MCP App Store
by KeenEthics
Sportily icon

Sportily MCP Server for ChatGPT

By Oglofus

Overview

Sportily helps users discover horse-racing cards, SmartPicks, Value Finder candidates, Race Lens matches, runner profiles, race context, post-race results, and their personal My Picks tracking data through ChatGPT. The app supports access-gated workflows for finding races and horses, analysing race cards, comparing runners, backtesting saved filters, and saving or reviewing private tracked picks.

How to connect

  1. ChatGPT: Open the Sportily listing in the ChatGPT app directory and choose Connect. ChatGPT listing Sportily exposes 66 tools here.

Tools

add_basketball_pick

ChatGPT
Only on explicit user request: log one pre-game match-winner prediction in your private Sportily prediction log. Bind forecastId from the displayed forecast to preserve identity/probability.

add_to_my_picks

ChatGPT
Save a horse to the user's personal My Picks tracker so its result and ROI are tracked over time. Provide the Sportily raceId and horseId (from search_races / get_race_card / discover_* tools). The pick is auto-tagged with the source (claude or chatgpt) so the user can filter by who suggested it. Idempotent — saving the same runner twice will not duplicate it. Use only when the user explicitly asks to save, track, or add a pick.

analyze_my_picks

ChatGPT
Analyse the user's My Picks track record: overall strike rate, stake-weighted ROI, beat-SP (closing-line value), max drawdown and win/lose streaks, plus a performance breakdown grouped by a chosen dimension (going, course, country, distance, class, type, or tag) and plain-language best/weakest insights. Use when the user wants to understand patterns in their picks — e.g. 'how do my picks do on soft going' or 'where am I losing money'.

backtest_race_lens

ChatGPT
Backtest one of the authenticated user's saved Race Lens filters, or a draft filterAst, over historical completed races. Race Lens model predicates use the base price-agnostic race model, not SmartPicks or Value Finder tipster percentages. Capped at 60 days for MCP (see the returned days / maxBacktestDays). Note: get_saved_lenses_summary reports metrics over each lens's own original lookback (which can be longer than 60 days), so its numbers will not exactly match this tool's — compare lenses using results computed by this tool over the same days. Returns performance, sample selections, and concrete filterAst improvement ideas to try next.

cancel_football_lens_run

ChatGPT
Cancel one of the member’s queued or running MatchLens jobs only on explicit user request. Completed jobs remain unchanged; does not disable future tracking.

compare_runners

ChatGPT
Use for horse-vs-horse comparison in a Sportily race. Returns focused evidence for selected runners; treat model percentages as directional analytics signals, not absolute truth.

create_football_lens

ChatGPT
Save a new personal MatchLens only after the user explicitly requests it. Provide a complete definition from the templates/catalogue in get_football_lenses. Saving does not start tracking or place bets.

delete_basketball_lens

ChatGPT
Only on explicit user request: delete your saved filter.

delete_basketball_pick

ChatGPT
Only on explicit user request: remove one of your recorded picks.

delete_football_lens

ChatGPT
Only on the user’s explicit request, archive one owned MatchLens using the website’s reversible removal workflow. Stops tracking, cancels forward runs and revokes its share link; retains version history and results. Use restore_football_lens to restore it.

delete_football_pick

ChatGPT
Remove one of the signed-in member’s picks only after an explicit request to delete that pick. Requires a pick ID from get_football_picks; does not cancel a bookmaker bet.

delete_tennis_lens

ChatGPT
Soft-delete an owned Lens only on an explicit request. Supply its current version from list_tennis_lenses or get_tennis_lens; stale or missing Lenses are rejected.

delete_tennis_pick

ChatGPT
Delete the user’s own unstarted tennis pick only on an explicit request. Supply its current version from list_tennis_picks; started picks cannot be deleted.

discover_racing_picks

ChatGPT
Use by default when a user asks for horse-racing picks, good horses, value, SmartPicks, Value Finder, or Sportily analytics candidates. For a specific request, drill into that pick immediately. For a broad scan, score the candidates first and analyse the top 2-3 races in parallel. The goal is to test whether model% is realistic, not just restate it. Only return a bare list if the user explicitly asks for a list.

