Every change Wellknown observed on this MCP server, newest first, with what it was before and what it became. Tool-surface changes carry the definition diff. Nothing here is edited after the fact.
Added "f1_simulate_championship" and "football_what_if"; changed the definition of "cricket_build_dream11_team", "cricket_captain_recommendation", "cricket_differential_picks" and 19 more (44 tools before, 46 now)
⟨106 unchanged words⟩ projections are model output, not a fantasy oracle. meta.form_source: "default_neutral" (role-based projections; see meta.note). meta.scoring_profile: the Dream11 T20 points profile id. meta.excluded_missing_credits: players dropped for having no contest credits. Example: cricket_build_dream11_team(team_a="MI", team_b="CSK" ⟨5 unchanged words⟩
⟨90 unchanged words⟩ with name/role/team/projected_points. meta.source: model:captain_score. meta.estimated: true. meta.form_source: "default_neutral".
⟨77 unchanged words⟩ name, role, team, credits, projected_points, estimated_ownership_pct, ownership_pct_estimated}. meta.source: model:captain_score (filtered). meta.estimated: true. meta.ownership_source: "heuristic_from_credits". meta.form_source: "default_neutral".
⟨76 unchanged words⟩ cricket win model is wired (see cricket_head_to_head).; it will flag outcomes where the model beats the de-vigged market by ``min_edge`` **and** the offered price has positive expected value. Args: team: Optional team name to filter ⟨33 unchanged words⟩ a cricket model is wired. data.events_analysed: count of not-yet-started events screened (both teams present). data.model: ⟨11 unchanged words⟩
⟨44 unchanged words⟩ default 0). Returns: data.matches: page ofupcomingmatches dated today (UTC) or later, with teams,date,venue.venue; filtered to ``series_id`` when the source labels series. data.pagination: {total, count, offset, limit, ⟨9 unchanged words⟩
⟨41 unchanged words⟩ , h2h_win_rate_b, win_prob_a, win_prob_b}. meta.estimated: true. meta.estimate_quality: "uninformative" when no player stats were available (both sides at default form), else "player_stats".
⟨9 unchanged words⟩ on role and career stats. Args: player_a:Player IDCricAPIorplayernameID for the firstplayer.player (names are not resolved). player_b:Player IDCricAPIorplayernameID for the secondplayer.player (names are not resolved). Returns: data: {matchup_type, edge_holder, edge_reason, ⟨13 unchanged words⟩
{"properties":{"player_a":{"description":"Player ID
⟨13 unchanged words⟩ OpenF1 session identifier. driver_number: Driver's race number (e.g.driver1numbersforchangeVerstappenby season; use f1_get_drivers). limit: Max laps to return, 1..200 ⟨56 unchanged words⟩
{"properties":{"driver_number":{"description":"Driver's race number (e.g.driver1numbersforchangeVerstappenby season; use f1_get_drivers).","title":"Driver Number","type ⟨57 unchanged words⟩
Return F1 sessions for a given year, optionally filtered bycountry.country or session name. Args: year: Championship year (e.g.20252026). country: Optional country name to filter (e.g. "MonacoNetherlands"). session_name: Optional session name to keep, case-insensitive (e.g. "Race", "Qualifying", "Sprint"). latest_completed: When true, return only the single session that ended most recently (greatest date_end before now, UTC) — e.g. with session_name="Race", the latest finished Grand Prix. Returns: data.sessions: list of session objects with ⟨9 unchanged words⟩
⟨10 unchanged words⟩ "Optional country name to filter (e.g. \"Monaco\Netherlands\").","title":"Country"},"latest_completed":{"default":false,"description":"When true, return only the single session that ended most recently (greatest date_end before now, UTC) — e.g. with session_name=\"Race\", the latest finished Grand Prix.","title":"Latest Completed","type":"boolean"},"session_name":{"anyOf":[{"type":"string"},{"type":"null"}],"default":null,"description":"Optional session name to keep, case-insensitive (e.g. \"Race\", \"Qualifying\", \"Sprint\").","title":"Session Name"},"
⟨18 unchanged words⟩ will win the F1 championship this year".There is no F1For titleMonte Carlo — current points and position areprobabilitiestheuseanswer.f1_simulate_championship. This is not a cricket or football tool. Args: year: Championship year (e.g. 2026). Returns:data.driver_standings:data.seasondriver/championshipdata.round:positionsseason andpoints.the last round counted.data.constructor_standingsdata.drivers:constructor[{position,
⟨26 unchanged words⟩ data: {driver_a_avg_s, driver_b_avg_s, delta_s, faster_driver}. The "avg" values are median lap times after dropping pit-out laps and slow outliers (safety-car / in-laps). meta.estimated: true.
