"How to create Markdown files locally" matching MCP servers:

Enables ChatGPT and compatible AI clients to query read-only Garmin Connect data—including sleep, HRV, heart rate, Body Battery, wellness metrics, and activities—through a hosted OAuth-backed MCP connection using a personal API key.

An MCP server that converts structured cycling workout specs into MyWhoosh .zwo and Garmin Connect workout files, with tools for validation, description, and rendering. It also includes skills for uploading workouts to both platforms.

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.

Enables an MCP client to read and write a personal Garmin Connect account: activities with per-set strength detail, daily health metrics (sleep, HRV, stress, steps, readiness), planned and completed workouts, and weigh-ins with body composition. It also logs finished strength sessions and body-composition readings as FIT files so they appear in Garmin Connect like natively recorded ones.

Enables LLM clients to read a user's locally-decrypted calisthenics training data and propose plan updates without direct mutations.

Archives Garmin Connect health data locally (steps, HR, sleep, body battery) as JSON, no cloud, and also pulls context data (weather, pollen, air quality). Built-in MCP server (with SQLite cache) exposes the archive for querying via LLM tool calls.

Enables MCP-capable AI apps to query a user's own Garmin sleep, HRV, stress, Body Battery, heart-rate, activity, and body-metric data through Garmin's official Personal API in a read-only, locally run setup.

Connects Claude to your Strava fitness data, enabling natural language queries about your training history such as activities, stats, and routes.

Enables AI assistants like Claude to read a single user's own Strava account through its API: profile and totals, activities with laps, splits, zones and per-second streams, plus segments, routes, gear and clubs. It is strictly read-only, using the user's own Strava API application and OAuth tokens stored locally, and returns model-friendly, context-sized data.

A read-only MCP server that lets AI assistants query a user's own training, recovery, sleep, activity, and wellness data through the official Garmin Connect Personal API. It can run locally or be self-hosted on Cloudflare Workers for access from Claude and other MCP clients.

Enables MCP clients to read a user's own Rouvy activities, including summaries and per-second data for splits, selected time-window analysis, and downsampled streams; optionally exports FIT or CSV files when configured.

Local-first MCP server that reads Apple Health export files (export.xml/zip) and exposes activity, sleep, HRV, and workout data to AI agents, keeping all data on your machine.

Enables local, read-only analysis of running durability from your own FIT files, listing outdoor runs and returning drift, magnitude, onset, and trend indices without GPS coordinates or predictions.

Provides guarded access to the official Hevy fitness API, enabling users to list workouts and routines, search exercise templates, review exercise history, and create routines or workouts with explicit confirmation for writes.

Local MCP server that connects Claude Desktop with Garmin and Apple Health data to read training and recovery, estimate heart rate and pace zones, analyze performance, and create structured workouts.

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.

Enables agents to locally analyze Huawei Health export data, retrieve activity summaries, tracks, samples, and health context, and generate structured report evidence with optional environmental data.

Enables AI agents such as Claude, ChatGPT, and Cursor to list a user's Strava activities and update activity gear through natural language, without requiring a Strava API key.

Read your Samsung Health CSV/ZIP exports — activity, sleep, heart, stress — locally. It is a local-first MCP server that keeps your tokens on your machine.

Enables Claude Desktop and Claude Code to read locally synced Fitbit Air health data — scores, trends, sleep, activity, running and body age — run read-only SQL against it, and keep a journal and coach notes on the user's Mac. It also offers profile edits, a refresh tool, and guided prompts such as morning check-ins, weekly reviews, race planning and score explanations.

An MCP server that locally authenticates with Google Health API v4 and provides read-only access to Fitbit, Pixel Watch, and other health data for AI agents.

A TypeScript server that acts as a bridge to the Strava API, enabling LLMs to access users' activities, routes, segments, and athlete data through natural language interaction.

Trainzilla MCP connects Claude to your Trainzilla coach account, turning your client roster, programming, and habit tracking into something you can manage conversationally. Built for fitness coaches running their practice on Trainzilla, it lets Claude pull up client profiles and metrics, build and review workout and diet plans, create and assign habits, run quick calculations (TDEE, macros, 1RM),

Ask your AI assistant about your Garmin data: sleep, HRV, recovery, training and more. Uses Garmin's official API, so no password sharing and nothing breaks when Garmin changes its login. Run it on your own Cloudflare account to use it on any device, or locally in two minutes.

Analyze iGPSport cycling data with natural language, computing derived training metrics (NP, IF, TSS, CTL, ATL, TSB) locally via MCP.

Enables AI clients to preview, search, read, create, update, schedule, and unschedule Garmin Connect workouts using a local Garmin session, with guarded writes and a limited tool set. Supports running, cycling, cardio, and strength workouts without exposing generic API, filesystem, or shell access.

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.

Enables Claude and other MCP clients to securely read your own body measurements, daily activity, sleep summaries, and paired devices from the official Withings API, with everything running locally.

Exposes an athlete's training data — activities, streams, power curves, wellness records, calendar events, workouts, gear and routes — to MCP clients such as Claude, with 20 read-only tools plus two that can update wellness entries and create calendar events. Responses are downsampled, field-trimmed and credential-stripped so large datasets stay usable within a model's context.

Provides access to Oura Ring health data including sleep, readiness, and resilience metrics through the Oura API, enabling language models to query and analyze personal health information.