Skip to main content
Glama
Sign In
GarminMCP

GarminMCP

by javiervisiedo
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python
Hybrid

Related Servers

Alternatives to GarminMCP

No user-submitted related servers found.

    Related Servers

    • coach-mcp

      snoozelieb
      A
      license
      Not graded
      quality
      B
      maintenance
      An AI training coach MCP server that integrates with Garmin Connect to provide science-based load management, code-enforced injury gates, and persistent coaching memory, keeping data local.
      325 PyPI
      3
      MIT

    • claude-garmin

      Jack-Abyss
      A
      license
      Not graded
      quality
      C
      maintenance
      MCP server that connects Garmin Connect data to Claude, enabling training analysis, recovery checks, and personalized plans based on real metrics like HRV, training load, and activities.
      24
      MIT

    • hybridlog

      Imgrund
      A
      license
      Not graded
      quality
      B
      maintenance
      MCP server that mirrors your Garmin data into a personal database and exposes tools for health summaries, training load, muscle readiness, and race analysis, with optional chat-driven insights via stdio or HTTP.
      1
      MIT

    • Garmin Connect MCP

      leewnsdud
      F
      license
      B
      quality
      D
      maintenance
      A Model Context Protocol server that integrates Garmin Connect data with LLMs to provide personalized running analysis and training plans. It enables users to monitor performance metrics, manage training loads, and receive data-driven workout suggestions based on health indicators like VO2 Max and recovery status.
      43
      5
      -

    • Garmin MCP Lite

      Golden0Voyager
      A
      license
      A
      quality
      B
      maintenance
      A lightweight Garmin Model Context Protocol server with 12 curated endpoints for endurance athletes, enabling natural-language queries of activity, training, health, device, and goal data from Garmin Connect.
      28
      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

    A4.1/5.0

    Scored across 8 tools

    Disambiguation4/5

    Each tool targets a distinct analysis slice (daily readiness, sleep/recovery, training load, activity list, activity deep-dive, longitudinal trends, body composition, workout creation), so misselection risk is low. The only real overlap is get_coach_daily_briefing, which re-synthesizes HRV, sleep, Body Battery, and yesterday's workouts that dedicated tools also return, but it is explicitly framed as the entry-point aggregator, which mitigates confusion.

    Naming Consistency5/5

    All eight tools follow a clean verb_noun snake_case convention with consistent prefixes (get_*, list_*, create_*) and domain-descriptive nouns. Requests are parameterized uniformly with target_date/start_date/end_date and response_format across the read tools.

    Tool Count5/5

    Eight tools is well-scoped for a Garmin coaching/analytics server: one aggregator, five focused health/training readers, one activity deep-dive, and one workout builder. Each tool occupies a distinct analytical role without redundant entries.

    Completeness4/5

    The read surface is comprehensive for a coaching domain (readiness, sleep, load, activity list+details, trends, biometrics), and workout creation is covered. The notable gap is workout lifecycle management: there is no way to list scheduled/uploaded workouts, update or delete one after create_structured_workout_json, nor any calendar/planned-workout visibility, which could force workarounds.

    Maintenance

    ActivityMaintained
    ResponsivenessOutdated data

    Resources