Google Health MCP
⚡ Ein-Befehl-Installation mit Delx Wellness for Hermes:
npx -y delx-wellness-hermes setup— vorkonfiguriert diesen Connector und die anderen 8 in einem dedizierten Hermes-Profil.Oder binden Sie ihn eigenständig in Claude Desktop / Cursor / ChatGPT Desktop ein — siehe Installationsabschnitt unten.
Inoffizieller, Local-First-MCP-Server für die neue Google Health API v4.
Er ermöglicht es Claude, Cursor, Hermes, OpenClaw und anderen MCP-Clients, vom Benutzer autorisierte Google Health-Daten von Fitbit, Pixel Watch und unterstützten Drittanbieterquellen über den OAuth 2.0-Flow von Google zu lesen.
Beta-Status: Google empfiehlt, bis Ende Mai 2026 zu warten, bevor offizielle Google Health API-Integrationen gestartet werden, da es zu Breaking Changes kommen kann, während Entwickler-Feedback eingearbeitet wird. Dieser Connector wird absichtlich als frühe Beta für Entwickler veröffentlicht, die die API jetzt testen möchten.
Inoffizielles Projekt. Nicht mit Google, Fitbit oder Alphabet verbunden, nicht von diesen unterstützt oder gebilligt. Kein Medizinprodukt. Keine medizinische Beratung.
Beta-Tester gesucht
Der wertvollste Beitrag ist derzeit echtes Einrichtungs-Feedback von Benutzern von Fitbit, Pixel Watch, Android und der Google Health API v4.
Wenn Sie mit einem echten Konto testen können:
Führen Sie
npx -y google-health-mcp-unofficial doctoraus und bestätigen Sie, dass der OAuth-Flow klar ist.Versuchen Sie
google_health_connection_status,google_health_data_inventoryundgoogle_health_daily_summaryvon Ihrem MCP-Client aus.Eröffnen Sie ein Issue für fehlende Datentypen, verwirrende Einrichtungsschritte, client-spezifische Probleme oder Datenschutzbedenken.
Fügen Sie keine OAuth-Token, Client-Secrets oder persönlichen Gesundheitsdaten in öffentliche Issues ein.
Nützliche Links:
Related MCP server: google-health-mcp-server
Warum existiert dies?
Die Google Health API ist der Nachfolger der Fitbit Web API: neues OAuth, neue Basis-URL, v4-Endpunkt-Schema, standardisierte Datentypen, abgeglichene Streams und Rollups.
Dieses MCP bietet Agenten eine saubere Möglichkeit, die API zu entdecken, die Einrichtung zu überprüfen, sich lokal zu authentifizieren und Daten abzufragen, ohne Token in Prompts oder Agenten-Konfigurationen einfügen zu müssen.
30-Sekunden-Demo
npx -y google-health-mcp-unofficial setup
npx -y google-health-mcp-unofficial auth
npx -y google-health-mcp-unofficial doctorStarten Sie dann Ihren Agenten mit:
google_health_connection_statusgoogle_health_data_inventorygoogle_health_privacy_auditgoogle_health_daily_summary
Installation
Erstellen Sie einen Google Cloud OAuth-Client, aktivieren Sie die Google Health API und fügen Sie hinzu:
http://127.0.0.1:3000/callbackFühren Sie dann aus:
npx -y google-health-mcp-unofficial setup
npx -y google-health-mcp-unofficial auth
npx -y google-health-mcp-unofficial doctorEmpfohlene Read-Only-Scopes:
https://www.googleapis.com/auth/googlehealth.profile.readonly
https://www.googleapis.com/auth/googlehealth.settings.readonly
https://www.googleapis.com/auth/googlehealth.activity_and_fitness.readonly
https://www.googleapis.com/auth/googlehealth.health_metrics_and_measurements.readonly
https://www.googleapis.com/auth/googlehealth.sleep.readonly
https://www.googleapis.com/auth/googlehealth.nutrition.readonlyEigenständige MCP-Konfiguration:
{
"mcpServers": {
"google_health": {
"command": "npx",
"args": ["-y", "google-health-mcp-unofficial"]
}
}
}Tools
Starten Sie hier:
google_health_connection_status- lokale Konfiguration, Token, Scope und Client-Bereitschaftgoogle_health_data_inventory- unterstützte Domänen, Scopes, Datentyp-Benennung und Agenten-Flowgoogle_health_agent_manifest- maschinenlesbare Installations-/Laufzeitanleitunggoogle_health_daily_summary- tägliche Beta-Zusammenfassung aus Rollups und abgeglichenen Streamsgoogle_health_weekly_summary- wöchentliche Beta-Überprüfung
