About intervals-mcp
intervals-mcp is a single-user remote MCP server for accessing and analyzing run data stored in intervals.icu. It connects directly to the service and includes interactive MCP Apps; the project no longer communicates with Strava.
Key features
- 01Access intervals.icu run data
- 02Run-data analysis tools
- 03Interactive MCP Apps
- 04Startup configuration checks
- 05Health and rate-limit status
Use cases
- 01Inspect run history through an MCP client
- 02Analyze intervals.icu data with an AI tool
- 03Display run-data workflows in MCP Apps
- 04Monitor server configuration and availability
MCP support
Provides tools and interactive MCP Apps to MCP clients through a Streamable HTTP endpoint. The server uses the configured intervals.icu API key and can require a bearer token for access.
Configuration
Local server config is the same for every client. Copy it into your client’s MCP config file.
docker run -i --rm -e INTERVALS_API_KEY -e INTERVALS_ATHLETE_ID -e TZ -e MCP_AUTH_TOKEN -e PORT -e PUBLIC_URL ghcr.io/ljcl/intervals-mcp:2.9.2INTERVALS_API_KEYSecretintervals.icu personal API key (Settings, Developer Settings)INTERVALS_ATHLETE_IDAthlete id: 0 (default, the API key's own athlete) or e.g. i12345TZIANA time zone for local dates, e.g. Australia/Sydney; unset or UTC follows the athlete's intervals.icu time zone (Etc/UTC pins UTC)MCP_AUTH_TOKENSecretShared secret (32+ characters) gating /mcp and detailed /health (recommended when internet-facing)PORTServer port, 1-65535 (default 3000)PUBLIC_URLPublic URL, used only to warn when /mcp is exposed without MCP_AUTH_TOKENLocal servers need a runtime on your machine (e.g. Node.js 18+). Config file locations differ by client; see your client’s docs.
ghcr.io/ljcl/intervals-mcp:2.9.2Streamable HTTPTools
Local servers expose tools only once running on your machine, and the maintainer has not provided a tool list.
Details
From the project READMEIntervals Extra (intervals-mcp)
A single-user remote MCP server for intervals.icu run data and analysis, with interactive MCP Apps.
All text tools and every MCP App talk to intervals.icu directly and
are verified against a real account; see docs/tools.md for
the full catalog. Configuration is checked at startup: a bad variable stops
the server with a message naming it, and the key's presence is reported on
/health.
History. This project began as strava-mcp and was migrated to intervals.icu as its data source; nothing in the server talks to Strava today.
Setup
1. Get an intervals.icu API key
- Log in to intervals.icu
- Go to Settings, Developer Settings
- Copy your personal API key
2. Configure environment
cp .env.example .env
Edit .env with your values:
INTERVALS_API_KEY=your_api_key
All variables are listed in docs/operations.md.
3. Run it
Local development (needs Bun):
bun install
bun run dev
Docker:
docker compose up -d
Prefer the prebuilt image? Pull ghcr.io/ljcl/intervals-mcp:latest, the
newest release (also on the
MCP registry as
io.github.ljcl/intervals-mcp), and point your compose image: at it instead
of building; you still supply your own API key. :edge tracks unreleased
main. Published images carry SBOM/provenance attestations you can verify; see
operations.md.
GET /health reports liveness without spending an intervals.icu API request;
with MCP_AUTH_TOKEN it also reports config and rate-limit state. Response
shapes and monitoring guidance: operations.md.
Point any client at http://localhost:3000/mcp. Repo layout, task runner,
tests, coverage gates, and Storybook workflow: docs/development.md.
Agent conventions live in AGENTS.md.
Connecting to AI Tools
Most AI tools (Claude Desktop, Claude Code, etc.) need an HTTPS URL to reach your MCP server. Since the server runs on your local network, you'll need a tunnel to expose it.
Tailscale Funnel (Recommended)
Tailscale Funnel exposes a local port to the internet over HTTPS with no configuration:
tailscale funnel --bg 3000
# → https://your-machine.tail1234.ts.net
Set PUBLIC_URL in your .env to the resulting URL.
Cloudflare Tunnel
cloudflared tunnel --url http://localhost:3000
Securing the endpoint
A tunnel makes /mcp reachable by anyone who discovers the URL, so they can
use the intervals.icu API key configured on the server (the key itself is
never exposed to them). Set MCP_AUTH_TOKEN to a
long random secret (openssl rand -hex 32) and every /mcp request requires
Authorization: Bearer <token>; each client snippet below shows where the
header goes. The secret also gates the detailed half of /health. Full
details: operations.md.
Set it in .env alongside your API key; docker-compose.yml forwards it
automatically.
AI Tool (Claude Desktop, Claude Code, etc.)
│ HTTPS
HTTPS Tunnel (Tailscale / Cloudflare)
│ HTTP (localhost:3000)
intervals-mcp Server (Docker / Bun)
│ HTTPS
intervals.icu API
Client configuration
The server works with any MCP client that supports the Streamable HTTP
transport. In every snippet below, replace https://your-public-url with
your tunnel URL (or http://localhost:3000 for local development), and
include the Authorization header only if you set MCP_AUTH_TOKEN.
