garmin-mcp@0.6.1
VERIFIED· not startedPublisher claims: "Enables AI clients such as Claude to query Garmin Connect read-only data including activities, sleep, HRV, Body Battery, training status, and challenges, and to retrieve original FIT files with Connect-IQ sensor channels." Observed in sandbox: no network, touches nothing outside the project, writes no memory.
Coverage
Not started: dependency install failed; the server itself was not observed.- Tested
- the dependency install step · every file read, file written and host contacted by what ran
- Not tested
- server startup · the tool list · tool behavior
What this means for the label: Verified here covers what ran. The server's tools were not exercised with a real credential, so nothing about their behavior is asserted; the credential summary below says what to do with that.
Before you give it your token
- It will ask for
GARMIN_MCP_TOKENSMYAUTH_APPMYAUTH_APP_KEYMYAUTH_PUBLIC_PORTMYAUTH_URLConfiguration, not credentials: FOOTER_NOTE, GARMIN_MCP_CACHE, MCP_DB- Where it talks to
- garmin.com (its own)
- What the honeypot saw
- no credential files read · no network
- What we could not test
- server startup · the tool list · tool behavior
Connect it with a scoped credential, under the guard. It asks for GARMIN_MCP_TOKENS, MYAUTH_APP, MYAUTH_APP_KEY, MYAUTH_PUBLIC_PORT, MYAUTH_URL and talks to garmin.com. Give the credential to the guard, not the server: the value never enters the server's environment and only travels to the host you bind. What the tools do with a real credential was not observed.
Never paste a credential into a chat, a ticket or a report, including ours. How the guard holds it.
Is [email protected] safe to install?
KillerSkills ran it in the KillerSkills honeypot sandbox (2 scenarios; not started: dependency install failed; the server itself was not observed) on 2026-11-13 and scored it 81/100 (Verified). In what ran, nothing we could detect went wrong: no undeclared network egress, no credential reads, no persistent instruction writes. What it does with a real credential was not observed; the static findings and the publisher carry the rest of the score. Summary: no network, touches nothing outside the project, writes no memory.
Behavior trace
Honeypot run · 0 s · 2 scenarios · 0 deviationsStatic findings
instance are environment variables (`.env.example`, docs/hosted.md).Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.## 4. Turn on developer modeFix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.In ChatGPT: **Settings → Apps & Connectors → Advanced → Developer mode**.Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.- A ChatGPT plan that offers developer mode: Plus, Pro, Business, Enterprise orFix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.# .env (see .env.example and docs/hosted.md). There is no host port: theFix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.## 4. Turn on developer modeFix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.env_file: ./.envFix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.r = subprocess.run([str(SYNC), "--check", block, str(REPO / "garmin_mcp")],Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.In ChatGPT: **Settings → Apps & Connectors → Advanced → Developer mode**.Fix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.| [Install for ChatGPT](docs/install-chatgpt.md) | Hosted only: developer mode, custom connector, troubleshooting |Fix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.MCP server mskerwiderski/MCPServerGarminConnect on Glama, built from https://github.com/mskerwiderski/MCPServerGarminConnect.Fix: Namespace tool names and keep tool descriptions literal; no instructions to the agent inside them.RUN useradd -u 1000 -m app && mkdir -p /data && chown app:app /dataFix: Request the narrowest permission that works; replace wildcards with the exact paths or hosts.(`.env.example`) plus a local `docker-compose.override.yml` for the networkFix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.- A ChatGPT plan that offers developer mode: Plus, Pro, Business, Enterprise orFix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.| [Install for ChatGPT](docs/install-chatgpt.md) | Hosted only: developer mode, custom connector, troubleshooting |Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.`docker-compose.yml` builds the image; configuration comes from `.env`Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.proc = subprocess.Popen([sys.executable, "-m", "garmin_mcp.cli", "stdio"], env=env,Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.Cost to the agent
Tokens estimated at four characters each. The tool list is re-read by the agent on every turn, so it is the number to compare between servers that do the same job: ranked across the index.
Known vulnerabilities
Vulnerability advisories (OSV) cover npm and PyPI packages; this registry has no advisory database.