Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
git clone --depth 1 https://github.com/davidmosiah/garmin-mcpWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/mcp/davidmosiah/garmin-mcp/garminmcp)<a href="https://agentmods.dev/mcp/davidmosiah/garmin-mcp/garminmcp"><img src="https://agentmods.dev/badge/mcp/davidmosiah/garmin-mcp/garminmcp/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/mcp/davidmosiah/garmin-mcp/garminmcp"><img src="https://agentmods.dev/badge/mcp/davidmosiah/garmin-mcp/garminmcp.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
garminmcp scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 1mo ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
{
"garminmcp": {
"command": "npx",
"args": [
"-y",
"garmin-mcp-unofficial"
],
"env": {
"GARMIN_TOKEN_PATH": "",
"GARMIN_PRIVACY_MODE": "",
"GARMIN_CACHE": "",
"GARMIN_CACHE_PATH": "",
"GARMIN_DOMAIN": "",
"GARMIN_NO_CACHE": ""
}
}
}What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 1mo ago First seen · 17 lines scan A de6ea7f4c7ee
garminmcp is an MCP server published in the GitHub repository davidmosiah/garmin-mcp (13 stars, last pushed 8d ago), licensed MIT. Its token cost is not measured: an MCP server costs its tool schemas, not its config file. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other mcp servers, from other repositories
mcp-server-whoop
Local-first, read-only WHOOP MCP server for recovery, sleep, strain, workouts, and body signals. Runs locally from the mcp-server-whoop npm package.
garmin-mcp
MCP server exposing Garmin Connect data to Claude. Runs locally from the garmin-mcp Python package.
whoop-mcp-server
MCP server "whoop-mcp-server" as configured in yuridivonis/whoop-mcp-server. Runs in Docker (ghcr.io/yuridivonis/whoop-mcp-server:1.4.1). Needs 7 environment variables to run.
withings
MCP server for Withings health data — sleep, activity, heart, and body metrics. Remote server at withings-mcp.com.
garmin-local-mcp
Local-first Garmin data warehouse with an analysis-grade MCP server. Sync once, analyze forever - even when the API is down. Runs locally from the garmin-local-mcp Python package. Needs 1 environment variable to run.
withingsmcp
Privacy-first, unofficial Withings MCP server for AI health, sleep, activity and heart-rate agents. Runs locally from the withings-mcp-unofficial npm package. Needs 8 environment variables to run.