Sportiq Mcp
About
MCP server with 44 tools across FIFA World Cup 2026 football, Formula 1, and IPL cricket - Monte-Carlo bracket sims, F1 pit-strategy, and a Dream11 IPL solver.
Details
- Author
- Ninjabeam20
- Downloads
- 502
- Categories
- Other
Jump to
- Monte Carlo tournament simulation with Poisson expected‑goals engine
- F1 pit‑strategy prediction using live tire‑degradation model
- ILP‑optimized Dream11 team builder under all constraints
- Live bookmaker odds and value‑bet detection
- Match predictors, xG models, and head‑to‑head tools
- Full coverage of live scores, fixtures, standings, and weather
Setting up with Highlight
This MCP is not yet compatible with Highlight’s one-click setup. However, you can still use it with Highlight by following these steps:
- Download and install Highlight from highlightai.com/download
- Navigate to the plugins tab and select "Add Custom Plugin"
-
Configure the plugin with the settings below
Plugin Name
Sportiq McpCommand (node, npx, python, etc.)Please refer to the README for specific instructions on how to obtain API keys or other required environment variables.
- Enable "Start Automatically" if you want the plugin to start when Highlight launches
From the repository
Install with a single command: uvx sportiq-mcp. Zero configuration required; simulation, prediction, and fantasy tools work offline with no API keys. Optional keys unlock live scores and odds. Then ask your AI questions like "Who's winning the 2026 World Cup, and where's the value in tonight's odds?"
sportiq_health
Report cache backend, per-adapter healthcheck, and quota status. Returns: HealthReport-shaped dict with `cache_backend`, `cache_ok`, `adapters` (per-source ok/detail), and `quotas`.
football_get_groups
Return the FIFA World Cup 2026 group draw and advancement format. Returns: data.groups: {group_letter: [4 team codes]} for all 12 groups. data.format: 48-team / 12-group / top-2 + 8-best-thirds rule. data.teams: team-code -> {name, fifa_code} metadata. meta.source: adapter that served the data.
football_get_fixtures
Return World Cup 2026 fixtures (live providers, else the group schedule). Args: limit: Max fixtures to return, 1..200 (default 50). offset: Number of fixtures to skip for paging (default 0). Returns: data.fixtures: page of {home, away, date/group, status, home_goals, away_goals}. data.pagination: {total, count, offset, limit, has_more, next_offset}. meta.source: adapter that served the data (static_seed = group schedule only).
football_get_standings
Return current World Cup 2026 group standings. Args: limit: Max standing rows to return, 1..200 (default 50). offset: Number of rows to skip for paging (default 0). Returns: data.standings: page of {rank, team, group, points, played, goals_diff}. data.pagination: {total, count, offset, limit, has_more, next_offset}. meta.source: adapter that served the data.
football_get_squad
Return a national team's World Cup squad. Args: team: Team code or name (e.g. "ARG"). Without an API-Football key, the static seed serves an empty-but-valid squad (rosters are a follow-up). Returns: data.squad: list of {name, number, position, age}. meta.source: adapter that served the data.
football_get_match_stats
Return a team's aggregate World Cup tournament statistics. Network-only enrichment: requires a configured API-Football (or football-data.org) key. There is no offline static fallback, so without a key the call returns a clean ALL_SOURCES_FAILED envelope. Args: team: API-Football numeric team id (not a country code). Returns: data.team_stats: {team, played, wins, goals_for, goals_against}. meta.source: adapter that served the data.
football_get_top_scorers
Return the World Cup 2026 top scorers. Returns: data.scorers: list of {name, team, goals, assists}. meta.source: adapter that served the data.
football_get_odds
Return live market head-to-head odds for upcoming World Cup 2026 matches. Sourced from The Odds API (requires THEODDS_KEY). Without a key the call returns a clean ALL_SOURCES_FAILED envelope rather than crashing. Args: team: Optional team name to filter events (case-insensitive substring, matched against both sides). Omit to return every WC event. Returns: data.events: list of {event_id, home, away, commence_time, bookmakers: [{name, home, draw, away}]} with decimal 1X2 prices per bookmaker. meta.source: adapter that served the data (theodds / cache:stale).
