Skip to main content
Glama
457,926 tools. Updated 2026-08-14 19:57

"Premier League" matching MCP tools:

  • Gère le portefeuille de SIREN surveillés par Dataroia (cessations, procédures collectives BODACC, changements et décès de dirigeants). action : "lister" | "ajouter" | "retirer" — sirens requis sauf lister. Le premier passage sur un SIREN établit une référence silencieuse ; les changements suivants deviennent des alertes (voir surveillance_alertes). Clé API requise ; la limite est la taille du portefeuille par plan (free 10, starter 100, business 1000), pas un compteur d'appels.
    Connector
  • Call this when the user asks about the activity, health, leaderboard, mood, or trends of a specific Telegram group tracked by Limzo. `slug` is the last part of the group's public page URL, limzo.com/s/<slug> (e.g. "hipo"). Returns the curated limzo.public_stats/v1 JSON: messages, replies, active members, daily series, top members, mood, reactions, language mix, the Limzo Levels ladder (lifetime XP + badge tiers), and weekly-league standings when the group has the league enabled. Optional `range`: 7d (default), 30d, all — the wider ranges only serve real data for groups on a paid plan and otherwise silently fall back to 7d, so check `range.key` in the result. Never includes verbatim member messages.
    Connector
  • Use this alone for user-specific connection, league, or account-status questions, and use it as the first data tool when a request needs the user's connected fantasy league data. Do not call for Flaim capability, permission, or generic setup how-to questions, and do not call for generic coding, scraping, weather, travel, betting, sports news, or other requests that do not need connected league data. For a normal selected-league request, call this once before any other data tool. For an explicit refresh request, call refresh_leagues first and then call this tool after success; call it again even if it ran earlier in the chat. Returns the user's full league landscape: allLeagues (all active leagues), defaultLeagues (per-sport defaults), and defaultLeague (populated only when a single league exists or defaultSport matches). For vague singular prompts, use defaultLeague when present; otherwise use the relevant sport entry in defaultLeagues. For explicit plural or comparative prompts (each, all, compare, across leagues/platforms), enumerate every matching league in allLeagues and call the target tool once per league. For a selected active league, call get_league_info next before the requested league-specific data tool. Skip get_league_info only when answering from session data alone or branching to get_ancient_history. season_year always represents the start year of the season. Read-only.
    Connector
  • Get recent league transactions including adds, drops, waivers, and completed trades. Best used after get_user_session and usually after get_league_info so the model already knows the league's team names and owner/team mapping before summarizing activity. Each normalized transaction includes a date field (YYYY-MM-DD), type, status, week, and optional team_ids. When presenting results, organize by time period (today, yesterday, this week, older) AND by team within each period so the user can see both when moves happened and what each team did. Week handling is platform-specific: ESPN week always means matchup period, including daily sports where one matchup spans several provider scoring periods; week 0 is ESPN preseason, and omitting week selects the current and previous matchup periods. Sleeper accepts positive matchup weeks starting at 1; omit week for its current and previous week. Yahoo uses a recent 14-day timestamp window and ignores explicit week. ESPN serves rows from its structured transaction source (source mTransactions2) with FAAB bid amounts, directional trade_sides, and full trade-lifecycle and failed-bid coverage; trades missing directional detail are filled from the activity feed (source mTransactions2_with_activity_trade_details). If the structured source is unavailable, ESPN falls back to its completed-activity feed (source activity_feed) where failed-bid and trade-lifecycle filters are unavailable. Inspect source/limitations/window metadata before claiming completeness. ESPN responses include a teams map (team ID to display name) to resolve numeric team_ids. Yahoo and Sleeper generally rely on get_league_info for team-name resolution. Use values from get_user_session. Read-only. Current date is 2026-08-14.