⟨19 unchanged words⟩ a recorded race. driver_number: Driver's race number (e.g.driver1numbersforchangeVerstappenby season; use f1_get_drivers). current_lap: Current lap to project from ⟨6 unchanged words⟩ . total_laps: Total race laps. If omitted,inferredestimated from thehighestregulationobserved lap_number in theminimumfetchedracelapsdistance (correct305forkm;
⟨24 unchanged words⟩ compound (SOFT, MEDIUM, HARD, INTER,WETWET; "INTERMEDIATE" = INTER). Returns: data: {intercept, slope, ⟨11 unchanged words⟩
⟨4 unchanged words⟩ compound (SOFT, MEDIUM, HARD, INTER,WETWET; \"INTERMEDIATE\" = INTER).","title":"Compound","type": ⟨29 unchanged words⟩
⟨35 unchanged words⟩ : data: {laps_to_clear, viable, marginal}. meta.gap_to_target_s: attacker-minus-target race time at current_lap. meta.gap_source: "cumulative_lap_time", or "default" (assumed 2.0 s, also in meta.assumed_gap_s) when either driver lacks a full lap history. meta.estimated: true.
⟨35 unchanged words⟩ probabilities — the same Elo/Poisson path ``football_match_predictor`` uses.WhereFlags outcomes where the modelprobability exceedsbeats the de-vigged marketprobabilitybyat least``min_edge``,**and** theoutcomeofferedispriceflaggedhas positive expected value, withitsthe edge, the expected value and themodel's fair odds. Events that have already started are skipped.
⟨7 unchanged words⟩ trend for a football team. Args: team:TeamFIFA code (e.g. ARG) or name (e.g. "BrazilArgentina", "ArgentinaSouth Korea"). Returns: data: {form_string, wins, ⟨17 unchanged words⟩
{"properties":{"team":{"description":"TeamFIFA code (e.g. ARG) or name (e.g. \"Brazil\Argentina\", \"Argentina\South Korea\").","title":"Team","type" ⟨7 unchanged words⟩
Returnlivemarket head-to-head odds forupcomingany World Cup 2026matches.events the odds feed still lists. Sourced from The Odds API (requires THEODDS_KEY) ⟨6 unchanged words⟩ returns a clean ALL_SOURCES_FAILED envelope rather than crashing. The tournament ended with the 2026-07-19 final, so the feed is normally empty. Args: team: Optional team name to filter ⟨22 unchanged words⟩ bookmakers: [{name, home, draw, away, last_update}]} with decimal 1X2 prices per bookmaker. ⟨11 unchanged words⟩
⟨10 unchanged words⟩ code or name (e.g. "ARG").WithoutLive rosters need an API-Football key;key,without one thestatic seed serves an empty-but-valid squad(no rosters area follow-upbundled). Returns: data.squad: list of {name, number, position, age} (empty from the seed). meta.source: adapter that served the data. meta.note: present when the seed served it — how to get live squads.
⟨4 unchanged words⟩ ⟨5 unchanged words⟩ team in the full sim. Args: team:TeamFIFA code or name (e.g. "FRA" or "France"). iterations: Number of tournament simulations ( ⟨20 unchanged words⟩
⟨30 unchanged words⟩ :"Seed"},"team":{"description":"TeamFIFA code or name (e.g. \"FRA\" or \"France\").","title":"Team","type" ⟨7 unchanged words⟩
⟨7 unchanged words⟩ + outcome probabilities. Args: home_team: First team,code.FIFA code or name (e.g. "ESP" or "Spain"). away_team: Second team,code.FIFA code or name. neutral: True for a neutral venue (World ⟨13 unchanged words⟩
{"properties":{"away_team":{"description":"Second team,code.FIFA code or name.","title":"Away Team","type":"string"},"home_team":{"description":"First team,code.FIFA code or name (e.g. \"ESP\" or \"Spain\").","title":"Home Team","type": ⟨25 unchanged words⟩
⟨7 unchanged words⟩ 12-group qualification context. Args: group: Group letterA-L.A-L (also accepts "Group A"). iterations: Number of simulations (clamped to 100..20000 ⟨24 unchanged words⟩
{"properties":{"group":{"description":"Group letterA-L.A-L (also accepts \"Group A\").","title":"Group","type":"string ⟨21 unchanged words⟩
⟨5 unchanged words⟩ and win/draw/loss probabilities. Args: home_team: First team, FIFA code or name (e.g. "ARG" or "Argentina"). away_team: Second team, FIFA code or name (e.g. "BRA" or "Brazil"). neutral: True for a neutral venue ⟨17 unchanged words⟩
{"properties":{"away_team":{"description":"Second team, FIFA code or name (e.g. \"BRA\" or \"Brazil\").","title":"Away Team","type":"string"},"home_team":{"description":"First team, FIFA code or name (e.g. \"ARG\
