Comprehensive Model Context Protocol server for managing Home Assistant through AI assistants.
Nothing to run from here
Garmin is installed from its publisher's own source and answers where it runs, so this marketplace is not in the path of a single call. There is no address here to send one to, and a panel that pretended otherwise would be showing you an answer we made up. Install it and call it from your own client — the Installation tab has the entry for each one.
100/100
trust score
760
downloads a day
local
runs on your machine
26
tools declared
What it does
Ask your AI assistant about your Garmin training, sleep and recovery data
Quickstart
# 1 — add it to Claude Code
claude mcp add --scope user --env 'GARMIN_API_KEY=${GARMIN_API_KEY}' --transport stdio colincooperio-garmin-mcp '--' npx -y garmin-mcp
# 2 — ask your agent for something these tools do
# get_readiness, summarize_wellness, get_profile and 23 more
It needs GARMIN_API_KEY: this reads it from your environment, so export it first.
Garmin costs nothing on mcprush: there is no plan to choose here, no cap to set and nothing mcprush can bill you for.
Publishernot claimed
COAll 1 server
colincooperio1 server
1 category
Collected from a public index. Nobody has claimed this account, so nothing here was written by its author — claim it if it is yours.
Installation
Where are you running it?
Every route below installs the same thing and ends at the same approval screen. This one runs on your machine: your client starts Garmin as a process under your own user, with your files and your network, so the tool surface below is what it can do to your computer rather than to a server somewhere else. Its scan result is on the Security tab — read the surface before you approve it.
Claude Codedeclared by this listing
This is a public server: you run it yourself and this marketplace is not in the path. You need Node.js — the current LTS (24) is the safe choice; npx comes with it. Claude Code registers it in one command; --scope user makes it available in every project. Claude Code reads GARMIN_API_KEY (Your Garmin Personal API key (Garmin Connect > Settings > Personal API Token)) from your environment each time it starts the server, so the value stays out of its config: export it in your shell profile (macOS, Linux), or run setx GARMIN_API_KEY … and open a new terminal (Windows). The '--' is in quotes so that PowerShell passes it on.
claude mcp add --scope user --env 'GARMIN_API_KEY=${GARMIN_API_KEY}' --transport stdio colincooperio-garmin-mcp '--' npx -y garmin-mcpReconnect, or start a new session, and the tools appear in the model’s tool list.
Free on mcprush, and it runs from its publisher’s own package: this marketplace is not in the path, so there is no key of ours to hold and no card to add.
What it asks of you
It reaches a system of yours, so it needs your own credential rather than the publisher’s: GARMIN_API_KEY — Your Garmin Personal API key (Garmin Connect > Settings > Personal API Token). You set it in your own client’s config, on your machine — this marketplace never holds it.
What it writes
One config entry your client uses to start the process locally. A local server runs with your file system and your network, which is why it is priced without metering.
What you approve
26 tools, with what each one reads, writes and reaches shown before you agree — the same list on every route above. Read the tool surface.
Tool surface
What the model actually sees. Descriptions are diffed on every release — see version history.
Read from its source code. A server that builds its tool list when it starts can list more tools than this.
Best first call for 'how recovered am I', 'should I train hard today', 'how did I sleep last night'.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| date | no | YYYY-MM-DD, or 'today' / 'yesterday' (resolved in the user's Garmin time zone). |
Best tool for wellness trends over weeks or months ('has my sleep improved', 'resting HR trend this year', 'stress lately').
| Parameter | Type | Required | Notes |
|---|---|---|---|
| period | string | no | Named period resolved in the user's time zone (weeks start Monday). Use instead of start_date/end_date. |
| start_date | string | no | First day, YYYY-MM-DD, inclusive. Required unless period is given. |
| end_date | string | no | Last day, YYYY-MM-DD, inclusive. Defaults to today. |
| group_by | string | no | — |
| include | array | no | Data sources to include. Drop ones the question doesn't need for a faster answer. |
User profile settings (units, measurement system, birth year, etc.) and heart-rate zones. Useful context before interpreting training data.
No parameter schema on file.
Heart rate for one day: resting, min, max, 7-day resting average, and hourly min/avg/max in local time.
No parameter schema on file.
