Samsung Health MCP
Related Servers
Alternatives to Samsung Health MCP
No user-submitted related servers found.
Related Servers
- AlicenseAqualityBmaintenanceLocal-first MCP server that reads Apple Health export files (export.xml/zip) and exposes activity, sleep, HRV, and workout data to AI agents, keeping all data on your machine.18367 npm3MIT
- AlicenseBqualityAmaintenanceA local-first MCP server that enables AI agents to read user-authorized Google Health API v4 data from Fitbit, Pixel Watch, and partners via OAuth, with tokens never leaving the machine.26586 npm75MIT
- AlicenseAqualityAmaintenanceMCP server for the Google Health API: heart rate, activity, sleep, SpO2, HRV, ECG and irregular-rhythm notifications, read into a local SQLite cache for fast offline queries and trend analysis. OAuth 2.0 with automatic token refresh, incremental sync, a cache-only offline mode, and a doctor command that diagnoses a setup without spending quota.24184 PyPI1GPL 3.0
- AlicenseBqualityCmaintenanceMCP server that provides local caching, sync, and tools for Zepp Life health data including steps, sleep, heart rate, workouts, and body measurements, supporting both file exports and cloud session access.1015MIT
- 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
- 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
TDQS
Scored across 18 tools
The data-reading tools (list_records, list_workouts, data_inventory, export_freshness, daily/weekly_summary) are reasonably distinct, but the diagnostics/meta cluster (quickstart, capabilities, agent_manifest, connection_status, privacy_audit, demo) overlaps heavily—all answer variants of 'what does this connector do and is it set up?' An agent could easily pick capabilities when connection_status or quickstart was intended.
Every tool uses the samsung_health_ prefix with snake_case, which is highly predictable. However, the suffixes mix verb_noun (list_records, profile_get) with bare nouns (capabilities, demo, agent_manifest, onboarding), so the pattern is prefix-consistent but not action-consistent.
18 tools is on the heavy side for a local CSV/ZIP export reader, and a large share are informational/diagnostic (quickstart, demo, capabilities, manifest, connection_status, privacy_audit, onboarding, freshness) rather than data operations. The core data surface would justify ~10 tools, so the set feels padded.
Coverage is solid: record listing, workout listing, daily/weekly summaries, inventory, freshness, profile read/write, cache clearing and reimport all exist for the local-export domain. Minor gaps remain (no single-record fetch or record-type enumeration helper beyond inventory), but workflows have no real dead ends.