@davidmosiah
基本情報
概要はまだありません
以下の設定を使って、このサーバーを MCP 対応クライアントに追加してください。
{
"mcpServers": {
"garmin": {
"command": "npx",
"args": [
"-y",
"garmin-mcp-unofficial"
]
}
}
}Inventory supported Garmin data domains, auth scope requirements, privacy boundary and recommended first calls. Does not call Garmin APIs or expose user data.
Machine-readable install, runtime and client guidance for AI agents. Does not call Garmin or expose secrets.
Explain supported Garmin data, privacy boundaries, recommended agent workflow and project links.
Personalized 3-step setup walkthrough for the human user. Adapts to current state (env vars set? token present? what's next?). Call this first when the user asks 'how do I connect Garmin?'
Returns realistic example payloads of garmin_daily_summary, garmin_wellness_context, and garmin_get_body_battery_day so agents see the contract before any real Garmin Connect call.
Read the shared Delx wellness profile (~/.delx-wellness/profile.json). Returns the user's preferred name, body basics, goals, devices, training context, nutrition context, agent preferences, and missing critical fields. Cross-connector — the same profile is also available from other Delx Wellness MCPs (WHOOP, Oura, Nourish, Fitbit, etc). Read-only.
Persist a partial patch to the shared Delx wellness profile (~/.delx-wellness/profile.json). REQUIRES explicit_user_intent=true. Top-level fields stored: profile (preferred_name, language, timezone, units, age_or_birth_year, height, weight, sex_or_gender_context), goals, devices, training, nutrition, preferences, safety, notes. NEVER stores OAuth tokens, API keys, refresh tokens, cookies, or any secret-shaped field — writes will be rejected at validation time. Cross-connector — the same profile is read by other Delx Wellness MCPs.
Return the 11-question Delx wellness onboarding flow (in English or pt-BR) plus the current shared profile state and missing critical fields. Read-only. The agent should ask these questions one-by-one, then call garmin_profile_update with explicit_user_intent=true to save. The same profile is reused by every Delx Wellness connector (WHOOP, Oura, Nourish, etc.) — agents can call the equivalent {connector}_onboarding tools to cover their respective domains, or rely on this one since all connectors share the same questions.
Explain the local Garmin Connect authentication flow without asking the user to paste secrets into an agent.
Get the authenticated Garmin profile using the configured privacy mode.
Get Garmin account user settings such as units and display preferences.
List devices registered to the Garmin account.
Get the primary Garmin training device when available.
Get Garmin daily movement and wellness summary for a date.
Get Garmin daily steps and summary chart for a date.
Get Garmin daily heart-rate samples and resting heart-rate context for a date. Not medical advice.
Get Garmin sleep summary, stages and sleep window for a date. Not medical advice.
Get Garmin stress summary and samples for a date. Not medical advice.
Get Garmin Body Battery daily report for a date. Not medical advice.
Get Garmin Body Battery charge/drain events for a date. Not medical advice.
Get Garmin HRV status and overnight HRV metrics for a date when available. Not medical advice.
Get Garmin training readiness for a date when supported by the device/account. Not medical advice.
Get Garmin aggregated training status for a date when supported by the device/account. Not medical advice.
Get Garmin respiration data for a date when available. Not medical advice.
Get Garmin Pulse Ox / SpO2 data for a date when available. Not medical advice.
Get Garmin intensity minutes for a date.
Get Garmin hydration summary for a date when available.
Get Garmin weight/body-composition logs for a date range. Not medical advice.
List recent Garmin activities. Supports pagination, optional date filters and privacy modes.
Get a Garmin activity summary by activity id.
Get detailed Garmin activity samples when available.
Bounded time-series for one activity metric. Returns exact stats computed on full-resolution samples plus a downsampled series capped at 500 points, so a 3-hour ride at 1 Hz never blows the context window. Prefer garmin_get_activity / splits / hr_zones first; reach for this when you actually need the shape of the effort over time. GPS is never returned here.
Get Garmin activity splits/laps by activity id.
Get Garmin activity weather by activity id when available.
Get Garmin activity heart-rate zone time by activity id when available.
Check local Garmin config, token file, Node version, privacy mode, cache readiness and optional MCP client readiness without calling Garmin or exposing secrets.
Show optional local SQLite cache status. Enable with GARMIN_CACHE=sqlite or GARMIN_CACHE=true.
Return local privacy, cache, token-path and env-presence posture without revealing secret values.
Delete the local Garmin token file. This does not change the Garmin account; use only when the user explicitly wants to disconnect this MCP. Gated by explicit_user_intent: true (requires explicit user intent).
Build a practical daily summary from Garmin activity, sleep, heart-rate, HRV, stress and Body Battery when available. Read-only and non-medical.
Build a weekly Garmin scorecard with movement, sleep, HRV, stress, Body Battery, bottlenecks and actions. Read-only and non-medical.
Normalize Garmin readiness, sleep score, Body Battery and recent movement load into the shared wellness_context shape for recommendation engines.
A local-first MCP server that connects AI agents to your Garmin sleep, HRV, Body Battery, stress, training readiness, and activities via the unofficial Garmin Connect personal-token mode. It is an independent, unofficial project built for individuals who want their AI to work with Garmin data without sharing credentials or tokens with any agent.
Install via npm, then run setup, auth, and doctor commands. After authentication, add the MCP server configuration to your client (e.g., Claude Desktop, Cursor, Hermes). Example: npx -y garmin-mcp-unofficial setup --auth then add the JSON config to mcpServers.
Sleep duration and stages, HRV status, Body Battery, stress, training readiness, training status, daily movement (steps, calories, distance, floors, intensity minutes), heart rate, activities, body composition, and hydration when supported by the device/account. Continuous device telemetry is not exposed.
Your Garmin password is never stored. The `auth` command prompts locally for credentials and MFA, then saves only short-lived Garmin Connect tokens to `~/.garmin-mcp/garmin_tokens.json` with user-only permissions. The MCP client never sees your credentials.
No. This is an unofficial project, not affiliated with, endorsed by, or supported by Garmin. It uses the unofficial Garmin Connect personal-token mode and can break if Garmin changes private auth or endpoints.
Node.js 20+ and a Garmin Connect account with active devices. Python 3 is only needed if you opt into the legacy `auth --use-python` flow; the default login is pure Node.
Yes. Set `GARMIN_PRIVACY_MODE` to `summary`, `structured`, or `raw` (default `summary`). Local read-through cache is opt-in via `GARMIN_CACHE=sqlite`. The token path and domain are also configurable via environment variables.
YC (S26) | Open Computer History | Continuously record your company computer work, map your workflows, help you find work worth automating, and power your agents' context
Request dedicated senior developers to work on your project, write job descriptions, and prep technical interviews — all without leaving your Claude chat. Just describe what you need, and Lemon.io MCP does the rest. 1–3
不止于 CSS
Couples therapist Figs O'Sullivan (LMFT, 17 years, endorsed by Sue Johnson, creator of EFT) inside your AI. Ask relationship questions answered from his clinical writing, name the pattern in a fight, get a three-step rep
PickFu MCP is a Model Context Protocol (MCP) server that connects AI assistants, developers, marketers, product managers, and AI agents to PickFu's consumer research platform. It enables users to create surveys, conduct
コメント