intervals-icu-mcp
About
Read/write Intervals.icu MCP server — 55+ tools across activities, streams, wellness, calendar, gear, and sport zones, plus structured workout generation for cycling, running, and swimming.
Details
- Author
- hhopke
- Categories
- Other
Jump to
Setup
Install intervals-icu-mcp in your MCP client (Claude Desktop, Cursor, Windsurf, and others).
Repository: https://github.com/hhopke/intervals-icu-mcp
Follow the installation instructions in the repository README, then restart your MCP client.
A Model Context Protocol (MCP) server for Intervals.icu integration. Access your training data, wellness metrics, and performance analysis through Claude, ChatGPT, and other LLMs.
Originally based oneddmann/intervals-icu-mcp(MIT licensed). This project is an independent continuation with significant bug fixes and new features — seeCHANGELOG.mdfor details.
62 tools spanning activities, activity analysis, activity messages, athlete profile, wellness, events/calendar, performance curves, workout library, gear, sport settings, and custom items — plus 4 MCP Resources (athlete profile, workout syntax, event categories, custom item schemas) and 7 MCP Prompts (training analysis, recovery check, weekly planning, and more). SeeAvailable Toolsfor the per-category breakdown.
- Get yourAPI key and athlete ID
- Add this to your Claude Desktop config:
{ "mcpServers": { "intervals-icu": { "command": "uvx", "args": ["intervals-icu-mcp"], "env": { "INTERVALS_ICU_API_KEY": "your-api-key-here", "INTERVALS_ICU_ATHLETE_ID": "i123456" } } } }
- Restart Claude and ask"Show me my activities from the last 7 days."
Prefer Claude Code, Cursor, or ChatGPT? SeeClient Configuration. Want to run from source or with Docker? SeeInstallation & Setup.
Before installation, obtain your Intervals.icu API key:
- Go tohttps://intervals.icu/settings→Developer→Create API Key.
- Copy the key, and note yourAthlete IDfrom your profile URL (format:i123456).
Nothing to install separately if you use the recommended setup.uvx(which ships withuv) automatically downloads and caches theintervals-icu-mcppackage the first time your MCP client launches it — just paste the config snippet fromClient Configurationinto your client and you're done.
git clone https://github.com/hhopke/intervals-icu-mcp.git cd intervals-icu-mcp uv sync uv run intervals-icu-mcp-auth # interactive credential setup; or create .env manually: # INTERVALS_ICU_API_KEY=your_api_key_here # INTERVALS_ICU_ATHLETE_ID=i123456
Then point your MCP client at this checkout — see theFrom sourcesnippet inside each client below.
docker build -t intervals-icu-mcp . # Interactive credential setup (creates intervals-icu-mcp.env in the current directory): touch intervals-icu-mcp.env # pre-create the file so Docker mounts it as a file, not a dir docker run -it --rm \ -v "$(pwd)/intervals-icu-mcp.env:/app/.env" \ --entrypoint= intervals-icu-mcp:latest \ python -m intervals_icu_mcp.scripts.setup_auth
Or createintervals-icu-mcp.envmanually (same format as the.envabove).
Then point your MCP client at the Docker image — see theDockersnippet inside each client below.
The server speaks MCP over stdio and works with any compliant client. Click a client to expand. If you followed Quick Start (uvx), use the first config block; if you used the source or Docker alternative above, use the matching variant inside the same collapsible.
- macOS:~/Library/Application Support/Claude/claude_desktop_config.json
- Windows:%APPDATA%\Claude\claude_desktop_config.json
{ "mcpServers": { "intervals-icu": { "command": "uvx", "args": ["intervals-icu-mcp"], "env": { "INTERVALS_ICU_API_KEY": "your-api-key-here", "INTERVALS_ICU_ATHLETE_ID": "i123456" } } } }
From source(requiresgit clone+uv sync+uv run intervals-icu-mcp-auth):
{ "mcpServers": { "intervals-icu": { "command": "uv", "args": ["run", "--directory", "/ABSOLUTE/PATH/TO/intervals-icu-mcp", "intervals-icu-mcp"] } } }
{ "mcpServers": { "intervals-icu": { "command": "docker", "args": ["run", "-i", "--rm", "-v", "/ABSOLUTE/PATH/TO/intervals-icu-mcp.env:/app/.env", "intervals-icu-mcp:latest"] } } }
Register the server as a user-scoped MCP server:
claude mcp add intervals-icu --scope user \ --env INTERVALS_ICU_API_KEY=your-key \ --env INTERVALS_ICU_ATHLETE_ID=i123456 \ -- uvx intervals-icu-mcp
Then in any Claude Code session, run/mcpto confirmintervals-icuis connected.
