Pierre MCP Server: Integrate Fitness API for AI Data Analysis

Pierre MCP Server

The Pierre Fitness API is a multi-protocol fitness data API that supports securely obtaining fitness data from providers such as Strava and Fitbit. It provides intelligent analysis for AI applications through MCP, A2A, and REST APIs, including enterprise-level API management, real-time analysis, and intelligent analysis of multiple sports types.

Health and wellness Developer tools #Fitness data #AI analysis #Multi-protocol #Intelligent training .TypeScript

rating : 2.5 points

downloads : 8.7K

update time : 2025-07-24

Open Site

What is the Pierre Fitness MCP Server?

The Pierre Fitness MCP Server is a bridge connecting fitness data and AI assistants. It provides secure and intelligent fitness data analysis services through the Model Context Protocol (MCP). Users can query their exercise data in natural language and obtain comprehensive analysis including running, cycling, and the impact of weather.

How to use the Pierre Fitness MCP Server?

Users can access the Pierre Server in multiple ways: 1. Use an AI assistant (such as Claude, ChatGPT); 2. Developers integrate through A2A or REST API; 3. Run in single-tenant mode locally. Simply configure it and you can start using it.

Applicable scenarios

Suitable for scenarios such as personal fitness analysis, AI coach development, multi-platform data integration, and real-time performance monitoring. Both developers and ordinary users can obtain valuable fitness insights through Pierre.

Main features

Multi-platform data integration

Supports obtaining fitness data from multiple platforms such as Strava and Fitbit, enabling unified management and analysis.

AI intelligent analysis

Conducts in-depth analysis of exercise data through artificial intelligence technology, providing intelligent suggestions including the impact of weather and terrain analysis.

Multi-protocol support

Supports multiple communication protocols such as MCP, A2A, and REST, facilitating the access of different types of clients.

Secure authentication mechanism

Adopts security mechanisms such as JWT and OAuth2 to ensure the security of user data.

Flexible deployment mode

Supports local single-tenant mode and multi-tenant mode in the cloud environment, adapting to different usage requirements.

Advantages

Provides AI-driven fitness data analysis to help users understand their performance more deeply

Supports multiple protocols, facilitating integration in different application scenarios

Has a complete authentication mechanism to ensure data security

Supports local and cloud deployment, with strong flexibility

Limitations

Requires a certain technical foundation for configuration and use

Some advanced features may require a paid subscription

For non-English users, the documentation and interface may not be friendly enough

How to use

Installation and configuration

Clone the project repository and compile and build it. Select a suitable running mode (single-tenant or multi-tenant).

Start the server

Select the running mode according to your needs, such as local single-tenant mode.

Integrate an AI assistant

Add the Pierre Server to the configuration of an AI assistant, such as Claude Desktop or ChatGPT.

Authorize access

Authorize Pierre to access your fitness platform data (such as Strava) through the OAuth process.

Usage examples

Query the longest running record

The user asks about their longest running record and location information.

Compare cycling and running performance

The user wants to know the performance difference between cycling and running.

Analyze marathon performance

The user wants to comprehensively analyze their marathon performance, including weather and terrain factors.

Frequently Asked Questions

Does the Pierre Server support a Chinese interface?

How to solve connection problems?

Can I customize the analysis content?

What permissions does the Pierre Server need?

Related resources

Official documentation

Contains a complete installation guide, API reference, and tool instructions.

GitHub code repository

Project source code and development information.

Setup guide

Detailed setup and installation steps.

Tool reference

Detailed instructions for all 21 fitness tools.

Deployment guide

Best practices for production environment deployment.

🚀 Pierre Fitness API

A multi - protocol fitness data API that offers secure access to fitness data from multiple providers (Strava, Fitbit) via the Model Context Protocol (MCP), A2A (Agent - to - Agent) Protocol, and REST APIs. It's designed for LLMs and AI applications, featuring enterprise - grade API key management, tiered rate limiting, trial keys with automatic expiration, OAuth integration, real - time analytics, comprehensive activity intelligence, and multi - protocol support for AI agent communication.

🚀 Quick Start

Method	Command	Use Case
🏠 Local	`cargo run --bin pierre-mcp-server -- --single-tenant`	Personal use, development
🐳 Docker	`./docker-compose-with-envrc.sh up`	Easy deployment, cloud - ready
🤖 AI Assistants	Add to MCP client config	Claude, ChatGPT, agent integration

One - Minute Setup

# 1. Clone and build
git clone https://github.com/Async-IO/pierre_mcp_server.git
cd pierre_mcp_server && cargo build --release

# 2. Run locally (single-tenant mode)
cargo run --bin pierre-mcp-server -- --single-tenant

# 3. Configure AI Assistant (Claude, ChatGPT, etc.)
echo '{
  "mcpServers": {
    "pierre-fitness": {
      "command": "'$(pwd)'/target/release/pierre-mcp-server",
      "args": ["--single-tenant", "--port", "8080"]
    }
  }
}' > ~/.claude/claude_desktop_config.json

✨ Features

🤖 AI - Powered Fitness Analysis

Pierre connects your fitness data to AI assistants like Claude, ChatGPT, and any agents supporting the MCP/A2A protocol, providing intelligent analysis with location, weather, and performance context.

