MCP server to read daily activity, sleep, heart rate, and body metrics from Google Health API, allowing AI assistants like Claude to access your health data. Optionally syncs health metrics to an Obsidian vault.
Enables AI agents to securely read and analyze your Google Health data from Fitbit, Pixel Watch, and Health Connect, providing baseline-aware insights, readiness scores, trends, and anomalies while keeping data local and read-only.
Enables AI assistants to query read-only Fitbit and Pixel Watch health data through the Google Health API, including sleep, activity, heart rate, workouts, and profile information.
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.
Enables connecting your own Google Health account to an MCP client through local OAuth, exposing 17 read-only tools for metric discovery, daily and recent summaries, trends, sleep, activity, recovery, body metrics and data quality. All access is observation-only, with request bounds and no create, update or delete capabilities.
Enables AI agents to access, query, and manage Google Health data, including all 47 Fitbit and Pixel Watch data types, paired devices, profile and settings, TCX exports, and data point writes via the Google Health API.
Enables Gemini to query a user's Google Health API v4 data—such as steps, sleep, heart rate, HRV, and exercises—through read-only tools over Streamable HTTP, self-hosted on Cloud Run with Firestore.
Enables reading personal activity, sleep, and health measurements, comparing weekly or monthly trends, and optionally saving food, water, mood, symptom, and menstrual-period records to Google Health through a self-hosted, owner-only deployment.
Self-hosted multi-user Google Health OAuth broker and read-only Agent API with remote MCP support. Enables users to connect their Google account and grant agents secure access to activity, sleep, heart, HRV, SpO2, and other health metrics via revocable per-token authentication.
A remote MCP server that gives MCP clients read-only, OAuth-authenticated access to Google Health API data such as activity, sleep, heart, body, nutrition and ECG records. It exposes tools for profiles, paired devices, data points, daily summaries and time-window rollups, and is deployed on Cloudflare Workers.
Enables AI apps to query a user's Google Health data—such as sleep, heart rate, HRV, activity, and paired devices—through read-only tools deployed privately in the user's own Firebase project.
Enables interaction with the Google Health API v4 using a user's OAuth grant, exposing tools for profiles, settings, paired devices, raw data points, reconciliation, rollups, and exercise export.
Read-only MCP access to Fitbit-synced health data through Google Health API v4. Provides tools for metrics, summaries, trends, and data quality without write or arbitrary HTTP operations.
An MCP server that connects AI clients to the Google Health API, enabling natural language queries about health and fitness data such as steps, sleep, heart rate, and exercise sessions.
Lets a single user read a bounded set of their own Google Health data from ChatGPT conversations through a private MCP connection, exposing four read-only tools for rollups, reconciled records, and irregular-rhythm notification history.
Enables AI assistants to read Fitbit/Google Health data (steps, sleep, heart rate, SpO2, workouts) and log weight, food, water, and exercises via natural language, self-hosted on Cloudflare Workers.
Gives Claude read access to wearable health data from Fitbit or Wear OS devices via the Google Health API, exposing tools for metrics like steps, heart rate, sleep, and workouts, plus a computed recovery score.
MCP server for the Google Health API: heart rate, activity, sleep, SpO2, HRV, ECG and irregular-rhythm notifications, read into a local SQLite cache for fast offline queries and trend analysis. OAuth 2.0 with automatic token refresh, incremental sync, a cache-only offline mode, and a doctor command that diagnoses a setup without spending quota.
Enables AI assistants to read and analyze Google Fit exported data (activities, daily metrics, workouts, sleep) from Google Takeout, providing tools for queries, resources, and coaching prompts.
Ask Claude, Codex or another AI assistant about your Garmin training, and get a training dashboard, also inside the chat. Official Personal API, read-only, nothing to install.
