Skip to main content
Glama
partymola

google-health-mcp

by partymola
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python
Local

Related Servers

Alternatives to google-health-mcp

No user-submitted related servers found.

    Related Servers

    • google-health-mcp-server

      madfreakz
      A
      license
      A
      quality
      D
      maintenance
      MCP 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.
      5
      MIT

    • Google Health MCP

      davidmosiah
      A
      license
      B
      quality
      A
      maintenance
      A 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.
      26
      345 npm
      66
      MIT

    • personal-health-mcp

      adamconde
      A
      license
      Not graded
      quality
      D
      maintenance
      Self-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

    • Google Health Broker

      zhanjinfeng
      A
      license
      Not graded
      quality
      B
      maintenance
      Self-hosted multi-user Google Health OAuth broker and read-only Agent API with remote MCP support. Enables users to connect their Google account and grant agents secure access to activity, sleep, heart, HRV, SpO2, and other health metrics via revocable per-token authentication.
      3
      MIT

    • zepp-mcp

      DhavalBhimani44
      A
      license
      A
      quality
      A
      maintenance
      MCP server that reads Zepp/Amazfit health and workout data, exposing tools for daily summaries, sleep, heart rate, and workout details to any MCP client.
      8
      3
      MIT
    Deploy Server
    One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

    TDQS

    A4.3/5.0

    Scored across 24 tools

    Disambiguation4/5

    Most tools target clearly distinct metrics or actions, and descriptions explicitly separate overlapping granularities like sleep vs sleep_sessions, weight vs weight_readings, and skin vs core temperature. A few zone-related (heart_rate vs AZM) or aggregate-vs-raw (trends vs getters) pairs could cause brief hesitation, but the descriptions resolve them.

    Naming Consistency4/5

    All names use snake_case with a consistent health_ prefix, and getters follow the health_get_<metric> pattern. Minor deviations are health_sync and health_trends, which are readable and conventional for their distinct actions.

    Tool Count3/5

    At 24 tools, the surface is in the heavy 16-25 range and creates a large selection space for an agent. The breadth of distinct Google Health metrics means few tools are truly redundant, but some consolidation (e.g., weight vs weight_readings, sleep vs sleep_sessions) could reduce the load.

    Completeness5/5

    The set covers a wide range of health data types—activity, heart, sleep, body composition, temperature, food, ECG, devices, profile—plus sync, trends, and all-time stats. For a read-only health API, there are no obvious dead ends; every major metric appears accessible.

    Maintenance

    ActivityActive
    ResponsivenessNo issues

    Resources