find_basketball_games

ChatGPT
Stored NBA schedules/results, grouped by America/New_York date; maximum 31 days. Experimental win probabilities are 0–1. This is not a live feed or bookmaker odds.

find_basketball_players

ChatGPT
Search stored player names and return IDs for player profiles. Case-insensitive literal name search, at most 100 results; no live roster feed.

find_basketball_teams

ChatGPT
Search stored team names and get IDs for profiles.

find_football_matches

ChatGPT
Stored football fixtures and results by UK calendar day (at most 31 days; default today and the next 6). Returns fixture IDs for get_football_match, team IDs for get_football_team and league IDs for get_football_table. Stored data, not a live feed.

find_football_players

ChatGPT
Search player names in Sportily’s bounded recent stored lineup catalogue. Returns provider player IDs for get_football_player. Coverage is incomplete and past lineup membership does not imply future availability.

find_horses

ChatGPT
Use by default when a horse-racing user names a horse, asks about a runner, or needs Sportily runner matching. Finds runners by partial horse name, or lists runners for a date so the MCP client can match a horse.

find_races

ChatGPT
Use by default when a user asks what horse races are on, asks for a course without a race id, or needs Sportily race ids. Lists racecourses and race ids for a date.

find_tennis_events

ChatGPT
Find stored tournament editions with matches in a London calendar-day range of at most 31 days. Includes event IDs, progress, remaining contenders and known finals. Results are stored coverage, not a complete tournament calendar.

find_tennis_matches

ChatGPT
Stored ATP/WTA singles fixtures and results by London calendar day (maximum 31 days). Prices include capture time and historical/prospective provenance. No live feed.

find_tennis_players

ChatGPT
Search stored player names; returns internal IDs for player and head-to-head tools.

get_basketball_game

ChatGPT
Stored game, ordered teams, box statistics, prior games, H2H and experimental forecast. Adds extras (roles and previous starts) and scheduled-game pregame rest, season strengths and last appearances; these are not confirmed lineups. Box statistics from this game are post-game information. Optional panel failures return null panels and researchWarnings while preserving the base game. No live feed.

get_basketball_player

ChatGPT
Stored game-by-game player box statistics and team history, plus a view with full-history season aggregates, recent form, notable nights and coverage exclusions. Both the existing games list and view.log return at most 100 recent games; view.logTotal and view.logTruncated describe the full log. Season aggregates use all stored completed games. Optional view failures preserve the base profile and return researchWarnings.

get_basketball_standings

ChatGPT
East/West standings calculated from stored completed regular-season games, with records, ranks and coverage. Optional season is the four-digit start year; defaults or falls back to the latest season with completed games. Inspect the returned season and fallbackFrom. Null means no completed season is stored; this is not a live or official standings feed.

get_basketball_team

ChatGPT
Stored games and observed players, plus a season view with records, scoring averages, quarter lines and averages, coverage caveats, upcoming games and player season averages. Optional season is the four-digit start year; unavailable seasons fall back to the latest played season. Player list is not a confirmed current roster. Optional season-view failures preserve the base profile and return researchWarnings.

get_external_race_context

ChatGPT
Fetch validated industry context for a Sportily race. Call automatically after get_race_card when externalResearchTargets are available. Returns status and extracted facts — fold insights into analysis without naming the source.

get_football_lens

ChatGPT
Read one owned lens, up to 20 version summaries, 25 recent runs, and up to 100 tracked selections/results with truncation flags and performance. A requested version selects its historical selections; selected contains the current editable definition. No scan is started.

get_football_lens_run

ChatGPT
Read an owned run’s status and results without starting or retrying it. Page is zero-based, with up to 200 evaluations per page and evaluationTotal/evaluationOffset for navigation. Runs may still be queued or running.

get_football_lenses

ChatGPT
List the member’s saved MatchLenses (default 20, maximum 100), alerts, valid rule catalogue, starter templates and up to 100 names per stored reference category. Returns totals for truncated lists; use find_football_players for player search. Start with a template to construct a valid definition. No scan is started.

get_football_match

ChatGPT
One stored match: teams, kick-off, table places, recent form, head-to-head, team news, Sportily’s experimental model (probabilities 0–1, made before kick-off), the stored market view (bookmaker margins removed, averaged — a record, not a live price) and, once played, the goals and who led for how long. Model and market are listed side by side; never present their difference as an edge or a tip.

