"Créer des systèmes de prompt pour les modèles de langage (LLM)" matching MCP servers:

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.

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.

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

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.

MCP server that connects Claude or any MCP-capable LLM to your Garmin golf data, enabling natural-language queries on rounds, shots, strokes gained, club distances, course intel, and health-performance correlations from a private local DuckDB cache.

A production-ready MCP server for the Hevy fitness API that exposes 27 tools for reading, writing, and analyzing workout data, enabling LLM-driven personal trainer workflows.

Enables users to query their Oura Ring data (sleep, readiness, activity, heart rate) via natural language through any MCP-compatible LLM.

MCP server integrating Foodvisor nutrition API for food search, meal logging, daily summaries, and progress tracking via LLM agents like Claude.

MCP server that turns any MCP-compatible LLM client into a wellness coach grounded in verified public data, offering nutrition, exercise, biometric, and preventive care tools with safety guardrails.

Enables LLM clients to query Xiaomi Mi Fitness family member sleep, heart rate, and step data via MCP, with QR-code login authentication.

Enables LLM clients to query Xiaomi Mi Health friend/family sleep, heart rate, and step data via MCP.

Enables LLM clients to query Xiaomi Mi Fitness authorized family members' sleep, heart rate, and step data via MCP after QR-code login, deployable on Cloudflare Workers.

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.

Exposes Xiaomi Mi Fitness family health data — sleep, heart rate, and step counts — to LLM clients over the MCP protocol. Runs on Cloudflare Workers with QR-code login and token-based authentication, requiring no self-hosted server.

Aggregates Android Health Connect data into daily summaries, time-series metrics, sleep details, and sync status, exposing them to LLM clients via MCP with caveats to prevent data fabrication.

Exposes Xiaomi Mi Health's friend/family sleep, heart rate, and step data to LLM clients via the MCP protocol, deployed on Cloudflare Workers.

Enables LLM clients to access authorized Xiaomi Mi Fitness health data, including sleep, heart rate, and steps, through an MCP server deployed on Cloudflare Workers.

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.

A remote MCP server that allows trusted LLM assistants to read Google Health/Fitbit data and log nutrition, hydration, and body measurements via the Google Health API.

Gives LLM agents read-only access to your WHOOP data — recovery, sleep, strain, workouts, and profile.