Intervals.icu MCP Server

Intervals.icu MCP Server

Integrates Intervals.icu training data, wellness records, workouts, and calendar events with AI assistants through MCP tools.

Category
访问服务器

README

Intervals.icu MCP Server

An MCP (Model Context Protocol) server that integrates Intervals.icu with AI assistants like Claude or ChatGPT. It exposes your training data, wellness records, planned workouts, and calendar events through a set of tools that Claude can call directly.

Features

  • Athlete profile & settings — retrieve profile info and sport-specific settings (FTP, LTHR, HR zones, pace zones)
  • Activities — list, search, and get detailed metrics for completed workouts
  • Wellness — read daily wellness records (weight, resting HR, HRV, sleep, soreness, fatigue, stress, mood)
  • Training calendar — list, create, and update planned events (workouts, races, notes, and more)
  • Routes — browse saved routes with optional GPS path data
  • Summary stats — aggregate training load, distance, and time over a date range

Available Tools

Tool Description
get_athlete_profile Athlete name, email, and preferences
get_athlete Sport settings including FTP, LTHR, max HR, and pace zones
list_activities Activities within a date range
get_activity Detailed metrics for a single activity (optionally with lap data)
search_activities Search by name or tag (use #tag for exact tag match)
get_athlete_summary Aggregate stats (count, time, distance, calories, load) for a date range
list_wellness Wellness records within a date range
get_wellness Single-day wellness record
list_routes All saved routes
get_route Route details, optionally with GPS lat/lng path
list_events Planned calendar events within a date range (filterable by category)
get_event Detailed info for a single planned event
create_event Add a planned event to the calendar
update_event Modify an existing calendar event
list_event_tags All event tags used by the athlete

Prerequisites

  • Node.js 18+
  • An Intervals.icu account
  • An Intervals.icu API key (found in Settings → API)

Setup

1. Clone and install dependencies

git clone <repo-url>
cd IntervalsMCP
npm install

2. Configure environment variables

cp .env.example .env

Edit .env:

INTERVALS_API_KEY=your_api_key_from_intervals_icu_settings
INTERVALS_ATHLETE_ID=i0

INTERVALS_ATHLETE_ID defaults to i0 which resolves to your own athlete ID.

3. Build

npm run build

Connecting to Claude

Add this server to your Claude Desktop (or any MCP-compatible client) configuration:

{
  "mcpServers": {
    "intervals-icu": {
      "command": "node",
      "args": ["/absolute/path/to/IntervalsMCP/dist/index.js"]
    }
  }
}

Claude Desktop config is typically located at:

  • macOS: ~/Library/Application Support/Claude/claude_desktop_config.json
  • Windows: %APPDATA%\Claude\claude_desktop_config.json

Development

# Watch mode — recompiles on file changes
npm run dev

# Run the compiled server directly
npm start

Project Structure

src/
  index.ts            # MCP server entry point
  intervals-client.ts # Intervals.icu API HTTP client
  tools.ts            # MCP tool definitions

推荐服务器

Baidu Map

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。

官方
精选
JavaScript
Playwright MCP Server

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。

官方
精选
TypeScript
Audiense Insights MCP Server

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。

官方
精选
本地
TypeScript
Magic Component Platform (MCP)

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。

官方
精选
本地
TypeScript
VeyraX

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。

官方
精选
本地
Kagi MCP Server

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。

官方
精选
Python
graphlit-mcp-server

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。

官方
精选
TypeScript
Exa MCP Server

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。

官方
精选
mcp-server-qdrant

mcp-server-qdrant

这个仓库展示了如何为向量搜索引擎 Qdrant 创建一个 MCP (Managed Control Plane) 服务器的示例。

官方
精选
e2b-mcp-server

e2b-mcp-server

使用 MCP 通过 e2b 运行代码。

官方
精选