"A local knowledge base" matching MCP servers:

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.

MCP server for connecting Claude Desktop to a local medical knowledge base with real-time file watching, enabling natural language interaction with medical documents.

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.

MCP server for hybrid medical consultation integrating Western and Traditional Chinese Medicine, enabling symptom analysis, diagnosis, and treatment suggestions through two specialized models.

Enables querying a local health knowledge base with hybrid RAG (vector + FTS5) and exploring backlinks between notes.

Enables AI assistants like Claude to log and delete period and ovulation records, review cycle history and averages, and check the current cycle phase with predictions of the next period and ovulation window. Records are kept in the user's own Supabase instance behind key or OAuth authentication.

为安宁疗护陪护志愿者提供一站式工具，粘贴群聊对话即可自动识别场景，生成标准化安抚话术和后续陪护行动建议。

Enables searching and retrieving detailed medical knowledge on diseases, vaccines, medical examinations, and treatments, supporting health-related queries and medical concept understanding.

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.

USDA nutrition API optimized for AI agents. x402 + USDC on Base

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

MyChart MCP Server

Enables scoring the WHO-5 Well-Being Index from five answers, returning a 0–100 score and a low, reduced, or normal band without providing a diagnosis.

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.

Ask your Oura Ring about sleep, readiness, activity, stress and heart rate in ChatGPT or Claude, in any language. Read-only, 10 task-oriented tools; runs in a sandbox demo mode with no credentials.

Fitness AI - MCP server providing AI-powered tools and automation by MEOK AI Labs

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.

Enables AI agents to look up businesses, find free appointment slots, book, list and cancel appointments at salons, barbershops, nail and brow studios and clinics. Works read-only without a customer login by returning a pre-filled booking link, and can also run against a built-in demo with sample businesses.

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.

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 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.

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.

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 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.