MCP Wellness Agent
Provides a ready Fitbit provider integration (requiring OAuth2 credentials) for accessing wellness data such as sleep, activity, heart rate, steps, and stress through MCP tools for current vitals, history, and trend analysis.
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@MCP Wellness Agenthow did I sleep last night and what's my resting heart rate?"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
MCP Wellness Agent
A Model Context Protocol (MCP) server that exposes wellness data (sleep, activity, heart rate) as tools for AI agents. Built for the Amazon Build Ship Shape 2026 hackathon as part of the Open Source Mini-Challenge.
π Features
MCP Protocol: Implements the Model Context Protocol for agent-tool communication
Multi-Provider: Supports Fitbit, Apple Health, and realistic simulation
A2A Compatible: Includes agent card for agent-to-agent discovery
Voice-Ready: Optimized for Alexa+ and voice-first interfaces
Type-Safe: Full Pydantic models for all data
Extensible: Easy to add new wellness providers
Related MCP server: vitals
π Quick Start
# Install
pip install mcp-wellness-agent
# Run MCP server
mcp-wellness-server --transport streamable-http --port 8001
# Or use as library
from mcp_wellness_agent import WellnessServer
server = WellnessServer(provider="fitbit")π‘ MCP Tools
get_vitals(user_id: str)
Get current wellness vitals for a user.
Returns:
sleep_hours: Hours of sleepsleep_quality: Quality score (1-10)activity_level: low/normal/highheart_rate_avg: Resting heart ratesteps: Daily step countstress_level: Stress score (1-10)
get_history(user_id: str, days: int)
Get historical wellness data.
analyze_trends(user_id: str)
Get trend analysis and insights.
π Providers
Provider | Status | Notes |
Simulated | β Ready | Realistic physiological simulation |
Fitbit | β Ready | Requires OAuth2 credentials |
Apple Health | π§ Planned | macOS/iOS only |
Garmin | π§ Planned | Coming soon |
ποΈ Architecture
βββββββββββββββββββ MCP ββββββββββββββββββββ
β AI Agent βββββββββββββββΊβ Wellness Agent β
β (Claude, etc) β Streamable β MCP Server β
βββββββββββββββββββ HTTP ββββββββββββββββββββ
β
βββββββββββββββΌββββββββββββββ
βΌ βΌ βΌ
ββββββββββ βββββββββββ ββββββββββββ
β Fitbit β β Apple β β Simulatedβ
β API β β Health β β Engine β
ββββββββββ βββββββββββ ββββββββββββπ€ Contributing
Contributions welcome! See CONTRIBUTING.md for guidelines.
π License
Dual-Licensed under GNU AGPLv3 (AGPL-3.0-only) and PolyForm Noncommercial 1.0.0 β No closed-source or commercial use is permitted without prior written permission (see LICENSE, LICENSE.NONCOMMERCIAL.md, and COMMERCIAL_LICENSE.md).
π Hackathon
Built for Amazon Build Ship Shape 2026 - Open Source Mini-Challenge.
This server cannot be deployed
Maintenance
Related MCP Connectors
Connect your health, fitness, nutrition, sleep, and wearable data to your AI assistant.
MCP server for Withings health data β sleep, activity, heart, and body metrics.
- freddyOAuthcoach.freddy
Connect your wearables, rings and training apps, then ask your AI about your own health data.
Read wearables and lab health data β sleep, activity, workouts, timeseries, lab tests and orders.
Related MCP Servers
- AlicenseNot gradedqualityDmaintenanceExposes personal Garmin wellness data through MCP tools for accessing summary, sleep, HRV, heart rate, stress, body battery, and historical data.MIT
- AlicenseNot gradedqualityBmaintenanceExposes personal health data (recovery, sleep, strain, etc.) as MCP tools for AI agents to query and analyze.5MIT
- AlicenseNot gradedqualityCmaintenanceProvides MCP tools to read and update a local-first personal OS for goals, tasks, habits, food, workouts, and check-ins. Enables assistants to manage daily life data and interact with an evidence-grounded AI coach.MIT
- FlicenseNot gradedqualityCmaintenanceExposes health metrics from the Sapphire Wellness App to AI assistants via MCP, enabling queries on activity, blood pressure, glucose, heart rate, sleep, and SpO2 data.-