football_xg_model
Estimate a match's expected goals and win/draw/loss probabilities. Args: home_team: First team code (e.g. "ARG"). away_team: Second team code (e.g. "BRA"). neutral: True for a neutral venue (no home advantage). World Cup default. Returns: data: {expected_home_goals, expected_away_goals, home_win, draw, away_win}. meta.estimated: true.
football_match_predictor
Predict a single match: most likely scoreline + outcome probabilities. Args: home_team: First team code. away_team: Second team code. neutral: True for a neutral venue (World Cup default). Returns: data: {most_likely_score, home_win, draw, away_win, predicted_winner}. meta.estimated: true.
football_simulate_group
Monte Carlo one group's round-robin -> per-team qualification probabilities. Args: group: Group letter A-L. iterations: Number of simulations (clamped to 100..20000). Returns: data.teams: {code: {p_first, p_second, p_third, p_fourth, p_advance, avg_points}}. data.iterations: iterations actually run. meta.estimated: true. meta.conditioned_matches: completed matches locked in.
football_simulate_bracket
Monte Carlo the full World Cup 2026 — per-team round + title probabilities. Simulates all 12 groups, advances the top 2 + 8 best third-placed teams to a 32-team knockout, and plays it to a champion, ``iterations`` times. Args: iterations: Number of tournament simulations (clamped to 100..20000; ~10000 gives stable ±2% probabilities). seed: Optional RNG seed for reproducible output. Returns: data.teams: {code: {reach_r32, reach_r16, reach_qf, reach_sf, reach_final, win}} sorted by win probability descending. data.champion: most likely winner. data.iterations: iterations run. meta.estimated: true. meta.conditioned_matches: completed matches locked in (played group results fixed, decided knockout ties locked). Example: football_simulate_bracket() football_simulate_bracket(iterations=20000, seed=42)
football_knockout_path
Round-by-round survival probabilities for one team in the full sim. Args: team: Team code (e.g. "FRA"). iterations: Number of tournament simulations (clamped to 100..20000). seed: Optional RNG seed. Returns: data: {team, reach_r32, reach_r16, reach_qf, reach_sf, reach_final, win}. meta.estimated: true.
football_find_value_bets
Surface the largest gaps between the model's win probability and the market. De-vigs each market's 1X2 decimal odds (removes the margin so implied probabilities sum to 1) and compares them to this server's own match-outcome probabilities — the same Elo/Poisson path ``football_match_predictor`` uses. Where the model probability exceeds the de-vigged market probability by at least ``min_edge``, the outcome is flagged with its edge and the model's fair odds. Args: team: Optional team name to filter events (case-insensitive substring, matched against both sides). Omit to scan every WC 2026 odds event. min_edge: Minimum edge (model_prob - devigged_market_prob), 0..1. Default 0.05 (5 percentage points). Returns: data.value_bets: list of {event_id, home, away, outcome, model_prob, fair_odds, market_odds, edge, bookmaker}, sorted by edge descending. data.events_analysed: events with both teams rated (model-comparable). meta.estimated: true. meta.is_stale reflects the odds freshness.
football_form_trends
Return rolling form, goal record, and xG trend for a football team. Args: team: Team name (e.g. "Brazil", "Argentina"). Returns: data: {form_string, wins, draws, losses, goals_scored, goals_conceded, xg_for, xg_against, recent_trend, matches_analysed}. meta.estimated: true — derived from available fixture data.
football_build_accumulator
Model the joint probability of several match outcomes from the top model-vs-market gaps. Calls ``football_find_value_bets`` internally to fetch live odds, then selects the strongest legs and combines them under the joint-probability model. Args: legs: Number of legs (2-8). Default 3. min_edge: Minimum edge threshold per leg. Default 0.05. Returns: data: {legs, legs_used, combined_odds, combined_model_prob, combined_edge, risk_flag, independence_warning}. meta.estimated: true.
