Garmin Local Archive
Related Servers
Alternatives to Garmin Local Archive
- AlicenseBqualityAmaintenanceConnects to Garmin Connect and exposes your fitness and health data (activities, sleep, heart rate, steps, body composition) to Claude and other MCP-compatible clients.1481,348MIT
- AlicenseAqualityAmaintenanceLocal-first Garmin data warehouse with an analysis-grade MCP server. Sync once, analyze forever, even when the API is down.13142 PyPI9MIT
- AlicenseAqualityDmaintenanceA read-only MCP server that gives Claude Desktop access to your Garmin Connect data — daily health metrics, sleep, activities, training status, and body composition.6MIT
- AlicenseAqualityBmaintenanceMCP server that lets you ask questions about your Garmin training history in plain language. It ingests FIT files into DuckDB locally and exposes typed tools for analyzing activities, streams, and summaries.9MIT
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.48183 PyPI160AGPL 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.242125 npm13MIT
- 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 11 tools
Each tool has a clearly distinct role: query_health vs query_context split cleanly by body vs external data, baselines vs anomalies vs gaps vs correlate each target a different analytical question, and query_raw is explicitly scoped against query_health with guidance on when to prefer each. The descriptions actively cross-reference and steer the agent away from the most likely confusions.
All names are lowercase snake_case, but the pattern mixes verb_noun forms (query_health, refresh_cache, get_archive_metadata, list_available_fields) with bare-noun analytical tools (baselines, anomalies, gaps, correlate). Readable and predictable enough, but not a single consistent convention.
Eleven tools is well within the ideal range and each one earns its place: discovery, health/context querying, raw access, three analytics tools, gap listing, cache refresh, and archive metadata. No redundant or filler tools.
For a read-only local archive the query/analytics surface is thorough (field discovery, daily and series queries, raw access, baselines, anomalies, gaps, correlation, metadata, cache refresh). The main gap is that FIT support is entirely non-functional — query_fit_activities is a stub and gaps 'fit' always degrades — which leaves a whole promised domain uncovered.