io.github.davidmosiah/garminmcp
Privacy-first unofficial Garmin Connect MCP for AI health, sleep, activity & recovery agents.
Verdict not yet evaluated for this tool. The semantic screen takes adversarial cases first; coverage rolls out as the corpus expands (15/150 labels to graduation). The deterministic conformance probe is built but has not yet run on the public corpus, so a recorded verdict here is REVIEW or UNVERIFIED, never a clearing ALLOW. Until a verdict is recorded, an agent should treat this tool as not-yet-cleared and fall back to its own checks. Method: the eval, four-state verdict, honest limits.
Own this server? Screen its description →
GARMIN_TOKEN_PATHOptional local path for Garmin Connect tokens. Defaults to ~/.garmin-mcp/garmin_tokens.json. Create it with garmin-mcp-server auth (self-contained Node login, no Python).
GARMIN_PRIVACY_MODEOptional payload mode: summary, structured, or raw. Defaults to structured. raw means full supported Garmin Connect payloads, not unrestricted raw sensor telemetry.
GARMIN_CACHEOptional SQLite cache toggle. Set to true or sqlite to enable.
GARMIN_CACHE_PATHOptional local SQLite cache path. Defaults to ~/.garmin-mcp/cache.sqlite.
GARMIN_DOMAINOptional Garmin domain override. Use garmin.cn only for China accounts; default is garmin.com.
GARMIN_NO_CACHESet to true to bypass the in-memory HTTP response cache (60s TTL for GET only). POST/PUT/DELETE and 4xx/5xx responses are never cached regardless.
AI-powered trading strategy development: backtesting, market data, and portfolio analysis
Feature flagging and A/B testing platform with AI-first experimentation workflows.
Query Meta Ads performance data — accounts, campaigns, ad sets, ads, metrics & settings.