Intervals.icu MCP Server
Enables interaction with Intervals.icu data, including activities, wellness, and calendar events, via natural language.
README
Intervals.icu MCP Server
This is a Model Context Protocol (MCP) server for Intervals.icu. It allows you to interact with your Intervals.icu data, including activities, wellness data, and calendar events.
Configuration
You need an API Key and your Athlete ID from Intervals.icu.
Environment Variables
| Variable | Description |
|---|---|
INTERVALS_ATHLETE_ID |
Your Intervals.icu Athlete ID (e.g., i12345) |
INTERVALS_API_KEY |
Your Intervals.icu API Key |
Setting Environment Variables
macOS / Linux
You can set environment variables in your terminal session or add them to your shell configuration file (e.g., .bashrc, .zshrc).
export INTERVALS_ATHLETE_ID="your_athlete_id"
export INTERVALS_API_KEY="your_api_key"
To make them permanent, add the lines above to your ~/.zshrc or ~/.bashrc file and run source ~/.zshrc (or source ~/.bashrc).
Windows (Command Prompt)
set INTERVALS_ATHLETE_ID=your_athlete_id
set INTERVALS_API_KEY=your_api_key
Note: This sets the variables for the current session only. To set them permanently, use the System Properties dialog or setx.
Windows (PowerShell)
$env:INTERVALS_ATHLETE_ID="your_athlete_id"
$env:INTERVALS_API_KEY="your_api_key"
To set them permanently:
[System.Environment]::SetEnvironmentVariable('INTERVALS_ATHLETE_ID', 'your_athlete_id', [System.EnvironmentVariableTarget]::User)
[System.Environment]::SetEnvironmentVariable('INTERVALS_API_KEY', 'your_api_key', [System.EnvironmentVariableTarget]::User)
Usage
Run the server using the package:
npx @moxus/intervals-mcp
Or if running from source:
node dist/index.js
Verify Command
You can verify your configuration and connection to Intervals.icu using the verify command. This will attempt to fetch your athlete profile.
npx @moxus/intervals-mcp verify
If successful, you will see your athlete details. If it fails, check your API key and Athlete ID.
Gemini Installation
The simplest way to install this MCP server for Gemini is using the extension:
gemini extension install https://github.com/moxus/intervals-icu-gemini
For more details, refer to the Intervals.icu Gemini Extension repository.
Manual Configuration (Alternative)
To add this MCP server to a CLI agent like gemini-cli (or similar agents that support MCP) manually, you typically need to configure the agent to spawn this server process.
Assuming gemini-cli supports an MCP configuration file (like mcp_config.json or command line arguments), you would add an entry for @moxus/intervals-mcp.
Example configuration (conceptual):
{
"mcpServers": {
"intervals": {
"command": "npx",
"args": ["-y", "@moxus/intervals-mcp"],
"env": {
"INTERVALS_ATHLETE_ID": "your_athlete_id",
"INTERVALS_API_KEY": "your_api_key"
}
}
}
}
Or if you are running it locally from source:
{
"mcpServers": {
"intervals": {
"command": "node",
"args": ["/path/to/intervals-icu-mcp-ts/dist/index.js"],
"env": {
"INTERVALS_ATHLETE_ID": "your_athlete_id",
"INTERVALS_API_KEY": "your_api_key"
}
}
}
}
Consult the documentation of the specific agent you are using for the exact configuration format.
Tools
get_athlete_profile: Get athlete details.list_activities: Get activities within a date range.get_activity: Get full details of an activity.list_wellness: Get wellness logs.list_workouts: Get workouts from the library.create_workout: Create a workout in the library.list_events: Get calendar events.create_event: Create an event (workout, note, etc.) on the calendar.update_event: Update an existing event.delete_future_event: Delete an event.
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。