"AWS instance metadata service endpoint URL" matching MCP servers:

Enables Claude to create, list, inspect, and delete custom rowing workouts in the EXR indoor rowing app, converting intervals.icu workout documents (power, cadence, ramps, repeats) into EXR's simpler timed or distance-based blocks with dates in the titles. Runs as an AWS Lambda-hosted claude.ai custom connector with per-user OAuth sign-in, so several people can share one deployment while each only sees their own EXR workouts.

Enables local access to Fitbit data via the Google Health API, including status/device metadata, bounded raw reads, daily activity rollups, and reviewed meal or water writes with previews, explicit commits, read-back, and duplicate protection.

Enables Claude, Cursor, or any MCP client to query your own recovery scores, sleep, strain cycles, workouts, profile, and body measurements through every WHOOP API v2 read endpoint. Tools return records exactly as WHOOP sends them, with paging and date-range filtering, and refresh tokens automatically after a one-time login.

Enables AI assistants to read, log, edit, and analyze workouts, routines, body weight, media, and personal records on a self-hosted openGym instance through its own HTTP API. Writes are scoped to requested changes with automatic backups and conflict detection, and tools are grouped into read, write, delete, and admin permission tiers.

Provides AI agents with access to Hevy workout data, allowing them to manage workouts, routines, exercises, and body measurements through a Dockerized SSE endpoint.

Official JustGains MCP server: lets AI agents build and save workouts, read training history and progress, search exercises, plan routes, and log meals and bodyweight in a JustGains account. A TypeScript stdio server on the MCP SDK with OAuth sign-in, serving the same tools as the hosted JustGains endpoint.

Enables Claude to access MyFitnessPal diary data through a stateless OAuth MCP endpoint deployed on Vercel.

Enables AI assistants to access and query personal health data from Garmin Connect and Technogym mywellness through a unified MCP endpoint.

Enables querying a Tonal fitness account for workout history with per-set weights, muscle readiness, strength scores, and lifetime stats through a remote MCP endpoint.

Enables self-hosted, read-only access to your own Oura account from an agent, exposing catalog and query tools that return native Oura API v2 JSON with pagination and provenance. Runs one isolated container per person with no hosted service or shared credentials.

Enables MCP hosts to query and analyze a local Samsung Health mirror, with tools for status, metadata, inventory, daily summaries, and aggregate analyses, plus optional bounded access to raw records and cloud synchronization.

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 agents to access local physiological context—Libre glucose, heart-rate, and watch history—with provenance and freshness metadata, so they can recognize when a user seems unusually off.

A unified MCP server that connects AI assistants to multiple fitness services (Hevy, Strava, Cronometer, Intervals.icu) through a single secure endpoint, enabling workout, nutrition, and activity data access.

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 AI assistants to query a user's Huawei Health data read-only, covering workouts and detailed activity metrics, sleep, resting heart rate, HRV, athletic performance and personal bests. Tokens are passed per request in HTTP headers, so no credentials are stored and multiple users can be served from one stateless instance.

Enables uploading FIT/TCX activity files to COROS Training Hub via unofficial APIs, including support for AWS S3 and Aliyun OSS regions, and manages import jobs and activity verification.

A remote MCP server that lets LLM clients read and change training data in a self-hosted openGym instance over HTTPS using the user's own openGym token. It covers routines, weekly scheduling, workout logging and editing, body weight and goals, plus custom exercises and plan imports, with conflict-safe conditional writes.

Enables a chat assistant to log what you ate — text, voice notes, recipe portions, or label/plate photos — by resolving foods against the Bundeslebensmittelschlüssel, Open Food Facts, or Tandoor recipe nutrition and storing copy-on-write nutrient entries in a local SQLite log. It serves these tools over stateless streamable HTTP MCP, grouping entries into meals and summarizing days, weeks, and training/body-weight data when an OpenGym endpoint is configured.

Enables agents to track workouts, body metrics, and training stats for registered users through a JSON-RPC MCP endpoint, with scoped agent permissions and a web dashboard.