Garmin Local Archive
Related Servers
Alternatives to Garmin Local Archive
No user-submitted related servers found.
Related Servers
- AlicenseBqualityAmaintenanceDownloads all your Garmin health and fitness data into a local SQLite database and exposes 45 MCP tools for AI analysis, enabling assistants to query sleep, training load, HRV, and more.48165 PyPI153AGPL 3.0
- 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
- 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 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
- AlicenseNot gradedqualityBmaintenanceThis MCP server exposes Garmin Connect health data—sleep, heart rate, HRV, stress, VO2max, and activities—to Claude through local tools, enabling natural language queries, data syncing, and statistical analysis like correlations and night-out detection.MIT
- FlicenseAqualityCmaintenanceA local MCP server that exposes Garmin Connect activity, health, and training data as tools for Claude Desktop. It provides read-only access to metrics like activities, sleep, heart rate, and training readiness.25-
TDQS
Scored across 7 tools
The core split is clear: query_health vs query_context vs query_fit_activities vs query_raw are separated by domain and by processed-vs-raw semantics, which the descriptions state explicitly. Minor overlap remains because query_raw also accepts a date range, field, and domain filter, so an agent could plausibly reach for it instead of the domain-specific query tools, and query_fit_activities is a placeholder that always returns 'not available'.
Every tool follows a clean snake_case verb_noun pattern (query_health, query_context, query_raw, query_fit_activities, get_archive_metadata, list_available_fields, refresh_cache). The verb varies appropriately with the operation type (query/get/list/refresh) rather than being arbitrarily inconsistent.
Seven tools is well-scoped for a local archive reader: three domain queries, a raw passthrough, metadata, field discovery, and cache refresh. Nothing feels padded, and no obvious capability is missing for the stated scope.
Coverage of the archive lifecycle is solid — field discovery, health/context/raw queries, metadata of many kinds, and a manual sync trigger address the main workflows. The one real gap is that activity/FIT data is unreachable until v1.8, so any fitness-activity question dead-ends at query_fit_activities.