Skip to main content
Glama
indaco

Garmin Personal MCP

by indaco
OverviewSchemaSourceRelated ServersDiscussionsAdmin
TypeScript
Local

Related Servers

Alternatives to Garmin Personal MCP

No user-submitted related servers found.

    Related Servers

    • Threshold

      KareemmSayed
      A
      license
      Not graded
      quality
      B
      maintenance
      Connects Garmin Connect to AI assistants, answering questions about training, sleep, HRV and recovery with metrics computed in code rather than guessed from raw JSON. Queries daily readiness, training load, activity FIT analysis and personal records through a self-hosted Cloudflare Worker with OAuth.
      9 npm
      7
      MIT

    • garmin-mcp

      mskerwiderski
      A
      license
      Not graded
      quality
      B
      maintenance
      Enables reading and analyzing Garmin Connect data—activities, health metrics, FIT files, and challenges—through natural language, for AI assistants like Claude and ChatGPT.
      MIT

    • durely insights

      durely
      A
      license
      A
      quality
      B
      maintenance
      Enables AI assistants to query a user's own Garmin Connect training, health, and recovery history through Garmin's official Personal API, backed by a local cache and built-in analysis tools.
      21
      394 npm
      2
      Apache 2.0

    • runcoach

      edxleon
      A
      license
      A
      quality
      A
      maintenance
      Provides Claude Code and Claude Desktop with safe, read-only access to your local Garmin training data, readiness decisions, run details, and trends so you can get coaching advice in natural language.
      15
      7
      MIT

    • garmin-personal-api-mcp

      aaronhaddad
      A
      license
      A
      quality
      A
      maintenance
      Enables Claude to read your own Garmin Connect data—activities and exact pace splits, VO2 max and training effect, sleep, HRV, Body Battery, stress, weight and more—through Garmin's official Personal API, with no password or scraping. Access is read-only and runs entirely on your machine, so you can ask natural-language questions about training and recovery.
      23
      0
      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

    A3.6/5.0

    Scored across 19 tools

    Disambiguation4/5

    Most tools target clearly distinct resources or actions, especially the activity-detail tools and the health metric getters. There is some intentional overlap between the aggregate getDashboardData/garminGet tools and the specialized getters, and writeDashboard vs editDashboard could be confused at first glance, but the descriptions clarify their roles.

    Naming Consistency4/5

    Most names follow a predictable camelCase verb_noun pattern: getActivity, getSleep, listActivities, writeDashboard, editDashboard, scheduleDashboardRefresh. garminGet is an outlier in both prefix and verb-order convention, and downloadActivityFit is a slight deviation, but the set remains readable and mostly consistent.

    Tool Count4/5

    With 19 tools, the server is slightly above the typical 3-15 range, but the domain is broad: health metrics, activity detail, FIT files, dashboard generation, editing, and scheduling. Most tools have a clear purpose, so it is not excessively bloated.

    Completeness4/5

    The server covers core read paths for activities, sleep, HRV, heart rate, body battery, weight, fitness age, zones, and dashboard lifecycle operations, with garminGet as a read-only fallback for uncovered endpoints. Minor gaps remain, such as direct write/update operations for many health metrics and dashboard deletion/cleanup, but these are not major workflow blockers.

    Maintenance

    ActivityMaintained
    ResponsivenessNo issues

    Resources