agentleFS
Sign inStart free
davidmosiahdavidmosiah/garmin-mcp/llms.txt

garmin-mcp

llms.txt13 starsChanged 6 months agoMITView on GitHub

Skill (same gates, no MCP client required): skill/SKILL.md npx -y garmin-mcp-unofficial call <tool> --json '{...}'

The file

We split this llms.txt into the rules it gives an agent

4 rules. About 0 are common, 4 are distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈4

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 0

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Start agents with garmin_connection_status and garmin_data_inventory before any data tool.

    line 10
  2. Distinctive:

    Read-only default tools: garmin_agent_manifest, garmin_capabilities, garmin_privacy_audit, garmin_connection_status, garmin_data_inventory, …

    line 11
  3. Distinctive:

    Prefer JSON responses for automation and markdown responses for human summaries.

    line 18
  4. Distinctive:

    Not medical advice. Use as trend context only — outputs are operational context, not medical, legal or financial advice.

    line 20

≈ “Common” is an estimate: at least 1 in 5 of the 3,592 llms.txt files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
llms.txt
# Garmin MCP
Unofficial local-first Garmin Connect MCP server for AI sleep, HRV, Body Battery, stress and training-readiness agents.
Repository: https://github.com/davidmosiah/garmin-mcp
Homepage: https://wellness.delx.ai/connectors/garmin
NPM: https://www.npmjs.com/package/garmin-mcp-unofficial
Primary command: npm exec --yes --package=garmin-mcp-unofficial -- garmin-mcp-server doctor
MCP command: garmin-mcp-server

- MCP registry name: io.github.davidmosiah/garminmcp
- Start agents with garmin_connection_status and garmin_data_inventory before any data tool.
- Read-only default tools: garmin_agent_manifest, garmin_capabilities, garmin_privacy_audit, garmin_connection_status, garmin_data_inventory, garmin_daily_summary, garmin_weekly_summary, garmin_cache_status.
- Auth: personal Garmin Connect credentials, prompted locally by `garmin-mcp-server auth` (not official Garmin Health API OAuth).
- Auth env for non-interactive mode: GARMIN_EMAIL, GARMIN_PASSWORD, optional GARMIN_MFA_CODE, or GARMIN_TOKEN_PATH for an existing local token file.
- Auth failures: if HTTP 429, Cloudflare, or missing responseStatus.type appears, tell the user to stop retrying and follow docs/auth.md; repeated headless retries can worsen throttling.
- Optional env: GARMIN_PRIVACY_MODE (summary|structured|raw, default structured), GARMIN_CACHE, GARMIN_CACHE_PATH.
- Note: ToS-fragile by design — Garmin does not publish a public OAuth API for consumer data.
- Pass an IANA timezone to garmin_daily_summary / garmin_weekly_summary so the Garmin calendar date is the user's local day. Empty sleep/HRV is data_quality.availability empty or failed, not a zero-sleep night.
- Prefer JSON responses for automation and markdown responses for human summaries.
- Tokens stay local under ~/.garmin-mcp/garmin_tokens.json (or GARMIN_TOKEN_PATH) and should never be printed.
- Not medical advice. Use as trend context only — outputs are operational context, not medical, legal or financial advice.

Skill (same gates, no MCP client required): skill/SKILL.md
npx -y garmin-mcp-unofficial call <tool> --json '{...}'

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

Check your setup, free