List individual recorded activities (runs, rides, swims, strength, etc.) with the activity_id needed for get_activity and get_activity_analysis.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| sort_by | string | no | Sort field. Use distance or averageSpeed to find longest or fastest. |
| sort_order | string | no | — |
| detail | string | no | — |
| limit | integer | no | Max results (1-100). |
| start | integer | no | Offset for paging. |
Best tool for activity totals and trends (e.g. 'how far did I run each month', 'has my pace improved').
| Parameter | Type | Required | Notes |
|---|---|---|---|
| start_date | string | no | First day, YYYY-MM-DD, inclusive. Required unless period is given. |
| end_date | string | no | Last day, YYYY-MM-DD, inclusive. Defaults to today. |
| group_by | string | no | — |
One activity in detail: distance, times, pace (per km and mile), speed, HR, cadence, running dynamics, power, training effect and load, temperature, RPE/feel, and split summaries (warm-up/active/cool-down totals, not per-km; use get_activity_analysis for km/mile splits and laps).
No parameter schema on file.
Side-by-side compact detail for 2-5 activities (same fields as get_activity), fetched in parallel.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| activity_ids | array | yes | 2-5 Garmin activity IDs. |
The planned workout linked to one recorded activity, if any: workoutName, sport and steps, each with intensity, durationType/durationValue (metres for DISTANCE)
| Parameter | Type | Required | Notes |
|---|---|---|---|
| activity_id | string | yes | Garmin activity ID, from search_activities. |
Per-km or per-mile splits, the watch's laps / workout reps, best efforts, time in HR zones and first-vs-second-half drift for ONE recorded activity,
No parameter schema on file.
Menstrual cycle tracking as of one date, in two parts returned as Garmin sends them: summary (Garmin's cycle summary for that date) and dayView (Garmin's day view for that date, with anything logged).
| Parameter | Type | Required | Notes |
|---|---|---|---|
| date | yes | YYYY-MM-DD, or 'today' / 'yesterday' (resolved in the user's Garmin time zone). |
One night's sleep, same compact shape as get_sleep_summaries. Use detail='full' for Garmin's complete record.
No parameter schema on file.
HRV summary plus individual readings for one night, times in local 'YYYY-MM-DD HH:MM'. Use get_hrv_summaries unless the readings themselves matter.
No parameter schema on file.
SpO2 for one day: average, lowest, sleep average, 7-day average and hourly averages, times in local 'YYYY-MM-DD HH:MM'. detail='full' adds every reading and altitude data.
No parameter schema on file.
Garmin's fitness age as of a date, plus the components behind it.
No parameter schema on file.
Food log for one day: nutrition goals, calories and nutrients consumed, and per-meal breakdown.
No parameter schema on file.
One flat row per day: steps, distance, floors, calories, resting/min/max HR, intensity minutes, stress, Body Battery, respiration, SpO2, hydration.
No parameter schema on file.
Night-by-night sleep over a range, one compact row per night filed under the date the user woke up.
No parameter schema on file.
Daily heart rate variability over a range: overnight average, 5-minute high, 7-day average, baseline band, status.
No parameter schema on file.
Daily Body Battery (Garmin's 0-100 energy estimate) over a range, one compact row per day.
No parameter schema on file.
Day-by-day all-day stress over a range, one row per day as Garmin returns it.
No parameter schema on file.
Day-by-day steps over a range, one row per day as Garmin returns it.
No parameter schema on file.
Garmin's wellness activity summaries over a range: all-day movement records kept apart from recorded workouts.
No parameter schema on file.
Weight and body composition measurements over a range, from a Garmin smart scale or entered manually in Garmin Connect.
No parameter schema on file.
Water intake the user logged in Garmin Connect, day by day over a range.
No parameter schema on file.
The weight goal the user set in Garmin Connect that was in effect over a range, with its goal range.
No parameter schema on file.
Free
$0 forever
- Every tool, no call limit
- No card, and mcprush charges nothing for it
- Source published under MIT
- Runs on your machine — nothing of it reaches our gateway
- Nothing to cap, because mcprush bills nothing
What counts against your monthly calls
| Tool | Unit | Calls used | Out of the allowance |
|---|
Nothing here is billable: mcprush charges nothing to install Garmin or to call it, at any volume.
Call allowance · this installenforced at the gateway
Monthly allowance, in calls
—
—
Alert at 80% · then the tool returns a normal MCP error
Used this month: —
ATrust score 100 / 100
Release 1.3.0 · scanned 10 Nov 2026
Two independent axes, because powerful and malicious are different questions. The grade is threat only. The capability level is blast radius, and it is never a penalty on the grade — it is priced as one subtract-only term in the score, where you can see it.
