Spec Driven Development
MCP Server that facilitates spec-driven development workflows, not just Vibe Coding.
作者による説明(英語の原文)
Unofficial Garmin Connect server: training load, form, HRV readiness and workouts for your watch
この3つを1つのスコアにまとめることはしません。意見、測定、人気はそれぞれ別のものだからです。
このサーバーのやさしい解説はまだ書いていません。以下はレジストリから読み取った事実です。
使っているAIアプリを選んで、設定をコピーしてください。
GARMIN_DATA_DIR, GARMIN_REGION, GARMIN_ENABLE_DESTRUCTIVE必要なもの
どのアプリを使っていますか?
上でアプリを選んでください。選んだアプリを覚えておくので、次からはボタンに「…にインストール」と表示されます。
Claude Desktop → Settings → Developer → Edit Config を開き、claude_desktop_config.json にこれを貼り付けます
{
"mcpServers": {
"garmin": {
"command": "npx",
"args": [
"-y",
"garmin-mcp-server"
],
"env": {
"GARMIN_DATA_DIR": "your-value",
"GARMIN_REGION": "your-value",
"GARMIN_ENABLE_DESTRUCTIVE": "your-value"
}
}
}
}ターミナルでこれを実行します
claude mcp add garmin --env GARMIN_DATA_DIR=your-value --env GARMIN_REGION=your-value --env GARMIN_ENABLE_DESTRUCTIVE=your-value -- npx -y garmin-mcp-server動かす前に、空欄の値を入力してください。
プロジェクトの .cursor/mcp.json、または ~/.cursor/mcp.json に貼り付けます
{
"mcpServers": {
"garmin": {
"command": "npx",
"args": [
"-y",
"garmin-mcp-server"
],
"env": {
"GARMIN_DATA_DIR": "your-value",
"GARMIN_REGION": "your-value",
"GARMIN_ENABLE_DESTRUCTIVE": "your-value"
}
}
}
}ブラウザがアプリを開いてよいか確認し、そのあとアプリが設定を表示して確認を求めます。キーの値は空欄のままなので、自分で入力してください。
プロジェクトの .vscode/mcp.json に貼り付けます
{
"servers": {
"garmin": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"garmin-mcp-server"
],
"env": {
"GARMIN_DATA_DIR": "your-value",
"GARMIN_REGION": "your-value",
"GARMIN_ENABLE_DESTRUCTIVE": "your-value"
}
}
}
}ブラウザがアプリを開いてよいか確認し、そのあとアプリが設定を表示して確認を求めます。キーの値は空欄のままなので、自分で入力してください。
これはパソコンで動くサーバーですが、ChatGPTがつなげるのはインターネット上のサーバーだけです。ほかのアプリを選んでください。
選んだアプリは、この端末のCookieに保存されます。アカウントは不要です。
GARMIN_DATA_DIR envGARMIN_REGION envGARMIN_ENABLE_DESTRUCTIVE envこの設定は、作者のレジストリ登録情報から作成しています。READMEと違う場合は、READMEに従ってください。
パソコンで動くサーバーです。インストールすると、ツール一覧がAIアプリに表示されます。
誰でも見られる情報をチェックしており、コードは読んでいません。当てはまらない項目は数に入れていません。 · 2026年11月7日にチェック
レジストリ名は、リポジトリを所有するGitHubアカウント endurancetools で確認済みです
このリポジトリはまだGitHubから読み取っていません
このリポジトリはまだGitHubから読み取っていません
これはパソコンで動くため、インターネット上のエンドポイントはありません
パソコンで動き、代わりにローカルの設定を使います
パソコンで動くサーバーです。ツール一覧を読み取れるのは、インターネット上のエンドポイントがある場合だけです
レジストリでこのカテゴリにある有効なすべてのサーバーと比較しています。スターは、公開者がリポジトリの所有者である場合だけ数えます。
当てはまる基本チェック1項目のうち1項目に合格しました。コードは読んでいません。キーやトークンを追加する前に、サーバーがどんなアクセスを求めているかを確認し、必要な権限だけを持つキーを使ってください。
レジストリには必須のキーは載っていません。ただし、最初に使うときにサインインを求めるサーバーもあります。
あなたのパソコンで動きます。必要なときにAIアプリが起動し、データは作者のサーバーを通りません(サーバー自体がオンラインサービスを呼び出す場合を除きます)。
GitHubリポジトリの最終更新は–、最新バージョン(0.5.0)がレジストリに届いたのは8 日前です。
Claude Desktop、Claude Code、Cursor、VS CodeなどのMCP対応アプリで使えます。パソコンにNode.jsも必要です。
同じカテゴリには:Spec Driven Development, Remote Desktop Commander, ScienceShot science reference
同じカテゴリで、ほかの作者が作ったサーバー。スターの多い順。
カードの見方:★ GitHubスターi3つの柱:レビュー · チェック · 利用状況i更新=最新バージョンをレジストリに公開した日i
MCP Server that facilitates spec-driven development workflows, not just Vibe Coding.