Google Health API-Methoden:
google_health_get_identitygoogle_health_get_profilegoogle_health_get_settingsgoogle_health_list_data_pointsgoogle_health_reconcile_data_pointsgoogle_health_daily_rollupgoogle_health_rollup
Diagnose:
google_health_get_auth_urlgoogle_health_exchange_codegoogle_health_privacy_auditgoogle_health_cache_statusgoogle_health_revoke_accessgoogle_health_wellness_context
Hinweise zu Datentypen
Endpunkt-Pfade verwenden Kebab-Case:
steps
sleep
heart-rate
daily-resting-heart-rate
daily-heart-rate-variability
active-zone-minutes
total-calories
weight
exerciseFilter-Ausdrücke verwenden Snake-Case:
steps.interval.civil_start_time >= "2026-05-07"
heart_rate.sample_time.physical_time >= "2026-05-07T00:00:00Z"
sleep.interval.civil_start_time >= "2026-05-07"Von der API unterstützte Quellfamilien:
users/me/dataSourceFamilies/all-sources
users/me/dataSourceFamilies/google-wearables
users/me/dataSourceFamilies/google-sourcesDatenschutz
OAuth-Token werden lokal unter
~/.google-health-mcp/tokens.jsonmit0600-Berechtigungen gespeichert.Secrets können in
~/.google-health-mcp/config.jsonoderGOOGLE_HEALTH_*-Umgebungsvariablen liegen.Tools geben niemals Zugriffstoken, Refresh-Token oder Client-Secrets zurück.
GOOGLE_HEALTH_PRIVACY_MODE=structuredist der Standard.Der
raw-Modus ist explizit und sollte nur für Debugging oder tiefe Analysen verwendet werden.
Hermes
npx -y google-health-mcp-unofficial setup --client hermes --no-auth
npx -y google-health-mcp-unofficial auth
npx -y google-health-mcp-unofficial doctor --client hermes
hermes mcp test google_healthVerwenden Sie nach Konfigurationsänderungen /reload-mcp oder hermes mcp test google_health. Starten Sie das Gateway nicht für den normalen Datenzugriff neu.
Entwicklung
git clone https://github.com/davidmosiah/google-health-mcp.git
cd google-health-mcp
npm install
npm testLinks
Google Health API: https://developers.google.com/health
REST-Referenz: https://developers.google.com/health/reference/rest
Datentypen: https://developers.google.com/health/data-types
Migrationsleitfaden: https://developers.google.com/health/migration
Delx Wellness Registry: https://github.com/davidmosiah/delx-wellness
Lizenz
MIT - siehe LICENSE.
Available Tools
26 toolsgoogle_health_agent_manifestGoogle Health Agent ManifestARead-onlyIdempotent
Machine-readable install, runtime and client guidance for AI agents. Does not call Google Health or expose secrets.
Inputs: client, response_format. Returns: links, oauth, client, hermes, +12 more
google_health_cache_statusGoogle Health Cache StatusARead-onlyIdempotent
Show optional local SQLite cache status. Enable with GOOGLE_HEALTH_CACHE=sqlite or GOOGLE_HEALTH_CACHE=true.
Inputs: response_format. Returns: path, enabled, entries, http_cache, +1 more
google_health_capabilitiesGoogle Health MCP CapabilitiesBRead-onlyIdempotent
Explain supported Google Health data, privacy boundaries, beta status and recommended agent workflow.
Inputs: response_format. Returns: links, status, creator, project, +11 more
google_health_connection_statusGoogle Health Connection StatusARead-onlyIdempotent
Check local Google Health config, token file, Node version, privacy mode, cache readiness and optional MCP client readiness without calling Google APIs or exposing secrets.
Inputs: client, response_format. Returns: ok, node, cache, oauth, +12 more
google_health_daily_rollupGoogle Health Daily RollupBRead-onlyIdempotent
Aggregate a data type over civil days using Google Health dailyRollUp. Useful for steps, distance, calories, active minutes, weight and heart summaries.
Inputs: end_date, data_type, page_size, page_token, +6 more. Returns: data, endpoint, privacy_mode
google_health_daily_summaryGoogle Health Daily SummaryBRead-onlyIdempotent
Build a practical daily summary from Google Health rollups and reconciled streams when available. Read-only, beta, non-medical.
