Iridium MCP Server
Connects AI agents to Iridium fitness data to query workout history, nutrition logs, and body measurements. It enables users to track exercise progress, training volume, and personalized trainer analysis through natural language.
README
Iridium MCP Server
An MCP (Model Context Protocol) server that connects AI agents like Claude to your Iridium fitness data. Query your workouts, nutrition, body measurements, training volume, and more directly from Claude Code or any MCP-compatible client.
Prerequisites
- Node.js 18+
- Iridium app with AI Data Sync enabled (Settings > AI Data Sync)
Setup
1. Enable AI Data Sync in Iridium
- Open the Iridium app on your iPhone
- Go to Settings > AI Data Sync
- Toggle Enable AI Data Sync on
- Copy your Sync ID and Sync Key
2. Install the MCP Server
npm install -g iridium-mcp-server
Or clone and build from source:
git clone https://github.com/iridium-fitness/iridium-mcp-server.git
cd iridium-mcp-server
npm install
npm run build
3. Configure Claude Code
Add the following to your Claude Code MCP settings (~/.claude/claude_desktop_config.json):
{
"mcpServers": {
"iridium": {
"command": "npx",
"args": ["iridium-mcp-server"],
"env": {
"IRIDIUM_SYNC_ID": "your-sync-id-here",
"IRIDIUM_SYNC_KEY": "your-sync-key-here"
}
}
}
}
If you installed from source, use the absolute path instead:
{
"mcpServers": {
"iridium": {
"command": "node",
"args": ["/path/to/iridium-mcp-server/build/index.js"],
"env": {
"IRIDIUM_SYNC_ID": "your-sync-id-here",
"IRIDIUM_SYNC_KEY": "your-sync-key-here"
}
}
}
}
Available Tools
| Tool | Description |
|---|---|
get_workout_history |
Get recent workout history with optional date range and category filtering |
get_workout_detail |
Get full details of a specific workout (exercises, sets, weights, reps, RPE) |
get_nutrition_log |
Get daily nutrition summaries or individual food entries for a specific date |
search_exercises |
Search the exercise database by name or muscle group |
get_exercise_progress |
Get performance history and 1RM trends for a specific exercise |
get_body_measurements |
Get body measurement history (weight, body fat, etc.) |
get_profile |
Get user profile including training goals, methodology, and experience level |
get_training_summary |
Get aggregate training statistics (total workouts, streaks, patterns) |
get_training_volume |
Get volume adaptation records per muscle group with fatigue and recovery data |
get_trainer_analysis |
Get weekly AI trainer analysis logs with recommendations and insights |
get_weekly_schedule |
Get the planned weekly training schedule |
get_workout_templates |
Get saved workout templates with exercise configurations |
Example Usage
Once configured, you can ask Claude things like:
- "Show me my workouts from last week"
- "How has my bench press progressed over the last 3 months?"
- "What did I eat yesterday?"
- "Am I hitting my protein goals?"
- "What does my training volume look like for chest?"
- "What's my weekly training schedule?"
Troubleshooting
"Missing IRIDIUM_SYNC_ID or IRIDIUM_SYNC_KEY"
Make sure both environment variables are set in your MCP server configuration. You can find these values in the Iridium app under Settings > AI Data Sync.
"API request failed (401)"
Your Sync Key may have been regenerated. Open Iridium, go to Settings > AI Data Sync, and copy the current Sync Key. Update your MCP configuration with the new key.
"API request failed (404)"
The data endpoint may not be available yet. Make sure you have synced your data at least once by opening Iridium and tapping Sync Now in Settings > AI Data Sync.
Stale data warnings
If you see a warning that data was synced a long time ago, open the Iridium app and tap Sync Now to push the latest data. The server will show staleness warnings when data is older than 24 hours.
Server not appearing in Claude Code
- Make sure the configuration JSON is valid
- Restart Claude Code after making configuration changes
- Check that Node.js 18+ is installed:
node --version
Development
# Install dependencies
npm install
# Build
npm run build
# Watch mode (rebuild on changes)
npm run dev
# Run directly
IRIDIUM_SYNC_ID=xxx IRIDIUM_SYNC_KEY=yyy npm start
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。