Add to~/.cursor/mcp.json(or the project-local.cursor/mcp.json):
{ "mcpServers": { "intervals-icu": { "command": "uvx", "args": ["intervals-icu-mcp"], "env": { "INTERVALS_ICU_API_KEY": "your-api-key-here", "INTERVALS_ICU_ATHLETE_ID": "i123456" } } } }
Restart Cursor and openSettings → MCPto verify the server is listed.
ChatGPT's custom MCP connector flow requires running the server over HTTP and exposing it via a tunnel, then registering the URL in ChatGPT's Developer Mode settings. Seedocs/chatgpt-connector.mdfor the full walkthrough, plan-tier requirements, and security notes.
Ask Claude to interact with your Intervals.icu data in natural language. A few starter prompts:
"Show me my activities from the last 30 days" "Am I overtraining? Check my CTL, ATL, and TSB" "How's my recovery this week? Show HRV and sleep trends" "Create a sweet spot cycling workout for tomorrow" "What's my 20-minute power and FTP?"
For the full catalogue of example prompts by category, seedocs/examples.md.
62 tools, 4 resources, and 7 prompt templates. One-line summary below — full reference indocs/tools.md.
Destructive tools are gated by the optionalINTERVALS_ICU_DELETE_MODEenv var (safe/full/none, defaultsafe) — a server-side gate outside the model's reach, so unregistered tools can't be invoked. Seedocs/tools.mdfor the full mode table, response envelope, and TZ-buffer rationale.
The server runs overstdioby default — the right transport for local clients like Claude Desktop, Claude Code, and Cursor. HTTP and SSE transports are available for remote or hosted use.
⚠️ MCP hasno built-in authentication— never expose an HTTP-mode server to an untrusted network without a tunnel (Tailscale, Cloudflare Tunnel) or an authenticating reverse proxy.
Seedocs/remote-deployment.mdfor transport flags and the full security model.
- Example prompts— full catalogue of natural-language prompts by category
- Tool reference— complete tool, resource, and prompt inventory
- Architecture overview— how the server, middleware, client, and tools fit together
- Remote deployment (HTTP/SSE)— transports, flags, and the security model for hosted/remote setups
- Testing guide— conventions for pytest + respx, fixtures, and running the suite
- Changelog— release history
- Adding a new tool— step-by-step workflow for contributors
Issues and pull requests are welcome. Before opening a PR, runmake can-releaselocally to match what CI enforces (ruff, pyright, pytest). For new tools, follow the pattern in.claude/skills/add-tool/SKILL.mdand add a respx-mocked test file alongside the implementation.
MIT License - see theLICENSEfile for details.
This project is not affiliated with, endorsed by, or sponsored by Intervals.icu. All product names, logos, and brands are property of their respective owners.
Read-only access to your Alma nutrition data, meals, goals, scores, workouts, weight history, pantry, and grocery list.
AI-powered cycling training coach: personalized training plans, daily workouts, nutrition, strength training, fitness metrics (FTP, VO2Max), and Strava, Garmin, Wahoo, MyWhoosh, and Rouvy integrations.
Local-first Garmin data warehouse: sync once into SQLite you own, then analyze trends, correlations, baselines and anomalies offline, even when Garmin's API breaks.
Pace is the first MCP connector that brings wearable health data directly into Claude — no third-party dashboards, no manual exports, no extra apps. Most health apps lock your data behind their own UI. Pace breaks that wall: connect once, and Claude can analyze your sleep, activity, workouts, nutrition and recovery in natural language — with full visualizations inline.
Connect Pelaris to any MCP-compatible AI assistant for personalised fitness coaching. Plan training programs, log workouts, track benchmarks, manage goals, and get data-driven coaching insights.
MCP server for Polar AccessLink API to export data from Polar watches.
8 running tools for AI agents — 86 calculators, marathon data, pace/HR/VO2max calculations.
Analyse endurance sports activities, build training plans and sync structured workouts to your sports watch.
AI workout coach MCP server. Access training data, workout history, personal records, and body progress through Claude Desktop.
Free remote MCP server giving AI assistants direct access to data from a mentoring practice: 3,400+ paid 1:1 sessions with 300+ engineering leaders since 2019.
Sign in to leave a review
Use Google, GitHub, or an email account so ratings stay tied to real people.
No reviews posted yet.
