# Strava

> Use this tool when you need to access and analyze Strava fitness data, such as activities, sensor streams, and workout metrics, with features like local caching, rate limit management, and OAuth token handling. It solves problems for fitness enthusiasts, coaches, and developers who require conversational or integrated access to Strava data, providing inputs like date ranges and activity filters, and outputs like detailed workout analytics. Ideal for use cases like training analysis, fitness application development, and conversational AI interfaces.

Canonical page: https://skillsregistry.net/skills/lyledean1-strava  
JSON: https://api.skillsregistry.net/v1/skills/lyledean1-strava

## Description

This MCP server provides AI assistants with access to Strava fitness data through local caching and rate limit management, built by Lyle Dean using Go with Gin web framework, zstd compression for storage, and OAuth token management. The implementation offers three core tools for retrieving and filtering Strava activities with date range support, accessing detailed sensor stream data including GPS coordinates, heart rate, and power metrics, and refreshing cached data from the Strava API with configurable time windows. Built with compressed local storage using zstd, automatic token refresh handling, and dual deployment modes supporting both MCP protocol and standalone REST API, it serves fitness enthusiasts wanting conversational access to their workout data, coaches needing AI-assisted training analysis, and developers building fitness applications who require cached Strava integration with intelligent rate limit management.

## Trust

- **Trust score (0–1):** 0.63
- **Verification tier:** scanned
- **Last scanned:** 2026-09-02

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** mcp-remote
- **Runtime environment:** api
- **Category:** devops-ci
- **Updated:** 2026-09-02

## Source

- **Source listing:** [PulseMCP](https://www.pulsemcp.com/servers/lyledean1-strava)
- **Repository:** <https://github.com/lyledean1/strava-mcp>

## Use it

Resolve this record through the SkillsRegistry MCP server (no auth, read-only):

```
claude mcp add --transport http --scope user skillsregistry https://api.skillsregistry.net/mcp
```

```json
{
  "jsonrpc": "2.0",
  "id": 1,
  "method": "tools/call",
  "params": {
    "name": "get_skill",
    "arguments": {
      "slug": "lyledean1-strava"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/lyledean1-strava` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/lyledean1-strava/pull`

---
SkillsRegistry indexes agent skills from public registries and GitHub. Skills we have analysed are scanned with Circle-IR and scored on six dimensions; each listing states its scan coverage. More: https://skillsregistry.net/llms.txt