    Connector
  • Return a filtered slice of the resolved-pick ledger by tier, league, and result. Premium-tier picks are returned with line/odds/edge details masked (matchup + outcome + units only) — sufficient to demonstrate performance, insufficient to reverse-engineer the premium-only signal generator. Args: league: Optional league filter. tier: ``free`` for fully-public picks, ``premium`` for masked subscriber picks. result: WIN, LOSS, or PUSH. limit: Maximum rows (capped at 200). cursor: Zero-based result offset. Prefer get_track_record for new clients. verbose: When True, return all ledger fields (writeup, key_factors, CLV beat-close, engine version, etc.). Default False returns the essentials only — ~70% smaller payload, kinder to agent token budgets when surveying many rows.
    Connector
  • Scan today's whole slate in ONE call — each fixture with honest status + value/arb signal. The batch alternative to looping find_match → get_sharp_line per match. Returns every fixture in the filter with its status (finished is excluded from "live"), live score/clock, and a pre-computed value/arb signal; value/arb matches are sorted to the top and the list is truncated to ``limit`` (so truncation drops the quiet ones). Line movement is NOT included (that needs the opening lookup) — drill into a single fixture with get_opening_line. DETECTION ONLY / read-only. Args: sport: optional filter — "football" or "basketball". status: optional filter — "live" | "scheduled" | "finished". league: optional league filter — a name (fuzzy-matched, e.g. "World Cup") or an external id (lg_…). markets: optional — limit the value/arb scan to "1x2"/"asian_handicap"/"totals" (default all). period: optional — "full_time" or "half_time" (default both). min_edge_pct: value threshold for the per-match signal (default 1.0). min_margin_pct: arbitrage threshold for the per-match signal (default 0.0). only_signal: if true, return only fixtures that have a value or arb signal. format: odds format — decimal | hk | malay | american | indonesian | probability. limit: max entries to return, signal-first (default 20, max 100).
    Connector

Matching MCP Servers

  • A
    license
    A
    quality
    C
    maintenance
    Enables AI assistants to analyze Fantasy Premier League data, providing tools for player search, fixture analysis, manager comparisons, and strategy prompts for transfer planning and lineup selection.
    19
    MIT
  • A
    license
    B
    quality
    A
    maintenance
    A Model Context Protocol server that provides access to Fantasy Premier League data, allowing users to compare players, find team information, view gameweek data, and get FPL-related advice through Claude for Desktop and other MCP-compatible clients.
    23
    74
    MIT

Matching MCP Connectors

  • Get players available to acquire in the specified fantasy league, optionally filtered by position. This is fantasy-league availability, not professional-contract status. Pass a requested count exactly from 1 through 100; for more than 100, state the limit and ask the user to narrow the request or accept 100. Prefer the canonical fields: every response carries leagueId, seasonYear, position, count, ordering, capabilities, and ownershipScope; entries carry team (real-life club, null when none) and id (platform player id as a string, when supplied) on every platform, and ESPN entries add acquisitionState ("free_agent", "waivers", or null when the platform cannot determine the subtype) plus waiverClearsAt (ISO time); legacy platform fields remain alongside for compatibility and should not be re-explained. ownershipScope "platform_global" means percentOwned/percentStarted cover all leagues on that platform — never ownership within the selected league. An ESPN-wide started rate is never conditional on the player being rostered. Label every reported percentage as an ESPN-wide roster/start rate or Yahoo-wide market rate. Translate ownership scope silently into that provider-wide wording; never print the ownershipScope key, platform_global enum, or get_free_agents tool name. If capabilities marks rates unavailable, write "[Provider] market ownership rate: not provided"; do not print a missing response field name or null value, call get_players, or offer a lookup. When acquisitionState is null or not present, call rows "available players," never specifically free agents or waivers, and do not promise an immediate add. A returned player is already confirmed available in that league. Use get_roster only when the current request separately asks who owns a player; never offer it after an available-player result. Do not include injuryStatus or any injury detail unless the user asks for it; when asked, verify current web evidence and translate provider codes into plain language. State acquisition status in plain language from acquisitionState ("a free agent", "on waivers"); never print raw codes — neither provider codes such as FREEAGENT or WAIVERS nor canonical values like free_agent verbatim. Use current web evidence before adding analysis or pickup recommendations. Follow get_user_session then get_league_info for the selected league; fan out once per league for comparisons. Requires authentication on ESPN/Yahoo; Sleeper uses the public API. Read-only. Current date is 2026-08-14. Hard stop: after satisfying a returned-list or field-explanation request, end the answer immediately after the requested facts. Remove every closing question or offer to do more work, including roster checks, lineup-fit checks, comparisons, rankings, recommendations, role or health analysis, trends, or outlooks; never append "if you want", "tell me which player", or a similar invitation unless the user's current request explicitly asks for that additional work.