Remote Desktop Commander: use files, terminal and processes on your own computers from any AI app.
Sourced, citable answers in radiation and particle physics, photonics, electronics and quantum.
作者のリポジトリから書かれたとおりにコピーしたものです。PopNx MCPは内容を確認・推奨していません。HTML、画像、スクリプトは取り除いています。リンクはこのサイトの外へ移動します。
Ask your AI assistant how your training is really going. Garmin MCP is an unofficial, open-source MCP server for your Garmin Connect data: training load, form and morning readiness computed on your machine with methods from published sports-science literature, with citations; 21 tools designed around the questions athletes ask, not a mirror of Garmin's API; a local SQLite cache that downloads only what a question needs; and structured workouts that go from the answer to your Garmin calendar and watch. It also reads activities, health, sleep, training status, body composition, gear, devices and the workout library.
Works with Claude Code, Claude Desktop, Codex, Antigravity CLI, opencode and any other MCP client (stdio or streamable HTTP).
Documentation: [endurancetools.github.io/garmin-mcp](https://endurancetools.github.io/garmin-mcp/) (getting started per client, what to ask, configuration, troubleshooting). Contributing and development: DEVELOPMENT.md.
Unofficial. Garmin and Garmin Connect are trademarks of Garmin Ltd. or its subsidiaries; this project is not affiliated with or endorsed by Garmin. The training analytics (get_load, get_readiness) are training information, not medical advice.
Requirements: Node.js 22 or newer, a Garmin Connect account, and Chrome, Edge, Brave or Chromium for the sign-in window (there is a terminal fallback).
1. Sign in once. This opens Garmin's own sign-in page in your browser. Your password never passes through the tool; only the tokens Garmin issues are stored, in ~/.garmin-mcp.
npx -y garmin-mcp-cli login
2. Add the server to your client.
| Client | Configuration |
|---|---|
| Claude Code | claude mcp add garmin -- npx -y garmin-mcp-server |
| Claude Desktop | install garmin-mcp- .mcpb from the GitHub release, or add to claude_desktop_config.json: {"mcpServers":{"garmin":{"command":"npx","args":["-y","garmin-mcp-server"]}}} |
| Codex | ~/.codex/config.toml: [mcp_servers.garmin] command = "npx" args = ["-y", "garmin-mcp-server"] |
| Antigravity CLI | agy mcp add garmin npx -y garmin-mcp-server |
| opencode | opencode.json: {"mcp":{"garmin":{"type":"local","command":["npx","-y","garmin-mcp-server"],"enabled":true}}} |
| Any other client | command npx, arguments -y garmin-mcp-server, transport stdio |
3. Ask. Nothing is downloaded until a question needs it. For example:
Optional: pre-load a range so the first questions answer instantly.
npx -y garmin-mcp-cli sync --scope all --from 2026-07-01 --to 2026-09-30
Logging in and starting the server download nothing. When a question needs days that are not in the local database, the tool downloads exactly that range, waits up to 20 s and answers; anything left keeps downloading in the background and the answer says so (meta.source is partial). Everything downloaded stays in the local database: stored days are never downloaded again unless you pass --force, so repeating a question costs nothing.
To stay gentle with Garmin, long ranges go in 7-day chunks, newest first, with a random 1-11 s pause after each chunk that actually downloaded something, at most 600 requests per day. A 429 or a Cloudflare challenge pauses all downloads for 6 h. An interrupted sync continues where it left off.
With GARMIN_AUTO_FETCH=false nothing is downloaded unless you run garmin sync or the garmin_sync tool; read tools then return the missing range in meta.sync_hint and the model asks you first.
