garmin-local-mcp
Related Servers
Alternatives to garmin-local-mcp
- AlicenseAqualityAmaintenanceFitness AI - MCP server providing AI-powered tools and automation by MEOK AI Labs511 npmMIT
- FlicenseBqualityCmaintenanceA personal remote MCP server for fitness data that provides read-only tools to query Garmin Connect activities and Hevy workouts, enabling users to list, retrieve, and analyze exercise records through natural language.13-
Related Servers
- FlicenseNot gradedqualityDmaintenanceA multi-platform fitness MCP server that syncs data from Garmin, Strava, Google Fit, and Suunto into a local DuckDB database and provides analytics tools via MCP.1-
- AlicenseNot gradedqualityAmaintenanceMCP 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.1MIT
- AlicenseBqualityAmaintenanceLocal-first MCP server that connects AI agents to your Garmin sleep, HRV, Body Battery, stress, training readiness and activities, keeping tokens on your machine.42262 npm12MIT
- AlicenseNot gradedqualityCmaintenanceA 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
- AlicenseBqualityAmaintenanceMCP server for local fitness-data extraction and analysis from Garmin Connect, Intervals.icu, and Strava. Provides read-only analytical tools over DuckDB and targeted Strava enrichment.3527 npmAGPL 3.0
- AlicenseAqualityBmaintenanceA local MCP server that caches Garmin Connect data in SQLite for fast, read-only queries, with tools for bulk import, rate-limited sync, and failure alerts.9MIT
TDQS
Scored across 12 tools
Each tool has a clearly distinct purpose: auth_status and sync_status are separate status checks, sync and import_fit bring in data via different channels, query_metrics and get_day operate at different granularities, and the analytic tools (anomalies, correlate, baselines) are conceptually separate. No two tools appear to do the same thing.
Naming is mixed: some tools follow a verb_noun pattern (get_day, list_activities, query_metrics, import_fit, get_activity), but others are bare verbs (sync, correlate), noun-only (anomalies, gaps, baselines), or compound nouns (auth_status, sync_status). The convention is readable but not consistently applied across the full set.
Twelve tools is right-sized for a local Garmin data store covering sync, import, query, and analysis. Each tool earns its place without redundancy, and the count stays within the well-scoped 3-15 range.
The surface covers core workflows well: data ingest (sync, import_fit), status (auth_status, sync_status, gaps), query (get_day, query_metrics, list_activities, get_activity), and analysis (anomalies, correlate, baselines). Minor gaps exist—no metric enumeration tool, no data deletion/update, and activity detail is deliberately summary-only—but these don't block the primary use case.