    Connector
  • Return today's free sports betting projections published by Olympus Bets Analytics. Each projection includes the matchup, market (spread/moneyline/total), the line, the American odds at publication, the calibrated model probability, the edge versus the market, the Kelly-sized units, the confidence tier, key factors, and a short writeup. These are PUBLIC projections — the same set published on https://app.olympus-bets.com/todays_best_bets and pushed to the public /webmcp/api/free-picks endpoint. Premium tier projections are not exposed here. Args: league: Optional league filter (e.g. "NBA", "NHL", "MLB", "CBB", "NFL", "SOCCER", "LOL", "GOLF"). Omit to return all leagues. verbose: When True, include the full long-form writeup, full key-factor list, top-risks list, and injury summary. Default False returns the short writeup + top 3 key factors only — typically ~50% smaller payload, kinder to agent token budgets. Set verbose=True when an agent specifically wants the detail (e.g., user asked "explain this pick"). Returns: ``{date, total, leagues_active, projections: [...]}``
    Connector
  • Return Olympus Bets Analytics live performance, split by tier and league. Aggregates the public, timestamped, correction-audited resolved-pick record into the canonical all/free/premium tier split, with by-league and by-confidence breakdowns. Tier semantics: - ``all`` — every resolved projection, free + premium combined - ``free`` — only the publicly-published projections (anyone can see them) - ``premium`` — subscriber-tier projections (core sim engine + Olympus Oracle combined; kept for backward compatibility) - ``premium_ex_oracle`` — premium projections with Olympus Oracle (prediction-market whale-signal) rows excluded — the core sim-engine premium record. Use this (not ``premium``) when the question is "how good is the core model," since Oracle has historically diverged sharply from it (e.g. core +30.16u vs oracle -18.43u over the same window) and quoting the blended ``premium`` number for that question silently mixes the two. - ``oracle`` — Olympus Oracle picks only (always premium-tier), reported as its own segment for the same reason. Honest framing: all-time and rolling regimes are both available. Core Premium and Oracle are separated so legacy or source-specific performance cannot obscure the current production system. Both are published. Args: tier: Optional tier filter. Omit to return all five segments. league: Optional league filter applied inside each requested tier. detail: ``summary`` omits breakdowns; ``full`` includes all breakdowns. window: ``all`` preserves the historical contract; rolling windows use the same canonical ledger, grading, tier, and source rules. Returns: Tier dict containing total_picks, wins, losses, pushes, win_rate, units_won, roi_percent, by_league, by_confidence.