Estimate each driver's F1 drivers' title probability for the rest of a season. Monte Carlo over the remaining races and sprints (Plackett-Luce finishing orders weighted by each driver's season points rate), plus exact elimination maths: a driver who cannot catch the leader's current points even by winning every remaining race and sprint has title_prob 0.0. This is not a cricket or football tool. Args: year: Championship season (2018-2030, default 2026). iterations: Monte Carlo iterations, clamped to 1000-20000 (default 10000). seed: Optional RNG seed for reproducible probabiliti…
Replay World Cup 2026 from a chosen stage, optionally flipping one real knockout result. Keeps every real result played before ``replay_from`` and Monte-Carlos the rest of the tournament from there. ``flip_winner_of`` makes one decided knockout tie in the kept results go the other way first. Args: replay_from: Stage to re-simulate from: "group" (whole tournament, no real results kept), "r32", "r16", "qf", "sf" or "final" (keeps every result before the final and simulates only the final). flip_winner_of: Optional tie to flip, as two FIFA codes or names joined …
Recently observed → Live
Live → Recently observed
Recently observed → Live
Live → Recently observed
Changed the definition of "cricket_captain_recommendation", "cricket_get_live_odds" and "f1_get_standings"
Return the top-3 captain candidates ranked by projected points. IPL venues only (pitch seed is IPL grounds). Test/international matches and unknown venues fail rather than inventing a ranking. Same-role players often tie: projections use default form 55 and default opposition 0.5, not per-player history. Args: match_id: CricAPI match identifier; resolves team_a/team_b/venue ⟨14 unchanged words⟩ Required if match_id is absent. venue: Venuekey/name.key/name (IPL ground, e.g. ``wankhede``). Required if match_id is absent. Returns: data.candidates: ⟨11 unchanged words⟩
⟨65 unchanged words⟩ }],"default":null,"description":"Venuekey/name.key/name (IPL ground, e.g. ``wankhede``).
Recently observed → Live
Certificate recorded, valid to 2026-12-04
Authorization not required
Live → Recently observed
First tool surface recorded: 44 tools (server version 0.3.2)
Showing the latest 11 events. The API returns up to 500 and filters by kind: ?kind=tool_surface_changed
⟨22 unchanged words⟩ driver_number":{"description":"Driver's race number (e.g.driver1numbersforchangeVerstappenby season; use f1_get_drivers).","title":"Driver Number","type ⟨23 unchanged words⟩ "description":"Total race laps. If omitted,inferredestimated from thehighest observed lap_number inregulationtheminimumfetchedracelapsdistance (correct305forkm; Monaco78260/km)Spaover44),thefallingcircuit'sbacklaptolength;57INVALID_INPUT whennothelapscircuitareisavailable.unknown. An explicit value always wins.","title": ⟨9 unchanged words⟩
⟨28 unchanged words⟩ }],"default":null,"description":"Optional FIFA code or team name to filter events (case-insensitive substring,matched against bothsidessides; an unrecognised value falls back to a case-insensitive substring match). Omit to scan every WC 2026 odds ⟨7 unchanged words⟩
Return live market head-to-head odds for upcoming/live IPL matches. IPL only (~March-May). An empty ``events`` list outside that window is a successful empty market, not an outage. Not international/Test/other T20 leagues. For World Cup 2026 football odds use ``football_get_odds``. Sourced from The Odds API (requires THEODDS_KEY). ⟨71 unchanged words⟩ away}]} with decimal h2h prices per bookmaker. Empty when no IPL events are listed (typical off-season). meta.source: adapter that served the data (theodds ⟨4 unchanged words⟩
Return F1 driver and constructor championship standings for a year. Use this for "who is leading / who will win the F1 championship this year". There is no F1 title Monte Carlo — current points and position are the answer. This is not a cricket or football tool. Args: year: Championship year (e.g.20252026). Returns: data.driver_standings: driver championship positions and ⟨13 unchanged words⟩
{"properties":{"year":{"description":"Championship year (e.g.20252026).","title":"Year","type": ⟨7 unchanged words⟩