f1_get_sessions
Return F1 sessions for a given year, optionally filtered by country. Args: year: Championship year (e.g. 2025). country: Optional country name to filter (e.g. "Monaco"). Returns: data.sessions: list of session objects with session_key, session_type, date. meta.source: adapter that served the data.
f1_get_drivers
Return driver list for a specific F1 session. Args: session_key: OpenF1 session identifier. Returns: data.drivers: list of driver objects with driver_number, full_name, team. meta.source: adapter that served the data.
f1_get_lap_times
Return lap times for a driver in a specific F1 session. Args: session_key: OpenF1 session identifier. driver_number: Driver's race number (e.g. 1 for Verstappen). limit: Max laps to return, 1..200 (default 100 — covers most full races). offset: Number of laps to skip for paging (default 0). Returns: data.laps: page of lap objects with lap_number and lap_duration. OpenF1 does not put compound/tyre_life here — those live on the stints endpoint. data.pagination: {total, count, offset, limit, has_more, next_offset}. meta.source: adapter that served the data.
f1_get_standings
Return F1 driver and constructor championship standings for a year. Args: year: Championship year (e.g. 2025). Returns: data.driver_standings: driver championship positions and points. data.constructor_standings: constructor championship positions and points. meta.source: adapter that served the data.
f1_get_race_results
Return the final classification for one F1 race, keyed by year and round. Args: year: Championship year (e.g. 2025). round: Round number within the season (1-based; e.g. 1 for the opener). Returns: data.results: Ergast/Jolpica RaceTable payload — finishing order, times, grid positions, points, and fastest laps for the race. meta.source: adapter that served the data.
f1_get_weather
Return weather data for a specific F1 session. Args: session_key: OpenF1 session identifier. Returns: data.weather: list of weather snapshots with temperature, rainfall, wind. meta.source: adapter that served the data.
f1_tyre_degradation
Fit a tyre degradation model for a driver + compound in a session. Args: session_key: OpenF1 session identifier. driver_number: Driver's race number. compound: Tyre compound (SOFT, MEDIUM, HARD, INTER, WET). Returns: data: {intercept, slope, residual_std, sample_count}. meta.estimated: true — model output, not telemetry oracle.
f1_undercut_window
Estimate whether an undercut is viable for the attacker against the target. Args: session_key: OpenF1 session identifier. attacker_number: Attacking driver's race number. target_number: Target driver's race number. current_lap: Current lap number in the race. Returns: data: {laps_to_clear, viable, marginal}. meta.estimated: true.
f1_head_to_head_pace
Compare lap-time pace distribution between two drivers in a session. Args: session_key: OpenF1 session identifier. driver_a: First driver's race number. driver_b: Second driver's race number. Returns: data: {driver_a_avg_s, driver_b_avg_s, delta_s, faster_driver}. meta.estimated: true.
f1_weather_strategy_impact
Analyse weather data and recommend compound or pit-window adjustments. Args: session_key: OpenF1 session identifier. Returns: data: {has_rain, avg_track_temp_c, compound_recommendation, recommendation}. meta.estimated: true.
f1_predict_pit_strategy
Predict the optimal pit-stop strategy for a driver in an F1 race session. Args: session_key: OpenF1 session identifier for a recorded race. driver_number: Driver's race number (e.g. 1 for Verstappen). current_lap: Current lap to project from (default 1 = full race ahead). total_laps: Total race laps. If omitted, inferred from the highest observed lap_number in the fetched laps (correct for Monaco 78 / Spa 44), falling back to 57 when no laps are available. An explicit value always wins. Returns: data.stop_laps: recommended pit laps. data.compound_sequence: tyre compounds for each stint. data.expected_finish_position: currently always None (not modelled). data.confidence: 0.0-1.0 model confidence. meta.total_laps: race length used (explicit arg, else inferred from laps). meta.estimated: true. Example: f1_predict_pit_strategy(session_key=9158, driver_number=1) f1_predict_pit_strategy(session_key=9158, driver_number=16, current_lap=20, total_laps=78)
f1_qualifying_analysis
Analyse a qualifying session: best lap per driver, gap to pole, projected grid. Args: session_key: OpenF1 session identifier for a Qualifying session. Returns: data.grid: [{position, driver_number, full_name, team_name, best_lap_gap_s}]. data.pole_time_s: pole lap duration in seconds. data.drivers_analysed: count of drivers with valid laps. meta.estimated: true — grid derived from session laps, not official timing.