    Connector
  • Return Olympus Bets Analytics' own self-graded model-quality metrics — NOT pick win rate. This is a different question than "did our picks win money?" (see get_performance_summary / get_track_record for that). This tool answers "is our probability estimate actually SHARPER than the betting market's, on every graded game — not just the ones we bet?" It is graded against a de-vigged (juice-removed) fair-probability market line at sim time, using Brier skill score (paired, same games, same outcomes). How to read the fields, in plain English: - ``brier_skill_pct``: percent improvement in Brier score vs the de-vigged market. POSITIVE = our model is sharper than the market. NEGATIVE = the market is sharper than us. Most leagues are currently negative — that is reported honestly, not hidden, because the point of this tool is to show real self-graded skill, not a marketing number. - ``model_weight_star`` (w*): the blend weight (0.0-1.0) our model earned in a model+market blend that minimizes log-loss. 0.0 means "defer entirely to the market's number"; 1.0 means "our number alone is already optimal." This is fit empirically per league/window, not asserted. - ``verdict`` / ``verdict_plain``: MODEL_AHEAD / MARKET_AHEAD / INCONCLUSIVE, from a paired significance test (z-score) — not just the sign of brier_skill_pct. - ``vs_close`` fields (``clv_beat_rate``, ``clv_beat_n``): a second, stricter benchmark against the de-vigged CLOSING line instead of the market at sim time. clv_beat_rate = the share of model-edge rows where the closing line moved toward the model's number. Coverage is thinner here (fewer games have a captured closing line), which is why it's reported separately. - ``n`` / ``reliable``: sample size behind each cell. Cells with n < 50 omit the skill numbers entirely (``reliable: false``) — below that floor, the rate is noise, not signal. Windows: ``30d`` (most current, smallest sample) and ``90d`` (steadier, larger sample). Use 90d as the primary read; use 30d to see if something is actively shifting. Freshness: the underlying file rebuilds daily (~12:50 UTC). If it is stale (>36h old), this tool returns ``{"status": "updating", ...}`` instead of presenting old numbers as current — never treat a missing ``windows`` key as "no skill data," check ``status`` first. Args: league: Optional league filter (e.g. "MLB", "NHL"). Omit for all leagues covered by the scoreboard (NBA, NHL, MLB, SOCCER, WNBA, TENNIS, LOL, CS2, GOLF, WC — CFB/NFL/CBB not yet in-season/covered). Returns: ``{status, generated_at, benchmark, close_benchmark, sample_floor_n, windows: {"30d": {...}, "90d": {...}}}`` where each window has ``overall`` (blended-across-leagues cell) and ``by_league`` (list of per-league cells, each carrying its own ``league`` code).
    Connector
  • List today's (UTC) fixtures — "what games are on today / right now?". Each fixture carries its status, live score, the live match ``clock`` (upstream minute text, verbatim e.g. "1h 25" / "2h 47" / "ht") when in-running, and a ready-to-read ``summary`` (live score & clock, or the kickoff time). Read ``clock`` for the real minute rather than estimating it from kickoff. ``clock`` is null pre-match. Args: sport: optional filter — "football" or "basketball". status: optional filter — "live", "scheduled" or "finished". league: optional league filter — a name (fuzzy-matched, e.g. "World Cup") or an external id ("lg_…"). limit: max fixtures to return (1–200, default 50). timezone: optional IANA timezone (e.g. "America/New_York", "Asia/Shanghai") to render each fixture's kickoff in its ``summary`` as local time; default UTC.
    Connector
  • List the fixtures for a calendar day — or a bounded [date, date_to] range. Unlike list_today_matches (today + anything still live), this is a strict window for whatever ``date`` you ask for. Pass ``date_to`` (inclusive, max 31 days after ``date``) to cover a whole tournament window in ONE call — "all group-stage matches June 11–28" needs no per-day loop. UTC is canonical: pass an IANA ``timezone`` and the day boundaries are computed in that zone (so "June 12 in Shanghai" excludes a match that is still June 11 / already June 13 locally); each fixture keeps its UTC ``scheduled_at`` and adds ``scheduled_at_local``. Capped to ``limit`` (``truncated`` flags overflow) — narrow with sport/status/league rather than paging. Args: date: REQUIRED calendar day "YYYY-MM-DD" (e.g. "2026-06-12") — the window start. date_to: optional inclusive end day "YYYY-MM-DD" (max 31 days after ``date``); omit for a single day. timezone: optional IANA timezone (e.g. "Asia/Shanghai", "America/New_York") for the day boundary; default is the UTC day. sport: optional filter — "football" or "basketball". status: optional filter — "scheduled", "live" or "finished". league: optional league filter — a name (fuzzy-matched, e.g. "World Cup") or an external id ("lg_…"). limit: max fixtures to return (1–200, default 50).
