Skip to main content
Glama
Lander-garmin

garmin-mcp

by Lander-garmin
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python
Hybrid

Related Servers

Alternatives to garmin-mcp

No user-submitted related servers found.

    Related Servers

    • garmin-mcp

      Tyler-Irving
      A
      license
      A
      quality
      B
      maintenance
      Enables Claude to access and query your Garmin Connect data, including sleep, activities, training load, and health metrics, through a set of read-only MCP tools.
      28
      214 PyPI
      4
      MIT

    • garmin-mcp

      Bartolome69
      A
      license
      A
      quality
      B
      maintenance
      Connects Claude to your Garmin Connect account to read activities, health metrics, and sleep data, and to create and schedule structured workouts directly onto your watch, all locally without exposing credentials.
      8
      3
      MIT

    • garmin-mcp

      wiande00
      A
      license
      Not graded
      quality
      B
      maintenance
      Enables Claude and other MCP clients to query Garmin Connect health, training, activity, and body data, analyze FIT files, and create structured workouts that sync to a Garmin watch.
      MIT

    • Garmin Health MCP Server

      eversonl
      A
      license
      A
      quality
      D
      maintenance
      Enables Claude Desktop to access and analyze Garmin wearable health data including sleep, HRV, Body Battery, and activity metrics. Users can query their health trends, track recovery, and generate interactive HTML dashboards using natural language.
      9
      6
      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

    B3.2/5.0

    Scored across 63 tools

    Disambiguation2/5

    Many tools have fuzzy boundaries: get_daily_summary, get_daily_briefing, and get_stats_and_body all return overlapping daily snapshots, and get_recent_activities, get_activities_by_date, and get_last_activity serve nearly the same retrieval purpose. Activity-level tools like get_activity_details, get_activity_timeseries, get_activity_split_summaries, and get_activity_typed_splits also overlap enough that an agent could easily select the wrong one.

    Naming Consistency5/5

    The tool names follow a very consistent verb_noun pattern: nearly all reads are get_* and writes use preview_, create_, delete_, schedule_, unschedule_, and list_. All names are snake_case with predictable prefixes, making the naming style highly uniform across the entire set.

    Tool Count1/5

    63 tools is far beyond the 3-15 well-scoped range and well into the 50+ extreme-mismatch territory. While Garmin has a broad data surface, this many tools creates navigational overhead and many could be consolidated into parameterized or grouped endpoints.

    Completeness4/5

    The read surface is exhaustive, covering sleep, HRV, body battery, stress, activities, workouts, nutrition, menstrual data, and more. The write surface covers workout preview/create/list/schedule/unschedule/delete, with the main gap being no workout update or edit flow.

    Maintenance

    ActivityMaintained
    ResponsivenessNo issues

    Resources