get_football_picks

ChatGPT
List only the signed-in member’s private football tracker entries, newest first; optionally filter to a fixture.

get_football_player

ChatGPT
One player’s stored appearances, performance, team and availability evidence. Use the numeric provider player ID from find_football_players. Stored observations are not a live availability feed.

get_football_table

ChatGPT
A competition’s table counted from Sportily’s stored results for one season (3 points a win, 1 a draw; matches not collected are missing, so it can differ from the official table). Defaults to the newest season with a played match.

get_football_team

ChatGPT
A team’s season in one competition from Sportily’s stored matches: place and points in Sportily’s table of stored results (not the official table), home/away records, goals by 15-minute window, rates with their sample sizes (clean sheets, both scored, 3+ goals), where it ranks in the league on each metric, its next fixtures and recent results. Team IDs are the provider team IDs from find_football_matches.

get_horse_profile

ChatGPT
Use after finding a Sportily horse id when a horse-racing user asks for an opinion, profile, form view, or analysis of a named horse. Fetches career stats, upcoming races, and recent runs; open the race card before a race verdict.

get_race_card

ChatGPT
Use by default when the user asks to analyse a horse race, Sportily race, runner, racecard, or named horse in a specific race. Fetches a pre-race analytics payload with race, runner, model, market price, stats, past-performance, response-shape, and external-research guidance. Target-race result fields are intentionally omitted so historical analysis can be run blind.

get_race_results

ChatGPT
Use when the user asks who won, what happened, or wants explicit result data for a Sportily race. This is the post-race companion to get_race_card and exposes outcome fields intentionally hidden from the analysis payload.

get_saved_lenses_summary

ChatGPT
List the authenticated user's saved Sportily Race Lens filters with compact backtest metrics and lens ids. Step 1 of the lens flow: use this before get_upcoming_lens_matches (to run lenses on upcoming races) or backtest_race_lens (to re-test over history) when the user wants to choose a specific saved lens, system, filter, or angle. Each lens's backtest metrics use its own stored lookback (backtest.days), which may exceed the 60-day MCP backtest cap.

get_tennis_event

ChatGPT
Read a stored tournament edition, up to 400 matches, seeds, other edition IDs and captured main draw with byes and observation time when available. Surface ratings are current research, not historical pre-match features. A missing draw is null, never a fabricated bracket.

get_tennis_head_to_head

ChatGPT
Stored meetings, including separate retirement and walkover statuses. Without surface returns the existing meetings array. Supply surface for {matches, player1, player2, surface, view}, including a hypothetical current matchup and 52-week serve/return profiles on that surface. This is the stored corpus, not a claim of complete career coverage; hypothetical probabilities are not a forecast for a scheduled match.

get_tennis_lens

ChatGPT
Read one owned Lens, its versions, run ledger and recorded forward selections with audited settlement.

get_tennis_match

ChatGPT
Stored match, pre-match form context, statistics, prices, H2H, derived research story and captured market/model chance history. Historical prices are retrospective, not evidence of an obtainable pre-match price. Forecast probabilities are 0–1, not percentages. Includes current result when known. No provider or model calls.

get_tennis_player

ChatGPT
Player profile, stored ranking, surface records, serve/return counts and recent matches. Current profile aggregates must not be used as historical pre-match features.

get_tennis_rankings

ChatGPT
Latest captured ATP or WTA rankings, with observation time.

get_upcoming_lens_matches

ChatGPT
Run the authenticated user's saved Sportily Race Lens filters against upcoming races in the next 24 hours. Use when the user asks for their Race Lens results, saved-lens matches, custom systems, filters, angles, or upcoming runners found by their lenses. Race Lens model fields use the base price-agnostic race model and can differ from SmartPicks or Value Finder tipster percentages. User-specific: only the connected user's saved lenses are considered. Step 2 of the lens flow — call get_saved_lenses_summary first if you need lens ids or want the user to choose specific lenses.

list_basketball_lenses

ChatGPT
Read your saved NBA probability filters.

list_basketball_picks

ChatGPT
Your logged NBA predictions and how they turned out, from your private Sportily prediction log. Any price or weighting shown is what you entered manually.

