Strava MCP Server
An MCP server that enables interaction with the Strava API v3 to manage fitness activities, athlete profiles, segments, and routes. It supports retrieving detailed performance metrics, exploring geographic data, and managing club information through natural language.
README
Strava MCP Server
An MCP (Model Context Protocol) server that provides tools for interacting with the Strava API v3. Built with TypeScript and the MCP SDK.
Tools
Activities
- strava_list_activities - List the authenticated athlete's activities with date range filtering and pagination
- strava_get_activity - Get detailed activity info including splits, laps, segment efforts, and gear
- strava_create_activity - Create a manual activity entry
- strava_update_activity - Update an activity's mutable properties
- strava_list_activity_comments - List comments on an activity
- strava_list_activity_kudoers - List athletes who gave kudos
- strava_list_activity_laps - List laps with distance, time, speed, heart rate, watts, and elevation
- strava_list_activity_zones - Get heart rate and power zone distribution
Athletes
- strava_get_authenticated_athlete - Get the authenticated athlete's profile
- strava_get_athlete_zones - Get heart rate and power zones
- strava_get_athlete_stats - Get year-to-date and all-time totals for runs, rides, and swims
Segments
- strava_get_segment - Get segment details including distance, elevation, grade, and effort count
- strava_list_segment_efforts - List efforts on a segment with date range filtering
- strava_get_segment_effort - Get a specific segment effort with achievements
- strava_explore_segments - Find popular segments within a geographic bounding box
- strava_star_segment - Star or unstar a segment
Routes
- strava_list_athlete_routes - List routes created by an athlete
- strava_get_route - Get detailed route information
- strava_export_route_gpx - Export a route as GPX
- strava_export_route_tcx - Export a route as TCX
Streams (Time-Series Data)
- strava_get_activity_streams - Get activity streams (heart rate, power, cadence, altitude, GPS, etc.)
- strava_get_segment_effort_streams - Get segment effort streams
- strava_get_segment_streams - Get segment GPS/altitude data
- strava_get_route_streams - Get route GPS/altitude data
Clubs
- strava_list_athlete_clubs - List clubs the athlete belongs to
- strava_get_club - Get club details
- strava_list_club_activities - List recent club member activities
- strava_list_club_members - List club members
- strava_list_club_admins - List club admins
Gear
- strava_get_gear - Get equipment details (bikes, shoes)
Uploads
- strava_create_upload - Upload a FIT/TCX/GPX file to create an activity
- strava_get_upload - Check upload processing status
Setup
1. Create a Strava API Application
Go to Strava API Settings and create an application. Note your Client ID and Client Secret.
2. Get an Access Token
You need an access token with the appropriate scopes. For read-only access use read,activity:read_all. For write access add activity:write.
You can obtain tokens through Strava's OAuth flow. The server will automatically refresh expired tokens if STRAVA_REFRESH_TOKEN, STRAVA_CLIENT_ID, and STRAVA_CLIENT_SECRET are set.
3. Configure Environment Variables
export STRAVA_CLIENT_ID="your_client_id"
export STRAVA_CLIENT_SECRET="your_client_secret"
export STRAVA_ACCESS_TOKEN="your_access_token"
export STRAVA_REFRESH_TOKEN="your_refresh_token"
4. Add to Claude Desktop
Add to your claude_desktop_config.json:
{
"mcpServers": {
"strava": {
"command": "npx",
"args": ["-y", "strava-mcp-server"],
"env": {
"STRAVA_CLIENT_ID": "your_client_id",
"STRAVA_CLIENT_SECRET": "your_client_secret",
"STRAVA_ACCESS_TOKEN": "your_access_token",
"STRAVA_REFRESH_TOKEN": "your_refresh_token"
}
}
}
}
Or if installed locally:
{
"mcpServers": {
"strava": {
"command": "node",
"args": ["/path/to/strava-mcp/dist/index.js"],
"env": {
"STRAVA_CLIENT_ID": "your_client_id",
"STRAVA_CLIENT_SECRET": "your_client_secret",
"STRAVA_ACCESS_TOKEN": "your_access_token",
"STRAVA_REFRESH_TOKEN": "your_refresh_token"
}
}
}
}
Development
npm install
npm run build
npm run dev # watch mode with tsx
License
MIT
推荐服务器
Baidu Map
百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。
Playwright MCP Server
一个模型上下文协议服务器,它使大型语言模型能够通过结构化的可访问性快照与网页进行交互,而无需视觉模型或屏幕截图。
Magic Component Platform (MCP)
一个由人工智能驱动的工具,可以从自然语言描述生成现代化的用户界面组件,并与流行的集成开发环境(IDE)集成,从而简化用户界面开发流程。
Audiense Insights MCP Server
通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。
VeyraX
一个单一的 MCP 工具,连接你所有喜爱的工具:Gmail、日历以及其他 40 多个工具。
graphlit-mcp-server
模型上下文协议 (MCP) 服务器实现了 MCP 客户端与 Graphlit 服务之间的集成。 除了网络爬取之外,还可以将任何内容(从 Slack 到 Gmail 再到播客订阅源)导入到 Graphlit 项目中,然后从 MCP 客户端检索相关内容。
Kagi MCP Server
一个 MCP 服务器,集成了 Kagi 搜索功能和 Claude AI,使 Claude 能够在回答需要最新信息的问题时执行实时网络搜索。
e2b-mcp-server
使用 MCP 通过 e2b 运行代码。
Neon MCP Server
用于与 Neon 管理 API 和数据库交互的 MCP 服务器
Exa MCP Server
模型上下文协议(MCP)服务器允许像 Claude 这样的 AI 助手使用 Exa AI 搜索 API 进行网络搜索。这种设置允许 AI 模型以安全和受控的方式获取实时的网络信息。