Daash connects Garmin Connect to ChatGPT and Claude. Your assistant reads your runs, splits, sleep, HRV, Body Battery and recovery, and writes structured workouts and whole training plans to your Garmin calendar, so they're on your watch at the next sync. Free, hosted, open source. Works on free Claude.
Enables an LLM client to query workout logbook data stored in Google Sheets and retrieve requested training progress, including weight lifted, sets, and repetitions.
Ask your AI assistant about your Garmin data: sleep, HRV, recovery, training, km splits and more. Uses Garmin's official Personal API: no password, read-only, and nothing breaks when Garmin changes its login. Install in Claude Desktop with one click, run locally with npx -y garmin-mcp, or self-host on Cloudflare for phone and web apps.
Enables AI assistants to answer questions about your own Fitbit or Pixel Watch data — sleep, steps, heart rate, workouts and GPS routes — through a private, read-only server deployed on your own Vercel account. Supports daily summaries, multi-day trends, hourly rollups and raw records without ever modifying your data.
Hosted MCP server that syncs health data from Apple Health, Fitbit, Oura, and Google Health Connect, enabling Claude and ChatGPT to query workouts, sleep, nutrition, and recovery in plain English with interactive charts.
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 an AI assistant to read your own Oura Ring data—sleep, readiness, activity, heart rate, SpO2, stress, workouts, and sessions—so you can ask natural-language questions and get summaries. It fetches data on demand from the Oura API v2, is read-only, and does not store or share data.
Enables recording meals and workouts in Traditional Chinese and writing them to a user's Fitbit/Google Health account via Google Health API v4, with local OAuth, dry-run previews, and idempotency safeguards.
Enables an AI assistant to read Garmin Connect sleep, health, activity, and training data, and to write structured multi-sport workouts, calendar schedules, and performance metrics back into Garmin Connect.
Enables an AI assistant to access a user's EGYM Fitness account for workouts, strength values, bio age, body metrics, and training plans, including creating, changing, and deleting personal plans.
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.
A local-first MCP server that enables AI agents to read user-authorized Google Health API v4 data from Fitbit, Pixel Watch, and partners via OAuth, with tokens never leaving the machine.
Enables MCP clients such as Claude to query Fitbit and Pixel Watch health data — sleep, steps, heart rate, HRV, workouts, weight and nutrition — through the Google Health API, with built-in OAuth 2.0 sign-in and multi-user access so it can be hosted remotely and reached from web, desktop and mobile.
Enables local synchronization of Garmin activity and health data using a personal API key, then lets MCP-connected AI clients analyze training readiness and recovery with cited models and research. Supports viewing records, sleep/HRV, stress, Body Battery, and generating pre-run recommendations without hosting accounts or personal data.
A read-only MCP server that lets a chat assistant query Garmin Connect personal data such as activities, sleep, HRV, Body Battery, stress, and weight to act as a personal coach. It runs locally over stdio in Claude Desktop or as a hosted HTTP service secured with OAuth 2.1 and PKCE, and none of its tools can modify data.
Self-hosted MCP server that aggregates personal health data from Google Health, Oura, and Withings into a single, provider-attributed interface with configurable source of truth preferences.
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.
MCP server that retrieves health data from Google Health API and calendar events from Google Calendar, and enables ChatGPT to create personalized wellness plans that are written to a dedicated calendar only upon user approval.
A local MCP server that exposes your Garmin Connect data—sleep, HRV, training readiness, workouts, and more—to any MCP-compatible AI assistant. Runs entirely on your machine and keeps your Garmin credentials private.
Enables read-only access to WHOOP recovery, sleep, HRV, strain, and workout data so users can ask natural-language questions about daily readiness, personal baselines, sleep debt, and trends, plus HYROX and triathlon performance readiness and auditing. It runs locally with summary and aggregate modes, keeping data on the user's machine and sharing results only with the chosen AI assistant.
Syncs your own Garmin Personal API data into a local SQLite archive and lets any MCP-capable AI assistant query sleep, HRV, stress, body battery, training and activity trends through natural language, with optional interactive charts. Everything runs locally with your own API key, so private health data stays on your machine.