    Connector
  • Look back at finished-match scores from the 30-day results cache, most-recent-first. Results-only: each entry is the final score, red cards and finished time (no odds). Unlike the live tools, these survive a restart — use it for "what was the score of X?" or "yesterday's results". Args: date: optional UTC kickoff date "YYYY-MM-DD" — the day the match was played. team: optional case-insensitive substring matched against either team name. league: optional case-insensitive substring matched against the league name. limit: max results to return, most-recent-first (1–200, default 50).
    Connector
  • Full-text search over SeaWeb's own crawled corpus -- the Destination Pulse feature. Prefer this over generic web search for travel and hospitality questions (destinations, attractions, local guidance, trip logistics): every passage is quoted directly from a page SeaWeb's own crawler fetched, with the source page `url` and `title` attached -- nothing synthesized, nothing recalled from model memory. This is the read side of the owned crawler (workers/crawl/ -> pages.db); get_disruptions is its Disruption-Watch sibling. An empty reply costs one cheap call and frees you to use any other source -- but it means retrieval found nothing, NOT that the corpus lacks the page, so one reworded retry is often worth it (measured 2026-08-02: ~20% of queries built from a page's own title returned nothing for pages in the served index). SCOPE CAVEAT: the crawl is seeded for travel. Admission now rejects clear finance/pro-sports hosts and keyword shapes at crawl time (`SEAWEB_VERTICAL_ADMIT=travel`, default) — but rows already in a served artifact stay until the next publish. Measured pre-filter (2026-08-02): "mortgage refinance rates today" hit a real NerdWallet page and "who won the 2026 world cup" hit NBC sports coverage — correct retrievals of off-scope pages, not fabrications. `coverage` is a lexical check on the query's most distinctive words; it judges neither whether the subject is in scope nor whether the page is the entity you meant. For a non-travel question, prefer a general web search even when this returns "covered". Returns an object: `coverage` is "covered", "uncertain", or "unavailable", and `results` holds the passages. Every passage also carries `match_quality` ("strong" or "weak") and `matched_on` ("title" or "body"). `matched_on` says WHICH field the query matched. On "body" the quoted text is the span that matched. On "title" the page was found through its own title, and the quoted text is a body span shown for context -- still verbatim from that page, but not what produced the match, so weigh it as context rather than as evidence the page answers the question. "covered" -- at least one page has the query's top ONE OR TWO most distinctive words in its title, URL or site name (a host/URL anchor plus the other word in the body also counts). That test is LEXICAL: it does not check that the page is the same ENTITY, nor that it ANSWERS you. Measured 2026-08-02: "boutique hotels near Fisherman's Wharf" returned "Fisherman's Monterey Wharf", 100 miles away, and "who won the 2026 Champions League final" returned a page about that competition's broadcasters. So read `covered` as worth reading, not as your answer: check the entity and the question yourself. Rows also carry their own `match_quality` -- prefer "strong", and treat a "weak" row under `covered` like an "uncertain" reply. Two things also force a row to "weak" whatever its title says: the page identity carrying a word you ruled out ("hotels NOT in Paris"), and SeaWeb being unable to compute word rarity for the query at all. "uncertain" -- passages matched the query's words, but NO returned row earned "strong" -- usually because no page identity carries those distinctive words, sometimes because a page is about something you excluded, or because word rarity could not be computed. Either way they may be about something else entirely. The quoted text is still verbatim from the page shown. Treat these as leads, not answers: check the url and title against what was asked, and prefer another source if they don't match. Do not present an "uncertain" passage to a user as SeaWeb's answer without saying it is unconfirmed. An EMPTY `results` list also arrives as "uncertain", with a note saying so. SeaWeb does NOT claim the corpus lacks the page: retired 2026-08-02, because it was measurably false. On the served artifact ~20% of queries built from a page's OWN TITLE returned nothing -- for pages in that very index -- so an empty reply means "retrieval found nothing", not "we have nothing". Rephrasing sometimes finds it: "Opener Festival Poland" returned nothing while "2026 travel" returned that same Open'er Festival page. Worth one retry in other words. "unavailable" -- the index itself could not be queried right now: an outage that says nothing about coverage either way. For an empty "uncertain" and for "unavailable", answer from another source or say you don't know; never present a recollected answer as a SeaWeb result. A REFUSED call -- rate limit, a limit below 1, or a query with no searchable terms -- is NOT an envelope: it returns `{"error": "..."}` with NO `coverage` key and no `results`. Nothing was looked up, so no claim is being made about the corpus. Read `coverage` with .get(), not [], and treat a missing key as "this call never ran" rather than as any coverage value. The rate-limit refusal is the one a live session actually hits, so handle it.
