"Using mcp-proxy to bridge a remote SSE server to a stdio server" matching MCP servers:

This project implements a Model Context Protocol (MCP) server providing Formula One racing data using the Python FastF1 library. Inspired by an existing TypeScript server, it offers similar F1 data functionalities natively in Python via FastF1.

Enables AI agents to search and analyze Japanese horse-racing data in a PostgreSQL database, including races, entries, odds, jockeys, trainers, pedigrees, training, and predictive metrics. Also provides forecasting knowledge resources and safe read-only custom SQL querying for deeper analysis.

A local, read-only stdio MCP server that bridges Codex to the COROS MCP gateway, enabling sport data queries through an allowlisted set of tools while excluding file and write operations.

Bridges local stdio MCP clients like Codex and OpenCode to Strava's official MCP endpoint, enabling Strava data access via imported OAuth credentials from Claude Code without a developer app.

Enables Claude to query Sleeper's public fantasy football API over Streamable HTTP, covering leagues, rosters, drafts, matchups, player stats, trends, and player search. Roster data keeps IR (reserve) and taxi players distinct and enriched with player names, positions, teams, and statuses.

Enables AI assistants to answer tennis tactical questions using shot-by-shot charted match data, producing game plans, serve and return tendencies, scouting reports, match forecasts, and explanations of why a match turned. Exposes read-only tools for player reports, head-to-head game plans, match breakdowns, and tactical leaderboards, each with confidence margins and links to full pages.

Enables GrokBot users to read their own Strava data from a self-hosted stdio server, querying activities with filters, laps, zones, and streams, viewing athlete profiles and stats, exploring segments and leaderboards, listing routes, exporting GPX/TCX, and analyzing or comparing training. It is read-only, using OAuth tokens stored locally on the user's cloud computer with scopes limited to profile and activity reads.

Provides tools for live sportsbook odds, player props, scores, football xG, historical closing lines, US horse racing entries and results, and prediction-market prices through a hosted endpoint and local stdio proxy.

Enables users to check whether a beach suits a beach day or a surf session today or up to six days ahead, using Open-Meteo weather and marine forecasts scored by deterministic, documented rules. It exposes tools for raw hourly forecast data, suitability scores and verdicts by activity and skill level, and finding the best multi-hour window within a day.

A chess training MCP server that downloads games from Lichess, analyzes moves with Stockfish, detects pattern errors using a compression model, and provides spaced repetition training to improve weaknesses.

Python MCP server that provides comprehensive access to MLB statistics and baseball data through a FastAPI-based interface. Acts as a bridge between AI applications and MLB data sources, enabling seamless integration of baseball statistics, game information, player data, and more.

A private, read-only MCP server that gives local Codex and Claude Desktop sessions access to athletics and wellness data from a Garmin Forerunner 55. It runs locally over stdio, exposes read-only tools for daily health, recovery, performance, and workouts, and caches data in SQLite.

Enables LLMs to accurately convert climbing grades across different rating systems using a data-driven approach.

Gives any MCP client local access to Garmin Connect sleep and nap data, recovery and Body Battery, training readiness and load, running tolerance, VO2 Max, race predictions, gear mileage and running summaries. It runs over stdio or Streamable HTTP and includes a credential-free demo mode with fictional sample data.

Enables AI agents to query real-time and historical Formula 1 data, including Grand Prix meetings, sessions (races, qualifying, practice), drivers, and lap times or telemetry, with support for filtering by year, country, session, and driver. Can be used via the Pipeworx gateway or as a local stdio server.

Enables AI agents to query roughly 4 million powerlifting competition entries from about 64,000 meets worldwide, retrieving a lifter's meet-by-meet history with best squat, bench, deadlift, total and points, the full ordered results of a specific meet, and all-time top lifts filtered by sex, equipment, lift, weight class, federation, age class, tested status or year. Runs keyless either through the hosted gateway URL or as a local stdio server.

Enables Claude, Codex, and GitHub Copilot to answer natural-language questions about WHOOP recovery, sleep, HRV, strain, and workouts using read-only access to personal health history, baselines, trends, and sleep debt. Also rebuilds HYROX and triathlon sessions, assesses race readiness, and serves a local performance dashboard.

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 access to published fantasy basketball and football rankings and player projections through a read-only remote MCP server, with tools for week, season, and player rankings and projections.

Enables remote access to Sleeper fantasy football leagues via an MCP endpoint, providing read-only tools for league snapshots, transactions, traded picks, and computed free agents to any MCP client.

Gives AI assistants read-only access to a user's connected ESPN, Yahoo, and Sleeper fantasy leagues, so they can answer start/sit, waiver, trade, and matchup questions using real roster and league data.

An MCP server that provides access to over 12 years of NFL play-by-play data through a local DuckDB database. It enables users to query player performance, team statistics, and situational efficiency metrics like EPA and WPA using natural language.

Provides read-only access to an Abler account's profile, groups, and sports schedules through MCP tools, including per-child schedule reports and individual event lookups. Uses a portable, reusable session credential so it can run headlessly on a remote machine after a one-time browser sign-in.

Provides 28 MCP tools to query KBO baseball data, including player stats, pitch arsenal, zone charts, usage patterns, and trend reports using a SQLite database.

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.

Enterprise-grade MCP server providing daily cricket updates via FastAPI and SSE transport, integrating with Claude Remote MCP Connector.

Enables querying K League official data (rankings, matches, players) via SQL using natural language, with a pre-built SQLite database.

Provides comprehensive sports intelligence including live scores, standings, schedules, betting odds, news, highlights, and more via SSE transport.

Enables natural language querying of a football knowledge graph via Neo4j, generating Cypher queries and answers using LLMs, and also provides tools to build the graph from text.

A real-time Formula 1 analytics server that lets you ask natural language questions about races, lap times, tyre strategies, pit stops, and more using live data from the OpenF1 API.