"Examples of MCPs (Microservices Communication Protocols) That Do Not Require API Keys" matching MCP servers:

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.

Enables retrieval of InBody body composition data including profile, scan history, and full metrics via MCP tools.

MCP server for Cronometer nutrition tracking, enabling food diary management, nutrition data retrieval, food search, and biometric tracking via Cronometer's mobile REST API.

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.

MCP server for Cronometer nutrition tracking using the mobile API. Enables food logging, nutrition data retrieval, diary management, and fasting tracking.

Connects a user's own Garmin data to compatible AI clients through Garmin's official Personal API, running locally over stdio with read-only access and no Garmin username or password.

Unofficial MCP server for Fitatu, the Polish calorie counter: read and log food, weight, water, body measurements and workouts, check calories and macros left, set goals and get weekly reports. 47 tools (26 read-only), read-only and demo modes, stdio or HTTP with a token, free and Premium accounts.

An MCP server that provides an interface to Google's Fitness API, enabling interaction with fitness data through natural language using the Multi-Agent Conversation Protocol.

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.

Exposes the complete Oura Ring v2 API to LLM agents, including detailed sleep data, time-series biometrics, hypnogram rendering, and analytical tools, unlike other MCPs that only provide daily scores.

Connects AI assistants to TrainingPeaks via secure cookie authentication (no API approval needed), letting users query and build workouts, schedule intervals on the calendar, analyze CTL/ATL/TSB fitness trends and power PRs, manage health metrics, events, equipment, and workout libraries through natural language. It also supports coach accounts with athlete groups and multi-week training plans.

Enables MCP clients to query read-only Oura health data—readiness, sleep, HRV, activity, stress, heart rate and tags—through combined daily overviews, multi-day trends and aggregated heart-rate series. Authentication stays local via OAuth with PKCE, graceful handling of unavailable data types, and an optional sandbox of public sample data.

MCP server for the Fitbit Web API with OAuth PKCE, local cache, and trend analysis.

Provides read-only access to Oura ring biometrics via the Oura API, enabling Claude to query daily summaries, sleep, readiness, stress, workouts, baselines, and heart rate data. Designed to complement a Strava connector for joint analysis of training and recovery.

Query Apple Health export data with an LLM via a semantic layer that avoids common data traps, enabling accurate natural-language queries about health metrics. Optionally imports CPAP therapy data for correlation.

Exposes the Oura API v2 as an MCP server with tools to query all 19 data collections (e.g., sleep, heartrate) with automatic pagination and explicit truncation warnings.

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.

Read-only MCP server enabling natural language querying of personal health and cultural activity scores from the health.ojimpo.com dashboard via Claude.

An MCP server that transforms Garmin data into compact, verdict-first coaching reports for LLMs, computing metrics like CTL/ATL/TSB and ACWR to answer training readiness questions.

MCP server that enables AI assistants to access Whoop health data including recovery, sleep, workouts, and daily strain for personalized health recommendations.