Claude Desktop
Add to your Claude configuration
(~/Library/Application Support/Claude/claude_desktop_config.json on macOS):
{
"mcpServers": {
"intervals-mcp": {
"type": "url",
"url": "https://your-public-url/mcp",
"headers": { "Authorization": "Bearer your-mcp-auth-token" }
}
}
}
Restart Claude Desktop to load the new configuration.
Claude Code
claude mcp add --transport http intervals-mcp https://your-public-url/mcp \
--header "Authorization: Bearer your-mcp-auth-token"
Cursor
Add to .cursor/mcp.json in your project (or ~/.cursor/mcp.json for all projects):
{
"mcpServers": {
"intervals-mcp": {
"url": "https://your-public-url/mcp",
"headers": { "Authorization": "Bearer your-mcp-auth-token" }
}
}
}
VS Code
Add to .vscode/mcp.json in your workspace (or run MCP: Add Server from the command palette):
{
"servers": {
"intervals-mcp": {
"type": "http",
"url": "https://your-public-url/mcp",
"headers": { "Authorization": "Bearer your-mcp-auth-token" }
}
}
}
Other clients (generic Streamable HTTP)
Any client that speaks Streamable HTTP can connect to the /mcp endpoint directly. The endpoint serves the 2026-07-28 revision: clients send stateless requests carrying the io.modelcontextprotocol/* envelope keys and the Mcp-Method/Mcp-Name headers (server/discover advertises capabilities). A 2025-era client (one that opens with initialize) is served statelessly too, because claude.ai loads MCP Apps that way, but it gets no write tool: update-activity, update-wellness and update-gear need a 2026-07-28 client. POST JSON-RPC messages with an Accept: application/json, text/event-stream header. Protocol details: docs/architecture.md.
Tools
The full tool catalog, prompts, permission behaviour, and example requests live in docs/tools.md. All text tools and every MCP App's data handler talk to intervals.icu directly.
Documentation
| Doc | Contents |
|---|---|
| docs/tools.md | Full tool catalog, prompts, permission behaviour, example requests |
| docs/operations.md | Environment variables, the API key, health endpoint, rate limits, endpoint security |
| docs/architecture.md | Server architecture: transport, HTTP layer, cache, error taxonomy, analysis math |
| docs/api-notes.md | Calling the intervals.icu API: auth, endpoints, verified behaviour from Phases 1 and 2 |
| docs/mcp-apps.md | MCP App packages: shared shell, mobile, theming, per-app details |
| docs/development.md | Monorepo mechanics: Turborepo, coverage gates, Storybook gates, Docker build |
| docs/releasing.md | Release automation: Conventional Commit PR titles, release-please, publishing |
| docs/project.md | Issue tracking and project board |
| docs/Intervals_MCP_Server.md | Capability reference to upload as project knowledge in a Claude project using this server |
PRs are squash-merged and the PR title becomes the commit on main, so write it as a Conventional Commit (fix: patch, feat: minor, any ! or BREAKING CHANGE: footer major; chore:/docs:/refactor:/ci: release nothing). A CI check rejects non-conforming titles; see docs/releasing.md.
Troubleshooting
Server exits at startup: The message names the variable to fix, one line per bad variable. See operations.md.
AI tool can't reach the server — MCP requires an HTTPS URL. Use a tunnel (Tailscale Funnel or Cloudflare Tunnel) to expose your local server. See Connecting to AI Tools.
API key errors: Check /health first: api_key_configured tells you whether the server has a key set at all. If api_key_configured is true but calls still fail, the key may be wrong or revoked; generate a new one at intervals.icu, Settings, Developer Settings, and update INTERVALS_API_KEY. See operations.md.
Today's run is missing, or dates are a day off: Check time_zone and time_zone_source on /health. With TZ unset (or UTC), the server uses your intervals.icu time zone; set TZ to choose one. See operations.md.
"Cloudflare … answered with a challenge": Cloudflare, in front of intervals.icu, stopped the request before it reached intervals.icu, so this is not an API key problem. Wait a few minutes and retry. See operations.md.
Client can't connect (401 or unsupported protocol version): Each refused /mcp request writes one mcp_rejected line to the server log with its status, JSON-RPC code and, when the client sent it, its name. A 401 means the bearer token is missing or wrong. Code -32022 means the client's envelope names an MCP revision the server does not serve. See operations.md.
Is the server up and reachable? curl https://your-public-url/health. It answers without touching the intervals.icu API, so it works even when your rate limit is exhausted.
Client re-prompts for read tools after I granted them — A release likely renamed a tool or changed its input schema; grants are stored per tool identity, so that drops the grant. Releases say so in the changelog. Otherwise persistence lives in the client — check both connector-level and per-tool settings. See docs/tools.md.
License
MIT
Comments
New to MCP?
From what the protocol is to installing your first server, these answers cover most first questions.
An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.