f1_race_pace_compare
Compare race-pace and tyre degradation between two F1 drivers in a session. Args: session_key: OpenF1 session identifier. driver_a: First driver's race number. driver_b: Second driver's race number. Returns: data: {by_compound, overall_faster, compounds_compared}. meta.estimated: true — degradation model fit, not official timing.
cricket_get_live_matches
Return all currently live cricket matches across all series. Returns: data.matches: list of live match objects (team names, score, status). meta.source: which adapter served the response. meta.is_stale: true if data is from stale cache.
cricket_get_scorecard
Return the full scorecard for a specific match. Args: match_id: The match identifier (e.g. from cricket_get_live_matches). Returns: data: full scorecard with innings, partnerships, bowling figures. meta.source: adapter that served the data.
cricket_get_points_table
Return the points table / standings for a cricket series. Args: series_id: The series identifier (e.g. IPL 2026 series ID from CricAPI). Returns: data: points table rows with team, P, W, L, NRR, Points. meta.source: adapter that served the data.
cricket_get_schedule
Return the upcoming match schedule, optionally filtered by series. Args: series_id: Optional. Filter to a specific series. If omitted, returns all upcoming fixtures across all active series. limit: Max matches to return, 1..200 (default 50). offset: Number of matches to skip for paging (default 0). Returns: data.matches: page of upcoming matches with teams, date, venue. data.pagination: {total, count, offset, limit, has_more, next_offset}. meta.source: adapter that served the data.
cricket_get_squad
Return the squad roster for a cricket team, optionally for a specific series. Args: team: Team code or name (e.g. "MI", "CSK", "IND", "AUS"). series_id: Optional. Series ID to pull the tournament-specific squad. If omitted, falls back to static seed data. Returns: data.players: list of players with name, role, and credits. meta.source: adapter that served the data (cricapi / static_seed).
cricket_get_live_odds
Return live market head-to-head odds for upcoming/live IPL matches. Sourced from The Odds API (requires THEODDS_KEY). Without a key the call returns a clean ALL_SOURCES_FAILED envelope rather than crashing. Args: team: Optional team name to filter events (case-insensitive substring, matched against both sides). Omit to return every IPL event. The Odds API uses its own opaque event ids, so a CricAPI match_id cannot be resolved to an event yet — filtering is by team name. Returns: data.events: list of {event_id, home, away, commence_time, bookmakers: [{name, home, away}]} with decimal h2h prices per bookmaker. meta.source: adapter that served the data (theodds / cache:stale).
cricket_build_dream11_team
Recommend an optimal fantasy XI + captain + vice-captain for one fixture. Args: match_id: CricAPI match identifier; resolves team_a/team_b/venue automatically. team_a: First team code/name (e.g. ``MI``). Required if match_id is absent. team_b: Second team code/name (e.g. ``CSK``). Required if match_id is absent. venue: Venue key/name (e.g. ``wankhede``). Required if match_id is absent. strategy: ``"balanced"`` only in Phase 2; future variants reserved. Returns: data.players: 11 picked players with name/role/credits/team/projected_points. data.captain: name of the chosen captain. data.vice_captain: name of the chosen VC. data.total_credits: sum of credits used (<= 100). data.total_projected_points: fantasy points including C x2 and VC x1.5 boosts. meta.estimated: true — projections are model output, not a fantasy oracle. Example: cricket_build_dream11_team(team_a="MI", team_b="CSK", venue="wankhede") cricket_build_dream11_team(match_id="abc123")
cricket_captain_recommendation
Return the top-3 captain candidates ranked by projected points. Args: match_id: CricAPI match identifier; resolves team_a/team_b/venue automatically. team_a: First team code/name. Required if match_id is absent. team_b: Second team code/name. Required if match_id is absent. venue: Venue key/name. Required if match_id is absent. Returns: data.candidates: list of 3 dicts with name/role/team/projected_points. meta.source: model:captain_score. meta.estimated: true.