Inputs: date, timezone, response_format. Returns: kind, generated_at
google_health_data_inventoryGoogle Health Data InventoryARead-onlyIdempotent
Inventory supported Google Health data types, auth scopes, privacy modes and recommended first calls without calling Google APIs.
Inputs: response_format. Returns: auth, kind, links, notes, +12 more
google_health_data_type_coverageGoogle Health Data Type CoverageARead-onlyIdempotent
Build a data-type coverage plan from the official Google Health API data-type table, or run explicit live read-only checks against a real OAuth account. Live mode returns only redacted status and point-count buckets, never raw health payloads.
Inputs: date, live, data_types, response_format, +1 more. Returns: kind, mode
google_health_demoGoogle Health DemoARead-onlyIdempotent
Returns realistic Pixel-Watch-style example payloads of google_health_daily_summary, google_health_wellness_context, and google_health_daily_rollup so agents see the contract before calling real Google Health APIs.
Inputs: response_format.
google_health_exchange_codeExchange Google Health OAuth CodeA
Exchange a Google OAuth authorization code for local tokens. Tokens are stored locally with 0600 permissions and are never returned. Gated: requires explicit user intent — agents must not call this autonomously.
Inputs: code (required), code_verifier (required), response_format. Returns: ok, note, scope, expires_at, +1 more
google_health_get_auth_urlGet Google Health OAuth URLARead-onlyIdempotent
Generate a Google OAuth authorization URL for Google Health API. Use this first when no local token exists.
Inputs: state, scopes, response_format. Returns: scopes, auth_url, next_step, redirect_uri, +1 more
google_health_get_identityGet Google Health IdentityARead-onlyIdempotent
Get the Google Health identity mapping for the authenticated user. Useful for Fitbit-to-Google migrations.
Inputs: privacy_mode, response_format, explicit_user_intent. Returns: data, endpoint, privacy_mode
google_health_get_profileGet Google Health ProfileARead-onlyIdempotent
Get authenticated user profile details from Google Health. Requires profile scope.
Inputs: privacy_mode, response_format, explicit_user_intent. Returns: data, endpoint, privacy_mode
google_health_get_settingsGet Google Health SettingsARead-onlyIdempotent
Get authenticated user settings such as units and timezone. Requires settings scope.
Inputs: privacy_mode, response_format, explicit_user_intent. Returns: data, endpoint, privacy_mode
google_health_list_data_pointsList Google Health Data PointsCRead-onlyIdempotent
Query detailed data points for a Google Health data type. Use kebab-case endpoint data types, e.g. steps, sleep, heart-rate.
Inputs: filter, data_type, page_size, page_token, +3 more. Returns: data, endpoint, privacy_mode
google_health_list_data_typesList Google Health Data TypesARead-onlyIdempotent
List the canonical kebab-case data_type slugs accepted by the data point, reconcile and rollup tools, with each slug's unit, OAuth scope family, and which endpoint verbs (list/reconcile/rollup) support it. Call this before list_data_points, reconcile_data_points, daily_rollup or rollup to choose a valid data_type instead of guessing a slug. Static metadata; does not call Google APIs.
Inputs: response_format. Returns: kind, note, count, source, +3 more
google_health_onboardingDelx Wellness Onboarding FlowARead-onlyIdempotent
Return the 11-question onboarding flow plus the current profile state and missing fields. Read-only — does NOT persist anything. Pair with google_health_profile_update once the user answers. Cross-connector: the same profile is shared by every Delx Wellness MCP (whoop, garmin, oura, fitbit, strava, polar, withings, apple-health, samsung-health, google-health, nourish, cycle-coach, cgm, air).
Inputs: locale, response_format.
google_health_privacy_auditGoogle Health Privacy AuditARead-onlyIdempotent
Return local privacy, cache, token-path and env-presence posture without revealing secret values.
Inputs: response_format. Returns: notes, project, cache_path, token_path, +15 more
google_health_profile_getGet Delx Wellness ProfileARead-onlyIdempotent
Read the shared Delx Wellness profile from ~/.delx-wellness/profile.json. Returns preferred name, goals, devices, training/nutrition/exercise/agent preferences and safety flags. NEVER contains OAuth tokens or API secrets. Read-only.
Inputs: response_format.
google_health_profile_updateUpdate Delx Wellness ProfileA
Persist a partial patch to ~/.delx-wellness/profile.json. Requires explicit_user_intent=true (otherwise returns USER_ACTION_REQUIRED). Rejects secret-like fields (oauth, token, secret, password, cookie, refresh, api_key, session) at write time. Use to record preferred name, goals, devices, training context, nutrition context, exercise preferences, agent preferences, and safety flags.
