"Exploring GraphRAG and HybridRAG" matching MCP servers:

MyChart MCP Server

Enables AI assistants to manage recipes, meal plans, and shopping lists in Mealie through natural language, supporting CRUD operations and URL-based recipe imports.

An MCP server that enables interaction with the Strava API v3 to manage fitness activities, athlete profiles, segments, and routes. It supports retrieving detailed performance metrics, exploring geographic data, and managing club information through natural language.

An ADT-based calendar management system that enables users to create, update, and organize events by category with integrated stamina tracking functionality.

Enables MCP-compatible AI clients to read and write wearable data through Whoop's private iOS API, covering recovery, sleep, strain, journal, strength training, live heart rate, and more via 55 tools. Write operations default to a preview gate requiring explicit confirmation.

A Model Context Protocol server that enables Claude to search and access detailed nutritional information from the USDA's FoodData Central database.

A Python-based Model Context Protocol server that provides AI assistants with access to Oura Ring health and fitness data across 15+ endpoints. It enables querying metrics like sleep, activity, readiness, and cardiovascular health through simple authentication and date-range filtering.

Enables AI-driven weekly meal planning with structured recipes, cooking steps, and grocery lists.

Enables estimating sweat rate and sodium loss, modeling subclinical dehydration cognitive deficits, and generating personalized hourly fluid and electrolyte replenishment schedules.

Enables MCP clients to connect to a privacy-first, self-hostable workout planning and training log, allowing coaching agents to preview and apply program changes while accessing training data through OAuth-protected endpoints.

Read-only MCP server with real Chinese chain-restaurant nutrition data: 103 menu items across 14 chains, calories and macros plus per-item health notes. Published on PyPI.

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.

Serves read-only archived ResMed CPAP data from a local SQLite database, enabling MCP clients to query nightly summaries, raw signals, and sync status over the LAN.

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.

An MCP server that securely syncs and queries your health data from Apple Health, storing it in your own Supabase Postgres database and exposing tools for AI assistants to retrieve weight, calories, macros, and more.

Connects to Garmin Connect and exposes your fitness and health data to OpenWebUI, Claude, or any MCP-compatible client via 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.

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

Enables AI assistants to access Oura Ring health data including sleep, readiness, activity, heart rate, and workouts through MCP tools with OAuth2 authentication.

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.

Enables users to query Garmin health, activity, sleep, HRV, and training data through read-only MCP tools from ChatGPT or Codex.

Enables Claude and other AI agents to read sleep and recovery data from a Fitbit or Pixel Watch through the Google Health API, including HRV, resting and sleeping heart rate, SpO2, breathing rate, skin temperature, and detailed sleep stages compared against a personal baseline. It runs as a shared AWS Lambda custom connector with per-user Google sign-in and read-only tools for recovery status, daily metrics, sleep sessions, and night-level detail.

Connects to Garmin Connect and exposes fitness and health data to MCP-compatible clients, enabling activity management, health metrics, training and performance analytics, workout creation/scheduling, gear, nutrition, and related data access.

MCP server providing full read/write access to Whoop wearable data, including recovery, sleep, workouts, journal, and more, via Whoop's private iOS API.

Enables AI apps such as Claude and ChatGPT to read an endurance athlete's watch data synced via Intervals.icu and turn it into history-checked race predictions. Access is read-only and OAuth 2.1-secured, with every value labelled by source and predictions returned as ranges rather than single times.

Enables ChatGPT to record, correct, and query meal nutrition and nutrition goals, with durable and auditable data storage.

Enables forecasting of 90-minute ultradian rhythm phases, alertness peaks and dips, and restorative nap windows through two-process sleep-wakefulness modeling.

A server that connects to the Health Planet API to fetch and provide weight measurement data through any MCP-compatible client, allowing for retrieval and analysis of personal weight records.

Enables LLMs to read and write Hevy workout tracking data, including workouts, routines, exercise templates, per-exercise history, and body measurements through all 15 Hevy public API endpoints.

Enables AI assistants to calculate recipe and per-serving calories, macros, and FDA-rounded Nutrition Facts values from ingredient lines using USDA FoodData Central data, including scaling recipes and looking up ingredient nutrition.