io.github.davidmosiah/garminmcp
Privacy-first MCP server for Garmin Connect health, sleep, recovery and activities.
Versions
0.5.8latest0.5.70.5.60.5.50.5.4+ show 18 moreshow less
0.5.30.5.20.5.10.5.00.4.50.4.40.4.30.4.20.4.10.4.00.3.00.2.10.2.00.1.40.1.30.1.20.1.10.1.0Tools 18
garmin_cache_status Show optional local SQLite cache status. Enable with GARMIN_CACHE=sqlite or GARMIN_CACHE=true.
garmin_privacy_audit Return local privacy, cache, token-path and env-presence posture without revealing secret values.
garmin_disconnect_local 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).
garmin_daily_summary Build a practical daily summary from Garmin activity, sleep, heart-rate, HRV, stress and Body Battery when available. Read-only and non-medical.
garmin_data_inventory Inventory supported Garmin data domains, auth scope requirements, privacy boundary and recommended first calls. Does not call Garmin APIs or expose user data.
garmin_agent_manifest Machine-readable install, runtime and client guidance for AI agents. Does not call Garmin or expose secrets.
garmin_capabilities Explain supported Garmin data, privacy boundaries, recommended agent workflow and project links.
garmin_quickstart 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?'
garmin_demo 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.
garmin_profile_get 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.
garmin_profile_update 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.
garmin_onboarding 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.
garmin_auth_instructions Explain the local Garmin Connect authentication flow without asking the user to paste secrets into an agent.
garmin_get_weight_range Get Garmin weight/body-composition logs for a date range. Not medical advice.
garmin_activity_series Bounded time-series for one activity metric. Returns exact stats computed on full-resolution samples plus a downsampled series capped at
garmin_connection_status Check local Garmin config, token file, Node version, privacy mode, cache readiness and optional MCP client readiness without calling Garmin or exposing secrets.
garmin_weekly_summary Build a weekly Garmin scorecard with movement, sleep, HRV, stress, Body Battery, bottlenecks and actions. Read-only and non-medical.
garmin_wellness_context Normalize Garmin readiness, sleep score, Body Battery and recent movement load into the shared wellness_context shape for recommendation engines.
Permissions 3
network medium shell high env_vars low