"Methods for Categorizing Images" matching MCP servers:

Minimalist Strava integration for Claude with 7 focused tools for querying athlete stats, activities, zones, and segment analysis.

This server lets Claude, Cursor, or any MCP client read a user's own health and fitness data through 26 read-only tools for activities, sleep, HRV, Body Battery, stress, steps, heart rate, weight, nutrition, and women's health. It connects via the official Personal API and can be self-hosted for free on Vercel.

Exposes Strava training data to Claude for coaching, planning, and analysis via a read-only MCP server with OAuth and Docker support.

Enables MCP clients to query AimHarder for authenticated account context, discover accessible gyms, and select a gym for queries.

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.

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

An MCP server for the Polar AccessLink API. Connect your Polar fitness data to Claude AI - access workouts, sleep analysis, recovery metrics, heart rate data, and more.

MCP server for the Hevy fitness tracking app, enabling management of workouts, routines, exercise templates, folders, and webhooks through AI assistants.

A production-ready MCP server for the Hevy fitness API that exposes 27 tools for reading, writing, and analyzing workout data, enabling LLM-driven personal trainer workflows.

Enables Claude and other MCP apps to query the user's own activity and health data—sleep, HRV, Body Battery, stress, heart rate, steps, and workouts—locally and read-only.

A local, read-only Model Context Protocol server for an athlete's Strava profile and activities, enabling retrieval of profile data, activity lists (with paging and date filters), and detailed activity information via standard input/output for MCP hosts.

Enables seamless interaction with MyWhoosh API for managing workouts, training sessions, and settings via natural language.

Provides local, Keychain-secured access to all 26 Garmin Connect Personal API GET endpoints plus 8 summary tools. Enables users to query sleep, HRV, Body Battery, activities, profile, weight, and other connected health data through their own Personal API key.

Enables AI assistants to read training, sleep, recovery, nutrition, body composition, race and goal data, and with permission write workouts, daily targets, meal plans, logged meals and notes. Also supports checking for updates since the last look.

HYBRD manage your wearables connection, is a system of record for your training plan / completed workouts, and steers LLMs towards giving better fitness coaching

MCP server integrating Foodvisor nutrition API for food search, meal logging, daily summaries, and progress tracking via LLM agents like Claude.

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.

Enables full integration with Strava API v3 for managing activities, athletes, clubs, segments, and routes through MCP-compatible clients like Claude Desktop.

MCP server for read-only access to Xiaomi Mi Fitness shared family health data, enabling queries for family members, health summaries, and historical metrics via ChatGPT.

Enables LLMs and MCP clients to securely access your Garmin Connect health and running data, including daily wellness metrics, activity details, training status, and race predictions, for personalized coaching and analysis.

MCP server that mirrors your Garmin data into a personal database and exposes tools for health summaries, training load, muscle readiness, and race analysis, with optional chat-driven insights via stdio or HTTP.

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

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.

Enables MCP-compatible clients to search foods and manage a personal nutrition diary, saved meals, exercise, weight, favorites, recipes, and monthly summaries via the FatSecret Platform API. It provides 39 tools with confirmation for mutating actions, OAuth 1.0 3-legged authentication, and MCP Streamable HTTP transport.

MCP server for Hevy that fetches live workout data and computes analytics like e1RM, PRs, volume, and consistency, while enabling writes for routines, folders, and body measurements without modifying workout history.

Enables Claude to read a user's Oura Ring data—including sleep, readiness, activity, stress, workouts, heart rate, and personal info—through a self-hosted, read-only connector deployed to the user's own Vercel account.

Unofficial MCP server for Hevy that lets AI assistants design training programs, create routines directly in your Hevy account, and analyze logged workouts.

Enables Claude to query read-only Oura Ring data—including sleep, readiness, activity, heart rate, stress, and device status—through raw collection access and analysis tools for summaries, weekly comparisons, HRV trends, and readiness drivers.

An MCP server that exposes a runner's own training data — computed training load, race-time predictions, and generated plans — as tools an LLM can call for grounded coaching advice.

MCP server for workout-file conversion: convert, validate, and inspect FIT, TCX, ZWO, and Garmin Connect files, with round-trip-safe conversions through the KRD canonical JSON format. Runs locally over stdio via npx -y @kaiord/mcp. Part of the open-source, local-first Kaiord training platform.