cricket_differential_picks
Suggest low-ownership picks with positive projected upside. Ownership is *estimated* — proxied by credit weight (lower-credit players tend to have lower ownership), not real ownership data. Flagged ``estimated: true`` in the response. Args: match_id: CricAPI match identifier; resolves team_a/team_b/venue automatically. team_a: First team code/name. Required if match_id is absent. team_b: Second team code/name. Required if match_id is absent. venue: Venue key/name. Required if match_id is absent. ownership_threshold: percent ownership cap; affects estimated label. Returns: data.picks: list of {name, role, team, credits, projected_points, estimated_ownership_pct}. meta.source: model:captain_score (filtered). meta.estimated: true.
cricket_player_form_index
Report a 0-100 form score for a player using the player_stats chain. Args: player_id: Upstream player identifier (CricAPI/Cricbuzz id). Returns: data.form_score: 0..100 indicator. data.trend: "rising" / "stable" / "falling". data.samples: how many recent innings were available. meta.source: which adapter served the underlying stats. meta.estimated: true.
cricket_get_pitch_report
Summarise pitch characteristics for a venue. Args: venue: Venue key (e.g. ``wankhede``), official name, or city. Returns: data: {batting_friendly 0..1, expected_first_inn, recommendation, venue, pitch_type}. meta.source: which adapter served the venue record.
cricket_find_value_bets
Compare model probabilities against market-implied IPL odds. Requires THEODDS_KEY. NOTE: cricket has no calibrated team-strength model wired yet (unlike the football Elo/Poisson path), so this tool currently returns an EMPTY ``value_bets`` list — scoring an edge against a neutral 50/50 prior would flag every market underdog, which would be misleading. It still reports how many events were screened so callers know odds were available. For raw de-vigged prices use ``cricket_get_live_odds``. Real edge detection lands when a cricket win model is wired (see cricket_head_to_head). Args: team: Optional team name to filter events (case-insensitive substring). Omit to scan every IPL odds event. min_edge: Minimum edge (model_prob - devigged_market_prob), 0..1. Default 0.05. Currently informational only (no bets emitted). Returns: data.value_bets: always ``[]`` until a cricket model is wired. data.events_analysed: count of events screened (both teams present). data.model: ``"neutral_baseline"``. data.note: why no bets are emitted. meta.estimated: true.
cricket_head_to_head
Compare two cricket teams head-to-head using squad form and player stats. Args: team_a: First team code or name (e.g. "MI", "India"). team_b: Second team code or name (e.g. "CSK", "Australia"). Returns: data: {team_a, team_b, team_a_edge_count, team_b_edge_count, key_players_a, key_players_b, h2h_win_rate_a, h2h_win_rate_b, win_prob_a, win_prob_b}. meta.estimated: true.
cricket_player_matchup
Analyse the head-to-head matchup between two cricket players based on role and career stats. Args: player_a: Player ID or name for the first player. player_b: Player ID or name for the second player. Returns: data: {matchup_type, edge_holder, edge_reason, signals, role_a, role_b}. meta.estimated: true — heuristic model, not ball-by-ball H2H data.
cross_sport_build_accumulator
Model the joint probability of multiple outcomes across football and cricket. Args: legs: Total legs across both sports (2-8). Default 3. min_edge: Minimum edge per leg. Default 0.05. Returns: data: same shape as football_build_accumulator, with sport field per leg. meta.estimated: true.
Claude Desktop / Cursor
Paste into your MCP client config file to install this server.