Threat score100
Client score100
Findings0 threat · 0 capability
Capabilityminimal
Coveragesource
Verificationsource
Surface digest1df701182cbf62652735a8c889a35800cd5b2d054c36f8ee81e4b92be9858fff
Score vectorthreat 100 → client 100
| Term | Level | What it prices | Points |
|---|---|---|---|
| capability-exposure | minimal | capability blast radius (minimal) — client exposure if the model is manipulated | −0 |
| verification-discount | source | publisher verification (provenance) — cryptographic build provenance ties the artifact to its source | −0 |
| coverage-honesty | source | inspection depth (source) — how much of the target the scan could see | −0 |
score = clamp(round(threatScore − E_cap − E_ver − E_cov), 0, 100). No model, no opinion, no network call at scoring time: the same methodology version against the same bytes always produces this number, and every line above is a field of the report rather than a summary of it.
What the scan could actually read
A grade is only as meaningful as its coverage, so the scanner publishes its own depth before it publishes its result.
Tool surfaceread
Implementation sourceread
Package metadataread
Live transportnot available
Tools were statically extracted from the published source (11 recovered), not enumerated from a running server. Tool-poisoning, Unicode-smuggling, capability and toxic-flow analysis ran on this inferred surface, but a mis-parsed registration could be missed or mis-attributed, so tool-derived findings are capped below “confirmed”. To grade the real runtime surface, scan the running server: --command "npx -y <package>".
Capability — what it could do if the model were manipulated
Tags derived from each tool’s schema and the implementation, not from what the tool calls itself. minimal is the level these add up to.
| Tool | Capability tags | Why the tag was assigned |
|---|---|---|
| get_readiness | untrusted-input | untrusted-input: declares openWorldHint: true (interacts with entities outside the server) |
| summarize_wellness | untrusted-input | untrusted-input: declares openWorldHint: true (interacts with entities outside the server) |
| get_profile | untrusted-input | untrusted-input: declares openWorldHint: true (interacts with entities outside the server) |
| get_heart_rate | untrusted-input | untrusted-input: declares openWorldHint: true (interacts with entities outside the server) |
| search_activities | untrusted-input | untrusted-input: declares openWorldHint: true (interacts with entities outside the server) |
| summarize_activities | untrusted-input | untrusted-input: declares openWorldHint: true (interacts with entities outside the server) |
| get_activity | untrusted-input | untrusted-input: declares openWorldHint: true (interacts with entities outside the server) |
| compare_activities | untrusted-input | untrusted-input: declares openWorldHint: true (interacts with entities outside the server) |
| get_activity_workouts | untrusted-input | untrusted-input: declares openWorldHint: true (interacts with entities outside the server) |
| get_activity_analysis | untrusted-input | untrusted-input: declares openWorldHint: true (interacts with entities outside the server) |
| get_menstrual_cycle | untrusted-input | untrusted-input: declares openWorldHint: true (interacts with entities outside the server) |
Toxic-flow graph
The lethal trifecta, checked as a graph rather than as a checklist: untrusted input, a sensitive source and an external sink have to meet before there is a path worth worrying about.
The public result for this release does not print the flow graph, so there is nothing to show here. That is not the same as "no paths were found": what the scan did read is above, under coverage.
Supply chain and provenance
Integrityfirst-seen
Surface digest1df701182cbf6265
Scanned2026-11-10
This is the first scan of this surface here, so there is nothing yet to compare it against.
Every result on this tab comes from one deterministic pass over the published package — offline, rule by rule, and auditable line by line above. Same methodology version, same bytes, same score.
Release history
Always latest — the install command names no version, so it installs the newest release when it runs; the current release on file is 1.3.0. Pin a release below and the command asks for exactly that one.
1.3.0
undated
latestNo release note was published with this version.
—
no reviews yet
Who can review
One review per account, from a signed-in account that does not publish this listing. Nothing else is asked — you can say what you think before you install it. Publishers can reply once per review, and a review can be edited or deleted by whoever wrote it.
Sign in to write one
Any signed-in account that does not publish Garmin can review it, once — before installing it or after. A review from an account that has installed it is marked as one.
No reviews yet
Nobody has reviewed this listing. The rating on the card is the mean of the reviews written here and nothing else, so there is no rating until somebody writes the first — which takes a signed-in account that does not publish it, and nothing else.