Measured on a real account after a 90-day sync (433 requests in about an hour): answers come from the local database in 1-110 ms.
| Tool | Purpose |
|---|---|
get_activities | dense activity list with cursor paging (GAP, cadence, NP, Training Effect label, temperature when downloaded); type takes a Garmin type key (all keys in garmin://activity-types), plus name, min_duration_min/max_duration_min and a pace range |
get_activity | one activity: summary (with running dynamics, breathing, stamina, HR source), splits (laps with dynamics and workout steps), hr_zones, power_zones, weather, exercise_sets (strength sets), stream_summary (stream per km, 5 min, half or quarter), or full (all sections plus the raw stream, 50 KB pages, optional metrics and downsample_s) |
update_activity | name, type, description, RPE, feel |
download_activity_file | FIT (unzipped), GPX, TCX, KML, CSV to the download directory (GARMIN_FIT_DOWNLOAD_DIR) |
query_health | steps (with daily distance), resting HR (with daily min/max HR), HRV (with status and baseline), sleep, stress, body battery, respiration, SpO2, intensity minutes, calories (burned, and eaten when a food log is linked), floors; per day or week, with 7/28-day trends |
get_sleep | one night with stages, or a range with averages |
get_training_status | VO2max, readiness, recovery time, Garmin status, load and load focus, garmin_load_model (CTL/ATL/TSB from Garmin's training load, optionally the daily series); race predictions, endurance/hill score, fitness age, personal records, acclimation |
get_body_composition | weigh-ins in kg with trend |
get_period_summary | week, month or any from..to range up to 366 days: volume per sport, HR zones, rest days, longest/hardest, garmin_load_model at the end, health and energy averages |
list_workouts, get_workout | workout library, scheduled workouts, races and events from the calendar in any date range (default: next 60 days), readable steps |
create_workout, schedule_workouts | workouts from presets (run intervals, walk/run, easy Z2, strength circuit) or a typed definition (nestable repeats, HR/pace/power targets); create_workout with dry_run: true shows the steps and estimated duration without saving; schedule_workouts puts workouts on the calendar and takes them off again |
get_gear, get_devices | gear with distance, devices with last sync and settings |
garmin_sync | explicit download of a scope (all/activities/health/training/reference) and date range, with progress notifications |
get_load | own load model (TSS per activity from power, pace, heart rate or RPE, with the thresholds valid on each date): CTL/ATL/TSB, ACWR 7:28, monotony and strain, flags with overridable thresholds, ISO weeks per sport, 3-zone intensity split; optional daily series, per-activity TSS/IF/load source/EF and running dynamics, monthly EF trend, monthly running dynamics at a reference pace |
compare_activities | sessions side by side (ids), or the ones similar to an activity (similar_to: same type, duration and pace, optionally same route or easy only): pace, GAP, HR, power, EF, decoupling, TSS, dynamics, weather |
get_readiness | morning GO / MODIFY / REST from HRV, resting HR, sleep hours and load, with Garmin's Training Readiness, Body Battery, stress and sleep score shown, not counted; overridable rules, every signal with value, reference and rating |
get_thresholds, set_threshold | threshold history per date (LTHR per sport, LT1, HRmax, FTP, VO2max...; Garmin profile changes recorded automatically), heart rate and power zones per sport from the Garmin profile, and recording a test result, locally only |
delete_activity, delete_workout, delete_weigh_in and overwriting a saved workout (create_workout with workout_id) are only available with GARMIN_ENABLE_DESTRUCTIVE=true.
Resources: garmin://profile, garmin://gear, garmin://devices, garmin://activity-types, garmin://sync-status, and the templates garmin://activity/{id} and garmin://workout/{id} with id completion. Prompts: weekly_review, plan_next_week.
Every response is { data, meta: { source: cache|live|partial|local, fetched_at, coverage?, sync_hint? } }, as JSON text and as structuredContent matching the tool's outputSchema; failures are { error: { code, message, hint } }.
Formulas, defaults and limits of the analytics tools: docs/analytics.md. Which Garmin Connect data is covered, and what is still missing: docs/coverage.md.
garmin-mcp-cli shares the core with the server and is handy for setup and checks:
garmin login [--strategy auto|browser|curl|fetch] [--email] [--token-path]
garmin import-tokens # garmin_tokens.json from python-garminconnect 0.3.x garmin status [--json] garmin sync [--scope ...] [--from --to] [--force] [--pause ] # default: last 7 days garmin activities [--from --to --type --limit --json] garmin health [--from --to --week --json] garmin load [--from --to] [--source auto|hrtss|garmin_load] [--flags ] [--series] [--activities] [--efficiency] [--by-sport] [--json] garmin readiness [date] [--rules ] [--json] # GO / MODIFY / REST for the morning garmin thresholds [--date --param --history --json] # LTHR, LT1, HRmax ... in effect, per sport garmin thresholds add [--source test|manual] [--note] garmin thresholds export [--out ] # date,param,value,source,note garm
冒頭だけを表示しています。続きはリポジトリで読めます