{
"mcpServers": {
"sportiq mcp": {
"sportiq": {
"command": "uvx",
"args": [
"sportiq-mcp"
]
}
}
}
}McpServers
{
"sportiq": {
"command": "uvx",
"args": [
"sportiq-mcp"
]
}
}SportIQ MCP — Turn any AI into your personal sports analyst, tipster & fantasy strategist 🏆⚽️🏎️ 🏏
What if you could just ask your AI: "Who's winning the 2026 World Cup, and where's the value in tonight's odds?" — and get a real, data-backed answer in seconds? That's SportIQ. It plugs 44 live sports tools straight into Claude, ChatGPT, Cursor, or any MCP-compatible AI — covering FIFA World Cup 2026 football, Formula 1, and IPL cricket. No spreadsheets. No ten browser tabs. No paid stats subscription. Just plain-English questions → instant analysis. ## 😮 The part that surprises people Stuff that used to take hours of research and a dozen websites now takes one sentence: - "Simulate the World Cup 2026 bracket 10,000 times — who actually lifts the trophy?" - "Find me the best value bets in this weekend's fixtures based on real bookmaker odds." - "Build me the optimal Dream11 team for tonight's IPL match under the credit cap." - "What's the smartest pit-stop strategy if it rains at the next Grand Prix?" - "Compare these two F1 drivers' race pace and tell me who's quicker." Your AI calls SportIQ behind the scenes, pulls live data, runs the math, and hands you a clear answer. Gathering data, comparing odds, and modelling outcomes genuinely becomes that easy. ## 🔥 Three flagship intelligence engines These aren't "fetch a stat" tools — they're real models: - ⚽football_simulate_bracket — Monte Carlo tournament simulation with a Poisson expected-goals match
engine and Elo-seeded brackets. Full WC 2026 format (48 teams, 12 groups, top-2 + 8 best-thirds → R32 knockout). Get
each nation's title probability, not a vibe.
- 🏎️ f1_predict_pit_strategy — a tyre-degradation model running on live OpenF1 telemetry, with
undercut-window detection and per-circuit pit-loss. Know when to box before the race does.
- 🏏 cricket_build_dream11_team — a PuLP ILP optimizer that builds a mathematically optimal Dream11 XI under
every credit, role, and team-count constraint. Fantasy edge, solved.
## 🎯 Everything you can do
Betting & value: live bookmaker odds, value-bet detection, accumulator/parlay builder, cross-sport bet slips.
Predictions & sims: match predictors, group + knockout simulations, xG models, head-to-heads.
Fantasy: Dream11 optimizer, captain picks, differential punts, player form & matchup analysis.
Live & raw data: live scores, fixtures, standings, squads, pitch reports, lap times, weather, qualifying & race
results.
## 👥 Who it's for
Sports bettors hunting an edge, fantasy (Dream11/FPL-style) players, F1 strategy nerds, data-driven fans, and
developers building sports-AI apps. If you follow the World Cup, Formula 1, or the IPL — this turns your AI into a
24/7 analyst.
## ⚡ Install in 10 seconds
uvx sportiq-mcp
Zero config. No API keys needed for the simulation, prediction, and fantasy tools — they work offline out of the box.
Optional keys unlock live scores and odds.
## ❓ FAQ
Can AI predict who wins the 2026 World Cup? Yes — football_simulate_bracket runs thousands of Monte Carlo
simulations and returns each team's win probability.
Can it find value bets? Yes — it compares model-implied probabilities against live bookmaker odds to surface
positive-expected-value bets across football, F1, and cricket.
Does it build Dream11 teams? Yes — an ILP solver returns a fully legal, points-optimized XI in one call.
Which AI tools does it work with? Any MCP client — Claude Desktop, Cursor, and the broader Model Context Protocol
ecosystem.
Is it free? The package is free and open-source (MIT).
---
🔗 PyPI: sportiq-mcp · Official MCP Registry: io.github.Ninjabeam20/sportiq-mcp · GitHub:
github.com/Ninjabeam20/SportIQ-MCP
👤 Built by Utkarsh Gupta (@Ninjabeam20)
SportIQ is an analytics and entertainment tool. It surfaces probabilities and value — not guarantees. Bet
responsibly, and only where it's legal for you.Sign in to leave a review
Use Google, GitHub, or an email account so ratings stay tied to real people.
No reviews posted yet.
