"Créer des systèmes de prompt pour les modèles de langage (LLM)" matching MCP servers:

MCP chess runtime that lets LLMs play, analyze, and adapt strength by exposing Stockfish, human move likelihood (Maia3), and Lichess statistics, with the LLM handling strategy and the server handling computation.

A Python-based MCP server that extracts football match data from multiple global sources like ESPN and BBC Sport using intelligent web scraping. It enables AI assistants to retrieve scheduled matches, real-time scores, and broadcasting details with advanced filtering for high-profile games.

Enables fetching sports odds from The Odds API and removing bookmaker margin (vig) to compute fair probabilities, with tools for today's MLB games, processed odds, and consensus lines.

GB & Irish horse racing signals for AI agents: per-runner AI scores, de-overrounded fair prices, draw-bias aggregates, trainer-jockey strike rates, and Racing Alpha's database-frozen public tips ledger (losses included).

Enables users to estimate football match probabilities using a Dixon-Coles model, compare them to de-vigged bookmaker odds, and identify value bets from Claude Desktop.

An MCP server that lets an LLM query a DuckDB warehouse of EuroLeague and EuroCup basketball data in natural language, offering tools for player and team stats, shot charts, boxscores, and fantasy draft analysis without contacting upstream APIs.

Enables LLM clients to plan Swiss mountain outings by public transport, providing computed facts such as launch sites, flyability probabilities, and train connections.

MCP server that connects Claude or any MCP-capable LLM to your Garmin golf data, enabling natural-language queries on rounds, shots, strokes gained, club distances, course intel, and health-performance correlations from a private local DuckDB cache.

Enables MCP-compatible LLM clients to access live NBA data, including stats, standings, rosters, scores, and box scores via callable tools.

Enables querying FotMob football data including matches, match details, teams, leagues, players, and search through MCP-compatible LLM clients.

MCP server for the FootballStack football data API. Gives LLM clients and AI agents (Claude, Cursor) access to real football data — fixtures, standings, lineups, live events, shot-level xG with pitch coordinates, and model-derived fair odds.

Enables LLM-powered race engineers to compute Formula 1 pit-stop strategies from real session data, including tire degradation modeling, optimal pit windows, undercut/overcut simulation, and finish-position projection.

Enables an LLM agent to reason about live British baseball league data through typed, read-only tools for scouting reports, matchups, lineup prediction, running-game tendencies, and playoff projection, with grounded caveats and sample sizes.

Enables interaction with Formula 1 data through LLM interfaces like Claude. Provides access to F1 information including circuits, constructors, drivers, grand prix, manufacturers, races, and seasons.

Analyzes pommel horse gymnastics routines using a categorical aesthetics framework that evaluates element groups, spatial patterns, temporal qualities, and form with 85% deterministic taxonomy and 15% LLM synthesis.

An MCP server that exposes Stockfish chess analysis to LLM chat clients, enabling move analysis, game review, and explanation of engine choices.