Analysis Type	Example Queries	Key Features
🏃 Running	"What was my longest run this year and where?"	Pace trends, location context, terrain analysis
🚴 Cross - Training	"Compare my cycling vs running performance"	Multi - sport analysis, heart rate zones, consistency
🗺️ Location Intelligence	"Where do I perform best?"	GPS tracking, terrain impact, route optimization
🌦️ Weather Impact	"How does weather affect my performance?"	Temperature correlation, seasonal patterns
📊 Activity Intelligence	"Analyze my marathon with full context"	AI - powered insights, environmental factors
🎯 Goal Tracking	"How close am I to my 1000km goal?"	Progress monitoring, achievement analysis
📈 Performance Trends	"Find patterns in my training data"	Long - term analysis, optimization suggestions

💡 See detailed examples: Check out our comprehensive prompt guide with 50+ real - world queries.

🔌 Integration Methods

Pierre supports multiple integration patterns for different use cases:

Integration Type	Best For	Setup Complexity	Authentication
🤖 MCP Protocol	AI assistants (Claude, ChatGPT, Copilot)	Low	JWT Token
🔗 A2A Protocol	AI agents & applications	Medium	API Keys
🌐 REST API	Web apps & dashboards	Medium	OAuth2 + JWT
🏠 Single - Tenant	Personal local use	Minimal	Optional

Quick Setup Examples

🤖 AI Assistant Integration (Claude, ChatGPT, etc.)

Configure MCP Server

// For Claude Desktop (~/.claude/claude_desktop_config.json)
{
  "mcpServers": {
    "pierre-fitness": {
      "command": "path/to/pierre-mcp-server",
      "args": ["--single-tenant", "--port", "8080"]
    }
  }
}

// For ChatGPT or other MCP-compatible clients
// Use the same MCP protocol with your client's configuration

Connect to Strava
- Visit the OAuth URL provided by Pierre
- Authorize access to your Strava data
- Start asking questions in natural language
Works with any MCP/A2A compatible agent
- Claude Desktop, ChatGPT with MCP support
- Custom AI agents, GitHub Copilot extensions
- Any application supporting MCP or A2A protocols

🔗 A2A Integration for Developers

# Register your application
curl -X POST https://your-pierre-server.com/a2a/clients \
  -H "Authorization: Bearer JWT_TOKEN" \
  -d '{"name": "My Fitness App", "description": "AI fitness coach"}'

# Execute fitness tools
curl -X POST https://your-pierre-server.com/a2a/execute \
  -H "Authorization: Bearer API_KEY" \
  -d '{
    "jsonrpc": "2.0",
    "method": "tools.execute",
    "params": {
      "tool_name": "get_activities",
      "parameters": {"provider": "strava", "limit": 10}
    }
  }'

📖 Detailed guides: See our setup documentation for complete integration examples.

⭐ Key Features

Category	Features
🔗 Integrations	Strava, Fitbit • MCP Protocol • A2A Protocol • REST APIs
🛡️ Security	OAuth2 + PKCE • JWT Authentication • Encrypted storage • Rate limiting
🧠 Intelligence	AI activity analysis • Location detection • Weather integration
🏗️ Architecture	Single & multi - tenant • Cloud - ready • Extensible • Production - ready

📚 Documentation

Guide	Description	Key Topics
📋 Setup & Installation	Get started quickly	Local setup, OAuth config, Docker deployment
🛠️ MCP Tools Reference	All 21 fitness tools	Data access, intelligence, goals, analytics
🌦️ Weather Integration	Weather - enhanced analysis	OpenWeatherMap setup, mock data, intelligence
🔑 API Reference	Enterprise features	API keys, rate limiting, security, monitoring
🚀 Deployment Guide	Production deployment	Docker, Kubernetes, cloud platforms

🔧 Technical Details

🏗️ Architecture

Mode	Best For	Features
🏠 Single - Tenant	Personal use	Local config, no auth required, simple setup
☁️ Multi - Tenant	Cloud deployment	JWT auth, encrypted storage, user isolation

📄 License

This project is dual - licensed under either of:

Apache License, Version 2.0 ([LICENSE - APACHE](LICENSE - APACHE))
MIT License ([LICENSE - MIT](LICENSE - MIT))

at your option.

Contribution

Unless you explicitly state otherwise, any contribution intentionally submitted for inclusion in the work by you, as defined in the Apache - 2.0 license, shall be dual licensed as above, without any additional terms or conditions.