A2A Mcp Strava Fitbit Server

CI Frontend Tests

Active Development - This project is under active development and not yet ready for production use. We welcome feedback, contributions, and early testing from the community. Please report issues and share your experiences.

An open source multi-protocol fitness data API providing secure access to fitness data from multiple providers (Strava, Fitbit) through the Model Context Protocol (MCP), A2A (Agent-to-Agent) Protocol, and REST APIs. Built for LLMs and AI applications with comprehensive API key management, rate limiting, OAuth integration, and real-time analytics.

Fitness Data Analysis

Pierre connects 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.

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:

Quick Setup Examples

# 1. Register your A2A client
curl -X POST http://localhost:8081/a2a/clients \
  -H "Content-Type: application/json" \
  -d '{
    "name": "My Fitness App",
    "description": "AI fitness coach",
    "capabilities": ["fitness-data-analysis"],
    "contact_email": "[email protected]"
  }'

# 2. Authenticate client
curl -X POST http://localhost:8081/a2a/auth \
  -H "Content-Type: application/json" \
  -d '{
    "client_id": "your_client_id",
    "client_secret": "your_client_secret",
    "scopes": ["read", "write"]
  }'

# 3. Execute fitness tools (requires user JWT token)
curl -X POST http://localhost:8081/a2a/execute \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer USER_JWT_TOKEN" \
  -d '{
    "jsonrpc": "2.0",
    "method": "tools.execute",
    "params": {
      "tool_name": "get_activities",
      "parameters": {"provider": "strava", "limit": 10}
    },
    "id": 1
  }'

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

Documentation

Key Features

Quick Start

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. Set up environment and run server
# Configure your environment variables (see docs/GETTING_STARTED.md)
cargo run --bin pierre-mcp-server

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

Fresh Start: Need to clean your database? See our Database Cleanup Guide.

Architecture

Pierre MCP Server is built as a production-ready, multi-tenant application with comprehensive security and scalability features:

• Authentication: JWT-based user authentication with secure token management
• Database: Encrypted storage with SQLite/PostgreSQL support
• Security: User isolation, rate limiting, and encrypted data storage
• Scalability: Cloud-ready deployment with Docker and Kubernetes support

License

This project is dual-licensed under either of:

• Apache License, Version 2.0 (LICENSE-APACHE)
• MIT License (LICENSE-MIT)

at your option.

Contributing

We welcome contributions! See CONTRIBUTING.md for details on how to get started.