Skip to main content
Glama
JohanBellander

garmin-mcp-server

by JohanBellander
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python
Local

Related Servers

Alternatives to garmin-mcp-server

No user-submitted related servers found.

    Related Servers

    • mcp-garmin-connect

      kavakoss
      A
      license
      B
      quality
      B
      maintenance
      An MCP server that gives LLMs access to Garmin Connect data, including training, recovery, sleep, stress, VO2 Max, and running summaries for personalized fitness advice.
      14
      1
      MIT

    • garmin-mcp

      aayush-lunawat
      A
      license
      Not graded
      quality
      C
      maintenance
      A local MCP server that exposes your Garmin Connect data—sleep, HRV, training readiness, workouts, and more—to any MCP-compatible AI assistant. Runs entirely on your machine and keeps your Garmin credentials private.
      MIT

    • garmin-connect-mcp

      jharkebusch
      A
      license
      A
      quality
      C
      maintenance
      MCP server that connects Garmin Connect to Claude Desktop, allowing users to query health and fitness data (sleep, workouts, heart rate, HRV, stress, Body Battery, etc.) in plain English and also log weight, hydration, and schedule workouts.
      25
      MIT

    • claude-garmin

      Jack-Abyss
      A
      license
      Not graded
      quality
      B
      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.
      19
      MIT

    • Garmin Open MCP

      limited
      A
      license
      A
      quality
      B
      maintenance
      Unofficial MCP server bridging Garmin Connect to MCP clients and ChatGPT, providing tools to access health data, activities, and trends via a self-hosted API.
      11
      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 29 tools

    Disambiguation4/5

    Most tools map to distinct Garmin data categories, but a few boundaries are fuzzy: get_weight and get_body_composition overlap on weight and body fat, and get_daily_summary overlaps with get_daily_steps and get_heart_rate on daily metrics. Still, an agent can usually select the right tool from the descriptions.

    Naming Consistency5/5

    The naming follows a consistent verb_noun pattern: get_* for data retrieval and download_activity_* for file exports. Plural/singular variations are minor and do not affect predictability.

    Tool Count2/5

    29 tools is excessive for a Garmin data server. Many could be consolidated, such as the five download_activity_format tools into a single exporter, and get_weight/get_body_composition into one body metrics tool. The broad scope helps justify the number, but the surface still feels over-split.

    Completeness4/5

    The server covers a comprehensive read-only Garmin domain: activities, daily summaries, body metrics, health metrics, training readiness, sleep, stress, devices, and file downloads. Minor gaps exist, such as lacking date-range endpoints for some metrics (e.g., sleep, stress) and no way to search activities beyond recent/date-based retrieval.

    Maintenance

    ActivityInactive
    ResponsivenessNo issues

    Resources