intervals-icu-mcp
Click on "Install Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@intervals-icu-mcpWhat's my training load and sleep score for the last 7 days?"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
π intervals-icu-mcp
MCP Server untuk Intervals.icu
Hubungkan AI agent (Claude, Antigravity, atau MCP client lain) langsung ke data training Anda di Intervals.icu β activities, wellness, calendar, gear, power curves, dan custom items.
β¨ Fitur
π Activities β Ambil daftar aktivitas, detail, interval splits, dan time-series streams (power, HR, cadence, pace)
π€ Wellness β Data harian HRV, resting HR, sleep score, CTL/ATL
π Calendar / Events β List, detail, hapus event, buat planned workout & catatan
βοΈ Gear β Katalog sepatu, sepeda, dan peralatan lain
π Power Curves β Best power per durasi (MMP)
ποΈ Custom Items β Baca, buat, update, dan hapus custom item
Related MCP server: fitness-mcp-server
π€ Bonus: Running Coach AI (Template)
Project ini dilengkapi template Antigravity skill & workflow untuk membangun Running Coach AI personal berbasis data Intervals.icu Anda:
/run-reportβ Slash-command untuk analisis pasca-sesi otomatis: tidak perlu upload CSV atau screenshot manual, data diambil langsung via MCP.running-coach-analysisβ Skill yang berisi panduan analisis fisiologis (Aerobic Decoupling, Cardiac Drift, Efficiency Factor) dan format coaching report 4-bagian.
Lihat panduan konfigurasi di
.agents/README.md.
π οΈ Tools (19)
Kategori | Tool | Keterangan |
Activities |
| List aktivitas dalam rentang tanggal |
| Detail + profil fisiologis satu aktivitas | |
| Data interval/lap per sesi | |
| Time-series: power, HR, cadence, pace | |
| Catatan/komentar pada aktivitas | |
| Tambah catatan ke aktivitas | |
Wellness |
| Data wellness harian (HRV, sleep, RHR, CTL/ATL) |
Events/Calendar |
| List event kalender |
| Detail satu event | |
| Hapus event | |
| Buat/update planned workout (support workout steps) | |
| Buat/update catatan di kalender | |
Gear |
| Katalog gear |
Power Curves |
| Best power per durasi |
Custom Items |
| List custom item |
| Detail custom item | |
| Buat custom item | |
| Update custom item | |
| Hapus custom item |
Setiap tool menerima apiKey opsional (override per-call) dan sebagian besar menerima athleteId opsional (fallback ke INTERVALS_ATHLETE_ID).
π Setup
1. Install & Build
pnpm install
pnpm run build2. Konfigurasi Environment
Copy .env.example ke .env untuk testing lokal:
cp .env.example .envIsi .env dengan kredensial Anda:
INTERVALS_API_KEY=your_api_key_here
INTERVALS_ATHLETE_ID=i123456INTERVALS_API_KEY: Wajib. Ambil dari Intervals.icu β Settings β Developer Settings.INTERVALS_ATHLETE_ID: Opsional. Jika kosong, wajib dikirim sebagai argumenathleteIddi setiap tool call.
3. Konfigurasi MCP Client
Antigravity / Claude Desktop
Tambahkan ke MCP config Anda (mcp_config.json atau claude_desktop_config.json):
{
"mcpServers": {
"intervals-icu": {
"command": "node",
"args": ["/path/absolut/ke/intervals-icu-mcp/dist/index.js"],
"env": {
"INTERVALS_API_KEY": "your_api_key_here",
"INTERVALS_ATHLETE_ID": "i123456"
}
}
}
}Restart client setelah edit config.
π Debug Lokal
pnpm run inspectorMembuka MCP Inspector untuk mencoba tiap tool secara interaktif tanpa perlu connect ke client dulu.
π Struktur Project
intervals-icu-mcp/
βββ src/
β βββ index.ts # Entry point, register semua tools, jalankan stdio transport
β βββ config.ts # Load environment variables
β βββ client.ts # HTTP client (Basic Auth, error handling)
β βββ types.ts # Helper convert ApiResult β CallToolResult
β βββ tools/
β βββ activities.ts
β βββ wellness.ts
β βββ events.ts
β βββ gear.ts
β βββ powerCurves.ts
β βββ customItems.ts
βββ .agents/ # Template Antigravity Agent konfigurasi (opsional)
β βββ skills/running-coach-analysis/SKILL.md
β βββ workflows/run-report.md
βββ .env.example
βββ .gitignoreβ οΈ Known Limitations
Belum ada tool untuk athlete profile atau training zones secara langsung β bisa ditambah mengikuti pola yang sama di
src/tools/.get_athlete_power_curvesmengembalikan raw response dari API; parsing tambahan bisa dilakukan di sisi client.Belum ada rate-limit handling khusus di luar pesan error 429.
π Referensi API
Base URL:
https://intervals.icu/api/v1Auth: HTTP Basic Auth β username selalu
API_KEY, password adalah API key Anda.Swagger Docs: https://intervals.icu/api-docs.html
Struktur endpoint di project ini juga diverifikasi dari
mvilanova/intervals-mcp-server, MCP server intervals.icu versi Python.
π License
Maintenance
Resources
Unclaimed servers have limited discoverability.
Looking for Admin?
If you are the server author, to access and configure the admin panel.
Related MCP Servers
- AlicenseAqualityFmaintenanceA Model Context Protocol (MCP) server for Intervals.icu integration. Access your training data, wellness metrics, and performance analysis through Claude and other LLMs.Last updated4835MIT
- Flicense-qualityDmaintenanceProvides MCP servers for Claude to access fitness data from Strava and intervals.icu, enabling natural language queries for activity analysis, advanced training metrics, and wellness tracking.Last updated1
- Alicense-qualityDmaintenanceIntegrates Intervals.icu training data, wellness records, workouts, and calendar events with AI assistants through MCP tools.Last updated211MIT
- Alicense-qualityBmaintenanceA self-hosted, multi-tenant MCP server that exposes the Intervals.icu APIβactivities, events, wellness, power curves, gear, and custom itemsβas MCP tools for Claude.Last updatedGPL 3.0
Related MCP Connectors
Self-hosted MCP gateway: turn any API, database or MCP server into AI connectors β no code.
MCP server for AI agents to plan, verify, and deploy Cloudflare-native apps.
MCP server for Argo RPG Platform β connects AI assistants to campaign data via OAuth2
Latest Blog Posts
- Who's Calling? MCP Hosts Are an Identity Blind Spot (And the Spec Knows It)By Om-Shree-0709 on .mcpAgent IdentityOAuth 2.1
- Your AI Chatbot Just Exposed Your CEO's Salary to an InternBy Om-Shree-0709 on .Agent IdentityMCP SecurityOAuth Delegation
- Why MCP Servers Need Execution Sandboxing (And Why Your Current Stack Isn't Enough)By Om-Shree-0709 on .Agentic AiPrompt InjectionWebAssembly
MCP directory API
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/hadidwirsty/intervals-icu-mcp'
If you have feedback or need assistance with the MCP directory API, please join our Discord server