Categories › Knowledge & Everyday › Research, papers & reference data
Expert soccer predictions from TipMaster, since 1997: crowd groups, accuracy and model benchmark.
Remote server: your requests and data go to tipmaster.net. Claude Code: claude mcp add --transport http tipmaster-expert-soccer-predictions https://tipmaster.net/api/agent/mcp · Claude app: Settings → Connectors → Add custom connector.
The tools this server listed when we connected to it, in its own words.
get_model_comparison — Experimental football outcome model trained on stored Sportmonks results. Returns a chronological holdout benchmark and comparisons with Natget_match_prediction — The TipMaster expert prediction for one football (soccer) match, found by team names ("Bayern vs Freiburg", one team name also works) or by find_matches — Football (soccer) matches with TipMaster expert predictions, filtered by team, competition (e.g. "Bundesliga", "Premier League", "LaLiga"), get_accuracy — How often TipMaster players got football (soccer) matches right, per group (Top 20%, Top 25%, All players): majorityCorrect is the share of get_expert_picks — The current TipMaster Classic round: 25 real football (soccer) matches per game (btm = Bundesliga TipMaster, tmi = TipMaster International),list_matches — Every published football (soccer) match (teams, kickoff, entry deadline, status, result) without the prediction fields.get_consensus — Full prediction records: the crowd’s home/draw/away shares, the top 3 exact scores and most likely score (National), the Top 20% / Top 25% /Not tested by KitScout yet. When our harness runs it, pros, cons and the tasks we tried appear here, with the date and evidence.