"A GitHub repository for agent guardrails" matching MCP servers:

A universal fitness intelligence layer for AI assistants like Claude, ChatGPT, and Copilot, enabling user profiles, workout/diet plans, calendar scheduling, and gamification via MCP and REST APIs.

Your AI running coach that actually remembers. An MCP server with persistent memory that connects your Strava data to Claude — tracking your zones, pace trends, injuries, and goals across sessions so coaching advice stays current.

Connects WHOOP fitness data to Poke AI assistant, enabling natural language queries for recovery scores, sleep analysis, strain tracking, and healthspan metrics.

Exposes Garmin Connect health and activity data (steps, sleep, heart rate, etc.) via MCP tools, with built-in login and MFA support.

Exposes over 90 Garmin Connect tools for tracking activities, health metrics, and training data through the Model Context Protocol. It is optimized for Poke compatibility and supports deployment to Render via HTTP.

Enables AI agents like Claude Desktop, Cursor, and VS Code to connect directly to COLMI R02/R03 and compatible smart rings over local Bluetooth LE, exposing tools for ring scanning, battery and firmware status, activity and sleep/recovery insights, real-time heart rate and SpO2 vitals, 3-axis motion sampling, clock sync, and physical LED blinking. Runs fully locally with no vendor cloud, accounts, or subscriptions.

HYBRD manage your wearables connection, is a system of record for your training plan / completed workouts, and steers LLMs towards giving better fitness coaching

Enables AI agents to access and manage fitness programs, exercise catalog, workout resources, activity metrics, journaled plan edits, and change tracking through authenticated tools.

A health-data MCP server with per-user authorization using JWT tokens, enabling secure access to fitness data like profiles, progress, meal logs, workout logs, and weight logs through MCP tools.

Enables Claude to act as a personal health coach by connecting to Garmin wearable data and Notion workspace for automated calorie tracking, photo food logging, and coaching insights.

Enables the agent to record meals, workouts, and check-ins, and to retrieve daily summaries, history, and settings through MCP tools.

Enables Claude to access and analyze Whoop health data including recovery, sleep, strain, and workouts through a custom MCP connector.

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.

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.

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 agents to securely access Apple Health data (sleep, heart rate, menstrual cycle, etc.) via end-to-end encrypted local decryption from the Tether iOS app.

Enables LLM clients to read a user's locally-decrypted calisthenics training data and propose plan updates without direct mutations.

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

Enables an LLM to search a movement library, log single-movement and multi-movement workout results, and pull complete logged training history plus PR trends for Beyond the Whiteboard straight from a chat. All logged entries are posted privately, and session authentication can refresh automatically.

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.