list_my_picks

ChatGPT
Return the user's saved My Picks with live result and stake-weighted ROI for each, plus headline performance (strike rate, ROI points, beat-SP rate, drawdown, streaks). Use when the user asks what they have saved, how their picks are doing, or for their track record.

list_race_lens_filters

ChatGPT
List the available Sportily Race Lens filter fields, operators, value types, and example predicates, plus the filterAst shape and rules. Use this when helping a user build or edit a lens. Model fields in this catalog use the base price-agnostic race model, not SmartPicks or Value Finder tipster percentages. Build flow: call this for the catalog, then backtest_race_lens with a draft filterAst to test the idea over history before saving. Note: a filterAst is a flat list of AND-ed predicates — there is no nested OR.

list_tennis_lenses

ChatGPT
Read the connected user’s private saved tennis research rules and versions.

list_tennis_picks

ChatGPT
Read the connected user’s private tennis prediction log: the player predicted for each match, notes and how each prediction turned out.

list_tennis_tournaments

ChatGPT
Discover enabled stored ATP/WTA tournaments, their internal IDs and countries.

preview_basketball_lens

ChatGPT
Filter upcoming published forecasts. Returns frozen game/side/forecast identities. Preview does not record picks and is not a historical backtest.

preview_football_lens

ChatGPT
After the user asks to preview football rules, scan up to 500 stored upcoming fixtures (at most 5,000 candidates) within the next 14 UK calendar days. Returns the first 100 evaluations with totals/truncation flags. Does not save a lens, pick or tracked selection; takes a temporary concurrency lease. Use definitions/templates from get_football_lenses. Quotes are stored, not live; incomplete and unknown evidence must be reported.

record_basketball_lens_picks

ChatGPT
Only on explicit user request: atomically record the exact game/side/forecast IDs from a preview. Changed forecasts require a new preview. Never places bets.

remove_from_my_picks

ChatGPT
Remove a previously saved horse from the user's My Picks tracker, identified by raceId and horseId. Use only when the user explicitly asks to remove or delete a saved pick.

restore_football_lens

ChatGPT
Restore an archived personal MatchLens only on explicit user request. Tracking stays disabled until the user separately requests it.

run_football_lens

ChatGPT
Only after an explicit request, queue a forward scan (next 14 days) or historical test (up to 366 days, ending before today) of an owned, unarchived lens. Uses stored evidence only. Returns a queued run; read its status with get_football_lens_run. Historical unsupported fields are rejected; reconstructed results are not forward performance.

save_basketball_lens

ChatGPT
Only on explicit user request: save a named NBA filter. Does not automatically track selections.

search_races

ChatGPT
Use by default for horse-racing race lookup requests, including races, racecards, runners at a course, or requests that say "on Sportily". Finds Sportily race cards by date, course, and region.

set_football_lens_tracking

ChatGPT
Only on an explicit user request, enable or disable automatic forward tracking of an owned lens. Enabling queues an immediate stored-data scan; disabling cancels forward runs. Restore archived lenses before enabling. Existing in-app Lens alert preferences continue to apply; this does not place bets.

update_basketball_pick

ChatGPT
Only on explicit user request: replace an owned prediction log entry’s notes and its permitted pre-game price/weighting. Omitted price/weighting remain unchanged; null clears them. Price and weighting lock at game start. Updates the Sportily prediction log only.

update_football_lens

ChatGPT
Save a new version of an owned MatchLens only on explicit user request. expectedVersion must equal the current version from get_football_lens; stale edits are rejected. Replaces name and definition, preserves omitted description/folder/alerts, cancels obsolete runs, and schedules a scan if tracking is enabled.

Capabilities

Writes

Example Prompts

Click any prompt to copy it.

Similar Apps

Listed on MCP App Store

Listed on MCP App Store

Add this badge to your site or README. It links to this page.

HTML

<a href="https://mcp-app-store.keenethics-labs.com/app/sportily"><img src="https://mcp-app-store.keenethics-labs.com/badges/listed-on-mcp-app-store.svg" alt="Listed on MCP App Store" width="220" height="44"></a>

Markdown

[![Listed on MCP App Store](https://mcp-app-store.keenethics-labs.com/badges/listed-on-mcp-app-store.svg)](https://mcp-app-store.keenethics-labs.com/app/sportily)