Skip to main content
Glama
andywangyzfh

Strava Cardio MCP

by andywangyzfh
OverviewSchemaSourceRelated ServersDiscussionsAdmin
TypeScript
Local

Strava Cardio MCP

A local, read-only Model Context Protocol server that connects agents directly to the official Strava API. It gives Codex and other MCP hosts structured access to personal cardio history without putting Strava secrets in chat or project files.

It can read activity summaries, laps, heart-rate and power zones, detailed streams, and aggregate run/ride/swim statistics. Its cardio summary filters strength and climbing by default and flags likely duplicate device imports without silently deleting them.

The server has no create, edit, upload, or delete tools.

Quick start: Codex on macOS

Requirements: Node.js 20 or newer, Git, Codex CLI, and a Strava account.

git clone https://github.com/andywangyzfh/strava-mcp.git
cd strava-mcp
npm ci
npm run build
npm run connect
npm run install:codex

Before npm run connect, create a personal application in Strava API settings and set Authorization Callback Domain to localhost. The setup page saves the Client ID, Client Secret, and rotating refresh token in macOS Keychain. Restart Codex or open a new task after registration.

Related MCP server: Strava MCP Server

Linux, Windows, and other MCP hosts

The server also supports a private JSON credentials file outside the repository. Set STRAVA_MCP_CREDENTIALS_FILE to an absolute path before running npm run connect; the setup helper creates the file with user-only permissions and keeps its rotating refresh token current.

See docs/SETUP.md for macOS Keychain, Linux, Windows PowerShell, manual MCP configuration, OAuth, heart-rate permissions, and troubleshooting.

Tools

Tool

Purpose

strava_get_athlete

Authenticated athlete profile

strava_list_activities

Paginated activity summaries

strava_get_activity

One detailed activity

strava_get_activity_laps

Activity laps

strava_get_activity_streams

Selected time-series streams, downsampled by default

strava_get_athlete_zones

Heart-rate and power zones

strava_get_athlete_stats

Aggregate run, ride, and swim statistics

strava_summarize_cardio

Date-range cardio totals and likely duplicate flags

Pass Strava athlete and activity IDs as strings so 64-bit values stay exact. See docs/TOOLS.md for usage guidance.

Privacy and behavior

  • OAuth requests read and activity:read_all so private activities can be analyzed.

  • Access tokens stay in memory. Rotated refresh tokens are persisted to the configured secret store.

  • Requests are fixed to Strava's official v3 API and reject HTTP redirects.

  • Detailed streams default to at most 2,000 samples and can return up to 10,000.

  • The package is marked private to prevent accidental npm publication; the source is MIT licensed.

Read SECURITY.md before changing credential handling. A ready-made English and Chinese installation prompt for another agent is in docs/AGENT_INSTALL_PROMPT.md.

Development

npm ci
npm run check
npm test
npm run build

中文说明

这是一个只读的本地 Strava MCP server，直接使用官方 API，不依赖第三方代理。它可以让 Codex 等 agent 分析跑步、骑行、步行、划船等有氧记录，并读取配速、心率、功率、踏频、海拔、分段和详细时间序列。

macOS 可以使用系统钥匙串保存凭证；Linux 和 Windows 可以使用仓库外的私密 JSON 文件。每位使用者应创建并授权自己的 Strava API application，不要分享 Client Secret 或 refresh token。

This server cannot be deployed

One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Maintenance

ActivityMaintained
ResponsivenessNo issues

Resources

Related MCP Connectors

Related MCP Servers

  • Strava MCP Server

    juanlarreapm
    A
    license
    B
    quality
    D
    maintenance
    Integrates with the Strava API to allow AI assistants to access fitness data including athlete profiles, activity history, and segment statistics. It enables users to query detailed performance metrics and explore geographic segment data through natural language commands.
    8
    43 npm
    MIT

  • Strava MCP Server

    LimeON-source
    A
    license
    B
    quality
    D
    maintenance
    Enables users to interact with their Strava data through natural language to analyze workouts, track fitness progress, and explore routes. It supports retrieving detailed activity stats, heart rate data, and segment insights directly within AI assistants.
    26
    206 npm
    MIT