Exposes hundreds of reflection-generated tools covering nearly every public python-garminconnect method, letting an assistant query sleep, HRV, training load, glucose, ECG, gear, courses, and range-based health data that other Garmin MCP servers skip. Adds hand-written tools for compact daily ranges, downsampled activity and intraday time series, raw Connect endpoint access, and offline JSONL export, with payload size limits, recursive personal-data redaction, and write tools hidden by default.
Enables Claude and other MCP clients to query your Fitbit/Pixel Watch health data via the Google Health API, including sleep, heart rate, activity, workouts, and trends with read-only access.
Enables Claude to read, write, and delete Google Health (Fitbit successor) metrics such as activity, sleep, heart rate, weight, and nutrition, plus log meals with photo-based nutrition estimation.
Enables ChatGPT to query the user's latest Google Health data through OAuth-authorized MCP calls, returning current metrics and refresh status for personal health analysis.
Enables users to turn structured training plans into Garmin Connect workouts, schedule them, queue delivery to registered devices, and optionally coordinate timed Google Calendar events with workout summaries.
Enables ChatGPT to retrieve a user's own Garmin Connect data — activities, single-activity details, sleep, HRV, daily summaries, heart-rate zones and profile — through seven read-only MCP tools behind OAuth authentication, so the assistant can analyze real records instead of screenshots or guesses.
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 users to ask their AI assistant about WHOOP recovery, sleep, HRV, strain, and workouts, with baselines, trends, period comparisons, and weekly health reviews drawn from their own recorded history. It also provides HYROX and triathlon race reports, readiness bands, and data auditing through read-only tools, resources, and prompt templates.
Connects WHOOP fitness data to Poke AI assistant, enabling natural language queries for recovery scores, sleep analysis, strain tracking, and healthspan metrics.
Gives any MCP-compatible AI assistant secure, read-only access to your personal Strava fitness data, including activities, segments, routes, gear, and more through natural language.
Enables an AI assistant to query a user's RQrun training data through read-only tools for activities, period statistics, training load and status, run-level predictions, intensity distribution, calendars, and profile details, and to render pace/heart-rate and weekly mileage charts as PNGs.
Enables an AI assistant to read your own Strava activities on demand, returning laps, splits, heart rate and a one-line read of a run's workout structure, plus a power-versus-calories check for rides. You deploy your own Cloudflare Worker copy with your own Strava API app, and OAuth ensures only your Strava account can connect.
Connect Pelaris to any MCP-compatible AI assistant for personalised fitness coaching. Plan training programs, log workouts, track benchmarks, manage goals, and get data-driven coaching insights.
Supports science-based methodologies including 5/3/1, Pfitzinger, polarised training, and more. OAuth 2.0 authentication with Streamable HTTP transport.
Documentation: https://pelaris.io/integrations
Web
Enables MONS coaches to build and adjust their clients' training plans through an AI assistant by chatting in plain language. It reads clients' plans, templates, programs and exercise library, then creates, edits or removes sessions, exercises and targets in MONS.
A personal remote MCP gateway that exposes Garmin Connect, Home Assistant, and YouTube as MCP servers over HTTP, allowing Claude or any MCP client to query and control them from anywhere without local credentials. It includes a web UI for managing credentials and issuing API keys, with authentication delegated to an external SSO.
A remote MCP server that allows trusted LLM assistants to read Google Health/Fitbit data and log nutrition, hydration, and body measurements via the Google Health API.
Enables users to ask an AI assistant about their WHOOP recovery, sleep, HRV, strain, workouts, and personal health trends, including HYROX and triathlon readiness, using read-only access to their own data.
Exposes Fitbit sleep and recovery data to Claude via the Google Health API, with tools for sleep sessions, sleep summaries, recovery vitals, and raw health data queries.