Inputs: patch (required), response_format, explicit_user_intent.
google_health_quickstartGoogle Health QuickstartARead-onlyIdempotent
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 Google Health?'
Inputs: response_format.
google_health_reconcile_data_pointsReconcile Google Health Data PointsBRead-onlyIdempotent
Read a reconciled stream for one data type across sources. Supports all-sources, google-wearables and google-sources data source families.
Inputs: filter, data_type, page_size, page_token, +4 more. Returns: data, endpoint, privacy_mode
google_health_revoke_accessRevoke Google Health OAuth AccessADestructive
Revoke the current Google OAuth grant and delete the local token file. Use only when the user explicitly wants to disconnect Google Health. Gated: requires explicit user intent — agents must not call this autonomously.
Inputs: response_format, explicit_user_intent. Returns: ok, note, token_path, local_tokens_cleared
google_health_rollupGoogle Health Physical-Time RollupCRead-onlyIdempotent
Aggregate a data type over physical time intervals using Google Health rollUp.
Inputs: end_time (required), start_time (required), data_type, page_size, +6 more. Returns: data, endpoint, privacy_mode
google_health_weekly_summaryGoogle Health Weekly ReviewARead-onlyIdempotent
Build a weekly Google Health scorecard with activity, sleep, heart context and missing-data awareness. Read-only, beta, non-medical.
Inputs: days, timezone, compare_days, response_format. Returns: kind, generated_at
google_health_wellness_contextGoogle Health Wellness ContextBRead-onlyIdempotent
Normalize Google Health activity/sleep context into the shared wellness_context shape for recommendation engines.
Inputs: days, notes, soreness, timezone, +2 more. Returns: notes, source, soreness, generated_at, +2 more
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 26 tools
Multiple tools overlap in purpose: connection_status, privacy_audit, and cache_status all touch local config/cache/token readiness; data_inventory, list_data_types, data_type_coverage, and capabilities all describe supported data types/scopes. The get_profile vs profile_get pair is especially easy to confuse because one is a Google Health profile and the other is a local Delx wellness profile.
All tools share the google_health_ prefix and use snake_case, but beyond that the pattern is mixed: verb-first names (get_profile, list_data_points, revoke_access) coexist with noun-first names (profile_get, profile_update) and pure noun names (capabilities, quickstart, data_inventory). This is readable but not a consistent verb_noun convention.
At 26 tools, the server crosses the threshold where the set becomes heavy. Many tools are narrow status/help/metadata endpoints (cache_status, privacy_audit, capabilities, agent_manifest, quickstart, demo) that could reasonably be consolidated into fewer, broader tools without losing capability.
The tool surface covers the main lifecycle for this domain: OAuth setup, identity/profile/settings reads, data type discovery, data point listing, reconciliation, rollups, summaries, local profile persistence, and access revocation. Minor gaps exist (e.g., no explicit token-refresh tool, no update for Google Health settings), but they are unlikely to block the core read-only Google Health workflow.
Maintenance
Related MCP Connectors
Hosted MCP server with managed OAuth for 15+ toolkits: Google Workspace, Fitbit, Oura, Kalshi, etc.
Hosted MCP server for the Healthie EHR & telehealth API: patients, appointments, charting, tasks.
MCP server for Withings health data — sleep, activity, heart, and body metrics.
Hosted MCP server for Cliniko — patients, appointments, availability, and invoices for AI agents.
Related MCP Servers
- AlicenseBqualityBmaintenanceLocal-first MCP server that connects AI agents to your Fitbit activity, sleep, heart-rate, HRV, SpO2 and weight data.33190 npm5MIT
- AlicenseAqualityDmaintenanceMCP server to read daily activity, sleep, heart rate, and body metrics from Google Health API, allowing AI assistants like Claude to access your health data. Optionally syncs health metrics to an Obsidian vault.5MIT
- AlicenseNot gradedqualityDmaintenanceSelf-hosted MCP server that aggregates personal health data from Google Health, Oura, and Withings into a single, provider-attributed interface with configurable source of truth preferences.MIT
- AlicenseCqualityDmaintenanceA local-first, model-agnostic MCP server that stores personal health data in a SQLite file and provides analysis-ready views for any AI client to log, retrieve, and reason over health records.79MIT