports with their leagues and current season. Returns each sport's id, slug, name, team-sport flag, and its leagues (each with its current_season). Use list_seasons with current_only=false for historical seasons.

list_teams(q, limit, sport, active, league, country, after_id, division, conference)

List teams, paginated by id (after_id). Filter by sport, league, conference, division, country, active status, or name (q, partial match). Returns each team's id, slug, name, city, conference/division, and venue. Use get_team for full detail on one id once resolved here.

query_events(limit, query)

Search events with a natural-language query instead of structured filters — e.g. 'live nfl games today' or 'college basketball this week'. Rule-based (not an LLM): recognizes sport (nfl/nba/mlb/nhl/tennis/soccer/ncaaf/ncaab + aliases like hockey, american football, college basketball), status (live/final/upcoming/…), dates (today/tomorrow, this week, next N days, YYYY-MM-DD ranges). Bare 'football' is ambiguous and left unrecognized. Response includes interpreted filters, equivalent REST call, and unrecognized_terms. Prefer list_events when you already know the structured filters you want. Required: query.

search_players(q, limit, sport, active, ranked, country, after_id)

Search players by name, sport, country, ranking, or active status, paginated by id (after_id). Returns each player's id, name, position, current team, and tennis ranking if applicable. Use get_player for full detail on one id, or get_player_events for a player's schedule/results.

Last successful function declaration observed on 2026-08-13. Source: https://lumify.ai/mcp. We list what the server declared; we do not call any of these functions.

Endpoint status observed on 2026-08-13. Source: https://lumify.ai/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.

Where to get it

• Repository — https://github.com/lumifyai/lumify
• Website — https://lumify.ai
• Remote endpoint (streamable-http) — https://lumify.ai/mcp

Related, by what their authors tagged them

• io.github.DanielTomaro13/sportsdata-mcp — last commit 2026-08-05, shares odds, sports
  Live sports data & cross-book betting odds — ~500 tools, 28 providers, free, zero-config.
• Buzzr Sports Engine — last commit 2026-08-05, shares odds
  Local sports math, DFS settlement, bet analytics, and game-entertainment tools.
• Flaim Fantasy — last commit 2026-08-06, shares sports
  Read-only fantasy analysis for ESPN, Yahoo, and Sleeper leagues via MCP
• app.turnale/turnale — last commit 2026-08-03, shares sports
  Run racket-sport tournaments from your AI assistant: fair draws, scores, live standings.
• io.github.Backspace-me/sportscore-mcp — last commit 2026-04-23, shares sports
  Live scores, standings, top scorers, brackets for football, basketball, cricket, tennis. Free API.
• io.github.cyanheads/sports-mcp-server — last commit 2026-07-30, shares sports
  Get live scores, schedules, standings, team and player data for NFL, NBA, MLB, NHL, and soccer.
• io.github.ebrunet001/mcp-server-espn — last commit 2026-07-05, shares sports
  Real-time ESPN sports data: live scores, standings, boxscores, odds & stats for 25+ leagues

These share tags the maintainers applied themselves, such as odds, sports. Common tags like "mcp" or "ai" are ignored for this: agreeing with six hundred other projects is not a similarity.

This is not a recommendation and not a test result. It is a map of what the authors said their work is about.

How the author describes it

Topics the maintainer set on GitHub: ai-agents, mcp, model-context-protocol, odds, sports.