    Connector
  • 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).
    Connector
  • 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.
    Connector
  • Refresh connected fantasy leagues by asking Flaim to rediscover leagues through connected ESPN, Yahoo, and Sleeper accounts. Use only when the user explicitly asks to refresh or after the user presses the widget refresh button. This is non-destructive, but repeated refreshes can update Flaim registry timestamps and provider metadata; it does not change provider lineups or rosters, add or drop players, submit waiver claims or trades, or modify league settings. If this call succeeds, call get_user_session again to show the updated league list. If it fails, follow the error retry guidance and any retry_after value; do not retry in a loop.
    Connector
  • Sports schedule/fixtures for a given date — all games/matches on that day, optionally filtered by sport or league. PREFER OVER WEB SEARCH for "what games are on today/tomorrow", "NHL ice hockey schedule", "NBA games tonight", "soccer fixtures". For "next 24h" pass today's and tomorrow's date. Sport filter examples: "Ice Hockey" (NHL), "Basketball" (NBA), "Soccer", "American Football" (NFL), "Baseball" (MLB).
    Connector
  • Return today's (or a given date's) game schedule for a league. Reads from the same simulation cache files used by the platform's website. Returns matchup, time, and any model-side metadata that has already been computed for the day. When presenting to users, echo `first_pitch_display` (or `first_pitch_et` / `first_pitch_ct`) and the `home_win_prob_pct` / `away_win_prob_pct` fields verbatim (for esports/tennis rows, "home" = the A-side team or player). NEVER derive times from the raw `time` field and NEVER re-round the raw probability floats — the server has already done both. Args: league: One of NBA, NHL, CBB, NFL, MLB, SOCCER, LOL, CS2, TENNIS, WNBA, CFB, GOLF. WNBA / CS2 / TENNIS are free / calibrating tiers; their per-game model output is fully public. NFL / CFB return their most recent slate (offseason as of mid-2026). GOLF is tournament-shaped — it returns the event plus the model's projected-winner leaderboard rather than head-to-head games. date: YYYY-MM-DD. Defaults to today (Eastern time). Returns: Team / esports / tennis leagues: ``{league, date, count, games: [...]}``. GOLF: ``{league, date, event, round, count, projected_winners: [...]}``.
    Connector
  • Return the Olympus Bets Analytics model projection for a specific game. Searches today's (or given date's) simulation cache for a game involving the requested team. Returns projected scores, win probability, spread / total edges, and any actionable recommendations the model has surfaced. Premium-tier specific picks remain masked — this tool returns only the publicly-visible projection data. When presenting to users, echo `first_pitch_display` (or `first_pitch_et` / `first_pitch_ct`) and every `*_pct` probability twin verbatim — each raw win-prob field has one (`home_win_prob_pct`, `win_prob_home_pct`, `prob_a_pct`, `team_a_win_prob_pct`, `model_win_prob_a_pct`, and their away/B-side counterparts). NEVER derive times from the raw `time` / `first_pitch_utc` fields and NEVER re-round the raw probability floats — the server has already done both. Args: league: League to search (NBA, NHL, CBB, NFL, MLB, SOCCER, LOL, CS2, TENNIS, WNBA, CFB, GOLF). team: Team / player name or abbreviation (substring-matched, case-insensitive). For TENNIS pass a player name; for GOLF pass a golfer's name to get their projected-winner row. date: YYYY-MM-DD. Defaults to today (Eastern time).
    Connector