"Using llama.cpp and Searxng with local models" matching MCP servers:

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.

A local MCP server that caches Garmin Connect data in SQLite for fast, read-only queries, with tools for bulk import, rate-limited sync, and failure alerts.

Local-first Garmin data warehouse with an analysis-grade MCP server. Sync once, analyze forever, even when the API is down.

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.

Connects AI agents to the Pilates With Neelam studio management platform, enabling natural-language class search, real-time availability checks, bookings, level assessments, and post-class check-ins.

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 local, read-only access to Oura API v2 data, returning pre-shaped physiology such as sleep, chronotype, temperature shifts, and baseline drift for interpretation by AI clients.

MCP server for tracking nutrition meals and workouts, integrating with claude.ai to manage food logs, macros, exercise catalogs, and generate daily/weekly summaries.

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.

Claude Code plugin and MCP server that nudges you to take outdoor breaks based on local weather, sunset timing, and session streaks. Exposes check_grass_conditions, suggest_activity, log_touch_grass, and get_stats tools — fully local, no API keys, no cloud storage.

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

Provides read-only access to Withings health metrics including body composition, sleep, workouts, and ECG data with local SQLite caching and trend analysis. Features incremental synchronization, automatic OAuth token refresh, and supports all 200+ Withings measurement types for comprehensive health tracking.

MyChart MCP Server

Provides local MCP tools to query your own Xiaomi Mi Fitness health data (sleep, workouts, heart rate, etc.) stored in a local SQLite database, enabling AI assistants to access personal health records without exposing credentials.

Enables AI assistants to answer food safety and shelf-life questions using USDA-grade data, with tools for shelf life, safety checks, storage tips, and waste cost calculations.

Local MCP server to access your personal health data from E-Nabız (Turkish Ministry of Health) via an LLM. Read-only, secure, and respects privacy.

Privacy-first MCP server for querying personal health and finance data with AI. Built with Python, FastMCP, and SQLite. Local-first and open source.

Provides SQL access to the ANSES Ciqual French food composition database with nutritional data for over 3,000 foods. Supports full-text search and bilingual queries for comprehensive nutrition analysis.

Enables local, read-only access to Garmin Connect health and training data through MCP, letting assistants summarize recovery, sleep, activities, and more without uploading your data.

Provides Claude with real-time access to local health data including sleep, recovery, strain, and workouts from WHOOP and Apple Health, enabling informed context-aware interactions.

Mock MCP server for pediatric CKD risk warning, enabling patient biochemical trend retrieval, deterministic risk rule evaluation, structured alert triggering, and clinical SOP lookup using simulated data.

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.

Query your Apple Health data including sleep, heart rate, steps, workouts, and more by ingesting an exported XML archive into a local SQLite database.

Solar vitamin D: whether the sun where you are can make vitamin D right now, how many minutes your Fitzpatrick skin type needs for a target dose, which months of the year synthesis is possible at your latitude, and how much a sun session produced. Computed from solar geometry, a clear-sky UV model with ozone and altitude, and live Open-Meteo UV data.

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

Provides Claude Code and Claude Desktop with safe, read-only access to your local Garmin training data, readiness decisions, run details, and trends so you can get coaching advice in natural language.

A local-first, read-only MCP server that provides compact recovery, sleep, strain, HRV, heart-rate, workout, and body-measurement data from WHOOP without sending credentials to a third party.

Enables AI assistants to query a user's own Garmin Connect training, health, and recovery history through Garmin's official Personal API, backed by a local cache and built-in analysis tools.

Local-first CGM MCP for AI agents: Dexcom Developer API and FreeStyle Libre via LibreLink Up.

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.