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/kavakoss/mcp-garmin-connectWrote 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/kavakoss/mcp-garmin-connect/garmin)<a href="https://agentmods.dev/mcp/kavakoss/mcp-garmin-connect/garmin"><img src="https://agentmods.dev/badge/mcp/kavakoss/mcp-garmin-connect/garmin/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/kavakoss/mcp-garmin-connect/garmin"><img src="https://agentmods.dev/badge/mcp/kavakoss/mcp-garmin-connect/garmin.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
garmin 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 8d 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
{
"garmin": {
"command": "uv",
"args": [
"--directory",
"..",
"run",
"garmin-mcp",
"serve",
"--demo",
"--transport",
"stdio"
]
}
}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.
- 8d ago First seen · 15 lines scan A 2c446c981961
garmin is an MCP server published in the GitHub repository kavakoss/mcp-garmin-connect (1 stars, last pushed 9d 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 2026-10-28.
Other mcp servers, from other repositories
garminmcp
Privacy-first unofficial Garmin Connect MCP for AI health, sleep, activity & recovery agents. Runs locally from the garmin-mcp-unofficial npm package. Needs 6 environment variables to run.
long-run-hybrid-coach
Adaptive running and strength coaching for the long run. Remote server at mcp.paceandstaystrong.com.
long-run-hybrid-coach
MCP server "long-run-hybrid-coach", hosted remotely at mcp.paceandstaystrong.com, as configured in atomchung/long-run-hybrid-coach.
garmin-mcp
MCP server exposing Garmin Connect data to Claude. Runs locally from the garmin-mcp Python package.
macrofactor-mcp
Unofficial local fueling and recovery decision engine; not affiliated with MacroFactor or Stronger By Science; not medical advice. Runs locally from the macrofactor-mcp Python package. Needs 3 environment variables to run.
mcp-server
A custom MCP server that provides useful tools and resources for AI assistants. Runs locally from the mcp-server Python package.