"Reliable sources for use in training language models" matching MCP servers:

Provides comprehensive access to Strava API for marathon training and race analysis, enabling language models to query athlete data, analyze training patterns, track performance metrics, monitor heart rate zones, and detect injury risks.

A stateless MCP server that exposes tools for evidence-based strength training, including classical powerlifting programs and fatigue management.

Running-first MCP server for COROS that allows authoring, editing, and scheduling running workouts, plus accessing sleep, HRV, training load, and activity exports.

Provides personalized recommendations for optimal outdoor exercise times by integrating weather data, Garmin Connect training schedules, and user performance metrics.

Enables AI clients to query and analyze Huawei Health data, including training records, sleep, heart rate, and athletic performance, through 14 MCP tools without third-party servers.

Connect Claude to XERT cycling analytics - access fitness signature (FTP, LTP, HIE), training load, workouts, and activities.

MCP server for TrainingPeaks that reads workouts, fitness metrics (CTL/ATL/TSB), and health data, and creates/updates/deletes planned workouts. Enables AI-powered training plan management and automated adjustment based on performance, fatigue, and injury.

MCP server for tracking nutrition meals and workouts, integrating with claude.ai to manage food logs, macros, exercise catalogs, and generate daily/weekly summaries.

Connects WHOOP fitness data to Poke AI assistant, enabling natural language queries for recovery scores, sleep analysis, strain tracking, and healthspan metrics.

Exposes over 90 Garmin Connect tools for tracking activities, health metrics, and training data through the Model Context Protocol. It is optimized for Poke compatibility and supports deployment to Render via HTTP.

Enables AI agents like Claude Desktop, Cursor, and VS Code to connect directly to COLMI R02/R03 and compatible smart rings over local Bluetooth LE, exposing tools for ring scanning, battery and firmware status, activity and sleep/recovery insights, real-time heart rate and SpO2 vitals, 3-axis motion sampling, clock sync, and physical LED blinking. Runs fully locally with no vendor cloud, accounts, or subscriptions.

Connects Claude to your Strava account for analyzing training, predicting race times, and generating periodized training plans via natural language.

Exposes Whoop fitness data (recovery, sleep, strain, workouts) to Claude for use as a daily training coach, enabling natural language queries about your health metrics and training readiness.

Connects to Intervals.icu to let users query training data, create workouts, manage calendar events, and coach athletes through natural language in Claude Desktop.

Enables Claude to act as a personal health coach by connecting to Garmin wearable data and Notion workspace for automated calorie tracking, photo food logging, and coaching insights.

Exposes Zwift training history stored in a local SQLite database to MCP clients and a REST API, enabling queries for activities, power curves, race results, and training load.

Enables users to describe workouts in plain English and have them created as structured Garmin Connect workouts with pace, HR, power, cadence targets, and repeat blocks. Also provides full workout lifecycle management including listing, updating, deleting, and scheduling to the calendar.

Provides local MCP tools to query your own Xiaomi Mi Fitness health data (sleep, workouts, heart rate, etc.) stored in a local SQLite database, enabling AI assistants to access personal health records without exposing credentials.

MCP server that lets you ask questions about your Garmin training history in plain language. It ingests FIT files into DuckDB locally and exposes typed tools for analyzing activities, streams, and summaries.

Ask your Oura Ring about sleep, readiness, activity, stress and heart rate in ChatGPT or Claude, in any language. Read-only, 10 task-oriented tools; runs in a sandbox demo mode with no credentials.