Strava Data Processor with Model Context Protocol (MCP) Integration

This solution bridges raw athletic performance data sourced from the Strava platform with the analytical capabilities of the Model Context Protocol SDK to derive actionable insights and personalized coaching suggestions.

✨ Key Features

• Ingestion and processing of exercise logs from Strava.
• Generation of prescriptive training guidance.
• Automated refreshing of necessary authorization credentials.
• Implementation of request throttling mechanisms to respect API quotas.

📚 Prerequisites

• Runtime Environment: Python 3.10 or newer.
• Access to Claude Desktop.
• An active Strava account.
• [uv] dependency manager (highly recommended for setup).

🛠️ Installation Guide

bash

Obtain the source code repository

git clone https://github.com/rbctmz/mcp-server-strava.git cd mcp-server-strava

Recommended installation using uv

curl -LsSf https://astral.sh/uv/install.sh | sh uv pip install .

Development environment setup

uv pip install -e ".[dev]"

Installing the MCP Framework

bash uv add "mcp[cli]"

📝 Configuration

Securing Strava API Credentials

1. Navigate to the API Settings portal.
2. Register a new application:
3. Application Identifier: MCP Strava Integration
4. Domain Classification: Training Analysis
5. Site URL: http://localhost
6. Redirect URI: localhost

Environment Variable Setup

1. Duplicate the template for environment variables:

bash cp .env-template .env

1. Execute the authentication script to acquire initial access tokens:

bash python scripts/auth.py

1. Verify operational status:

bash mcp dev src/server.py curl -X GET "http://localhost:8000/activities"

🌐 Resource Access & Tooling

Available Interface Endpoints and Utility Functions

Interface Type	Identifier	Description
Data Fetcher	strava://activities	Collection of user activities
Data Fetcher	strava://activities/{id}	Specific activity record
Metric Source	strava://athlete/zones	Athlete's physiological metrics zones
Data Fetcher	strava://athlete/clubs	Affiliated athletic organizations
Data Fetcher	strava://gear/{gear_id}	Equipment details utilized
Function Call	analyze_activity(activity_id)	Detailed assessment of a single workout
Function Call	analyze_training_load(activities)	Aggregated physiological strain calculation
Function Call	get_activity_recommendations()	Suggested future training protocols

Operational Examples

python from mcp import ClientSession

Retrieving user activity history

async with ClientSession() as session: activity_list = await session.read_resource("strava://activities") single_record = await session.read_resource("strava://activities/12345678")

Performing granular workout analysis

analysis_output = analyze_activity(activity_id="12345678") """ { "type": "Run", "distance": 5000, "moving_time": 1800, "analysis": { "pace": 5.5, # minutes per kilometer "effort": "Moderate" } } """

Summarizing cumulative training stress

load_summary = analyze_training_load(activities) """ { "activities_count": 10, "total_distance": 50.5, # kilometers "total_time": 5.2, # hours "heart_rate_zones": { "easy": 4, "medium": 4, "hard": 2 } } """

Fetching established physiological boundaries

async with ClientSession() as session: zones_data = await session.read_resource("strava://athlete/zones") """ { "heart_rate": { "custom_zones": true, "zones": [ {"min": 0, "max": 120, "name": "Z1 - Recovery"}, {"min": 120, "max": 150, "name": "Z2 - Endurance"}, {"min": 150, "max": 170, "name": "Z3 - Tempo"}, {"min": 170, "max": 185, "name": "Z4 - Threshold"}, {"min": 185, "max": -1, "name": "Z5 - Anaerobic"} ] }, "power": { "zones": [ {"min": 0, "max": 180}, {"min": 181, "max": 250}, {"min": 251, "max": 300}, {"min": 301, "max": 350}, {"min": 351, "max": -1} ] } } """

💻 Development Workflow

Quality Assurance and Security Posture

• 
• 
• 

Continuous Integration Checks (GitHub Actions)

Check Type	Utility	Purpose
Syntax/Style	ruff	Code linting and formatting enforcement
Testing Suite	pytest	Unit and integration verification
Coverage Report	pytest-cov	Measurement of code path execution

Security and Secrets Management

1. Protection of sensitive credentials:
2. Exclusion of .env via .gitignore.
3. Utilization of GitHub Secrets for CI/CD contexts.

4. API request limits enforced: 100 requests per 15-minute interval.

5. Secret configuration procedure:

bash # Configure within GitHub Repository Settings → Secrets → Actions STRAVA_CLIENT_ID= STRAVA_CLIENT_SECRET= STRAVA_REFRESH_TOKEN=

Contribution Guidelines

1. Fork the primary repository.
2. Install required dependencies: uv pip install -e ".[dev]".
3. Establish a feature branch: git checkout -b feature/topic-name.
4. Validate all changes:

bash ruff format . ruff check . pytest --cov=src

1. Submit a comprehensive Pull Request.

📞 Support & Contact

• Issue Tracker: File a new issue
• Direct Contact (Telegram): @greg_kisel

📜 License

This project is governed by the MIT License.

---

Note: The following sections are derived from the original Wikipedia context provided for stylistic padding and do not directly describe the MCP tool itself, although they conceptually relate to asynchronous data transfer methods.