Empower your AI with Strava Data.
A production-ready Model Context Protocol (MCP) server that exposes the Strava API for AI agents and LLMs.
Features
Comprehensive access to your training data through standardized MCP tools.
Athlete Profiles
Detailed profiles, heart rate zones, and power stats for personalized analysis.
Activity Deep-Dive
Access laps, streams, comments, and detailed segment efforts.
Segments & Routes
Explore popular segments and your saved routes with all metadata.
Hardware Tracking
Manage your equipment and track the mileage of your bikes and shoes.
Dual-Output Architecture
Optimized for both humans and machines. Every tool delivers two outputs:
- User Content: Formatted markdown for an aesthetic display in the chat.
- Assistant Resource: Structured JSON for precise data processing by the LLM.
// JSON Resource for Assistant { "id": "12345678", "name": "Morning Ride", "distance": "45200", "moving_time": "5400", "audience": ["assistant"] }
Quick Start
Start the server locally with a single command via UV.
$ uv run strava-mcp-server