This MCP server enables logging workouts in plain language through AI assistants and provides tracking of sessions, programs, records, estimated 1RM, and per-muscle load, with coaching informed by the user's logged data.
Enables AI assistants to access and analyze Polar device health data, including exercises, heart rate, sleep, and recovery metrics, by preprocessing raw sensor data into compact summaries to avoid context window overload.
Enables AI assistants to query a user's own Garmin Connect training, health, and recovery history through Garmin's official Personal API, backed by a local cache and built-in analysis tools.
Enables MCP clients to read a user's own Garmin data—including activities, sleep, HRV, Body Battery, stress, steps, heart rate, weight, and more—through 26 read-only tools backed by Garmin's Personal API.
Turns any AI assistant into a physiological AI running coach by abstracting fitness APIs and exposing 70+ structured analytical MCP tools based on endurance models.
Enables answering questions about your disc golf rounds, courses, hole-by-hole scores and scoring trends, plus practice-throw speed, distance, spin and angle, read entirely from your own CSV exports with no credentials or network access.
Enables Claude to answer natural language questions about your Apple Health data by analyzing local CSV exports, supporting metrics like steps, heart rate, sleep, and more.
Enables Claude to answer trail and ultra running questions from a local DuckDB warehouse built from Garmin FIT files, with 29 parameterised tools that compute running-only pace by grade, matched-terrain heart rate drift, segment comparisons and training load, each result stating its filters and exclusions.
Enables users to search and retrieve fitness exercise information from the Api Ninjas database. It supports filtering by exercise name, target muscle, type, and difficulty level.
Lets Claude Code, Codex, and other AI assistants query locally collected Apple Health data, build weekly reports, check sync status, and log workouts or meals by hand.
Enables local, read-only access to Oura API v2 data, returning pre-shaped physiology such as sleep, chronotype, temperature shifts, and baseline drift for interpretation by AI clients.
Provides personalized recommendations for optimal outdoor exercise times by integrating weather data, Garmin Connect training schedules, and user performance metrics.
An MCP server specialized in managing and querying gym exercises through a centralized database. It enables users to search for workouts by name or muscle group and retrieve detailed information including sets, repetitions, and rest intervals.
Enables AI apps such as Claude and ChatGPT to read an endurance athlete's watch data synced via Intervals.icu and turn it into history-checked race predictions. Access is read-only and OAuth 2.1-secured, with every value labelled by source and predictions returned as ranges rather than single times.
Exposes 66 OAuth-scoped tools over Streamable HTTP that let MCP clients read and log nutrition, food, water, recipe, diet-plan, training, and progress data by calling the Fitaily REST API. Access is limited to 15-minute HS256 tokens with per-domain read/write scopes, and every tool returns structured JSON alongside text output.
MCP server that reads local SQLite database populated by a Playwright scraper to provide daily summary, food log, weight history, and water log from LoseIt.
Enables private conversations about recovery, sleep, and recorded training by exposing official API data to MCP assistants, including period comparisons and daily evidence with explicit units and missing values.
Supplements the official Strava MCP connector by adding write access, segments, routes, photos, derived analysis, and interactive visualizations, enabling activity management, segment exploration, route export, and training analysis through MCP.
Enables users to ask ChatGPT or Claude where a runner or cyclist is in a live race, how the race is going, and what the weather along the course will be, returning live maps and 3D route flyovers inline in the chat. Also surfaces cycling tour day-by-day routes, GPX links and organiser notes, all read-only and free.
Enables AI agents to query personal health data collected by any wearable or phone fitness app through Android Health Connect or Apple Health, exposing read-only tools for metrics like heart rate, sleep stages, VO2 max, and body composition. It can run locally over USB with nothing stored, or be self-hosted on Cloudflare Workers with D1 to retain history beyond Health Connect's 30-day limit.
Enables Claude to read intervals.icu training data — wellness metrics, completed activities with per-lap and time-series detail, and planned events with planned-versus-completed reconciliation — and to create, update, or delete planned run and bike workouts on the intervals.icu calendar, which syncs to Garmin Connect. Writes are guarded by dry-run defaults and explicit approval.
Enables searching a catalogue of over 1,400 video-backed exercises by text, muscle group, equipment and difficulty, fetching full details for any exercise, and generating structured workouts or multi-week periodized programs. It also exposes the muscle-group and exercise-type vocabularies with their counts, returning the upstream API's JSON unchanged.
Enables AI assistants such as Claude, ChatGPT and Gemini to read wearable health data — daily activity, sleep stages, heart rate, SpO2, HRV, workouts, weight and nutrition — through a self-hosted, OAuth-protected Cloudflare Worker endpoint. It also lets users log weight, body fat, water, food, exercises, mood and symptoms by voice or chat, while leaving sensor-recorded data read-only.
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.