# io.github.colincooperio/garmin-mcp (npm · garmin-mcp)

Ask your AI assistant about your Garmin training, sleep and recovery data

- Trust score: 87/100 (high trust)
- Change this week: +14
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-11-21

## Components

- npm · `garmin-mcp`: 87/100 (this document), [markdown](https://verifymcp.io/servers/colincooperio-garmin-mcp/garmin-mcp.md), [page](https://verifymcp.io/servers/colincooperio-garmin-mcp/garmin-mcp)

## Channel facts

- Registry: `npm`
- Package: `garmin-mcp`
- Version: `1.4.3`
- Transport: `stdio`

## Trust breakdown

How this component scores in each security and reliability category. Every signal is checked automatically from public evidence about the published package, including repeated runs of it in an isolated sandbox, and we only credit what we can confirm. Scores are 0–100 per category. Scoring method: https://verifymcp.io/docs/scoring (what has changed: https://verifymcp.io/docs/scoring/changelog)

Scored 2026-11-21.

- **Supply Chain Security**: 100/100
  - No malware found by supply-chain analysis.
  - No known CVEs affecting this package version or its production dependencies.
  - No install/post-install scripts declared.
  - 0 of 3 dependencies flagged as unhealthy.
- **Provenance & Transparency**: 100/100
  - Source repository is publicly reachable at the declared URL.
  - Cryptographically verified build provenance (signed, bound to colincooperio/garmin-mcp).
  - Clear OSI-approved license (MIT).
  - Actively maintained (last published 4 days ago).
  - Publishes a security disclosure policy (SECURITY.md).
- **Schema Quality & AI Usability**: 77/100
  - 100% of prompts and resources have a non-trivial description (not blank, and not just the item's name).
  - AI-judged instruction clarity (excellent).
  - Context-footprint check failed: tool/resource definitions use about 6326 tokens (~225/item across 28 items; 28 tools + 0 resources), over budget; trim descriptions and params.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 40/100
  - Stability observed for 12 of 30 days with no destabilising changes; credit accrues until the full window elapses.
- **Tool Coverage**: 99/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 96% of tool parameters carry a description.
- **Tool Safety**: 100/100
  - No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.
  - We read all 28 captured tool definition(s), and no name or description among them implies an irreversible operation.
  - An AI judge read all 29 captured unit(s) of tool text and found none that tries to manipulate the model reading it.
- **Capabilities**: 100/100
  - Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.

## Install

### How do I install the io.github.colincooperio/garmin-mcp server?

io.github.colincooperio/garmin-mcp runs locally as an npm package, launched with npx -y garmin-mcp. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.

### Claude

```bash
claude mcp add colincooperio-garmin-mcp -- npx -y garmin-mcp
```

### Cursor

```json
{
  "mcpServers": {
    "colincooperio-garmin-mcp": {
      "command": "npx",
      "args": [
        "-y",
        "garmin-mcp"
      ]
    }
  }
}
```

### VS Code

```json
{
  "servers": {
    "colincooperio-garmin-mcp": {
      "command": "npx",
      "args": [
        "-y",
        "garmin-mcp"
      ]
    }
  }
}
```

### Codex

```bash
codex mcp add colincooperio-garmin-mcp -- npx -y garmin-mcp
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "colincooperio-garmin-mcp": {
      "type": "local",
      "command": [
        "npx",
        "-y",
        "garmin-mcp"
      ],
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add colincooperio-garmin-mcp --command npx --arg -y --arg garmin-mcp
```

### Hermes

```yaml
mcp_servers:
  colincooperio-garmin-mcp:
    command: "npx"
    args: ["-y", "garmin-mcp"]
```

### Netclaw

```json
{
  "McpServers": {
    "colincooperio-garmin-mcp": {
      "Transport": "stdio",
      "Command": "npx",
      "Arguments": [
        "-y",
        "garmin-mcp"
      ]
    }
  }
}
```

### Vellum

```bash
assistant mcp add colincooperio-garmin-mcp -t stdio -c npx -a -y garmin-mcp
```

### Other

```json
{
  "mcpServers": {
    "colincooperio-garmin-mcp": {
      "command": "npx",
      "args": [
        "-y",
        "garmin-mcp"
      ]
    }
  }
}
```

## Changelog

Every change recorded for this component, newest first. Days that predate change tracking, or that we cannot explain, say so: "we were watching and nothing happened" and "we were not watching" are different claims.

### 2026-11-20 (score 87, +1)

No change was recorded against any check on this day. Stability & Change Management went from 33 to 37. That category is still filling its 30-day observation window: 10 days of observed history at the previous scan, 11 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-11-17 (score 86, +1)

- [functional] Package version: 1.4.2 → 1.4.3

### 2026-11-16 (score 85, 0)

- [security regression] Stability: 0.20 → unverified
- [security regression] Tool safety: pass → unverified
- [functional regression] Capabilities: pass → unverified
- [functional regression] Tool coverage: 100 → unverified
- [functional regression] Schema quality: 100 → unverified
- [functional] Package version: 1.4.1 → 1.4.2

### 2026-11-15 (score 85, +12)

- [security improvement] Known CVEs: unverified → pass
- [functional improvement] Dependency health: unverified → 1.00

### 2026-11-14 (score 73, −11)

- [security regression] Known CVEs: pass → unverified
- [functional regression] Schema quality: 5349 → 6326
- [functional regression] Dependency health: 1.00 → unverified
- [functional] Package version: 1.3.0 → 1.4.1
- [functional] Package version: 1.3.0 → 1.4.0

### 2026-11-13 (score 84, +1)

No change was recorded against any check on this day. Stability & Change Management went from 10 to 13. That category is still filling its 30-day observation window: 3 days of observed history at the previous scan, 4 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-11-11 (score 83, +1)

- [functional improvement] Security disclosure: fail → pass

### 2026-11-10 (score 82, +12)

- [security improvement] Known CVEs: unverified → pass
- [functional improvement] Dependency health: unverified → 1.00

## MCP tools (28)

### `get_readiness` (~142 tokens)

Readiness snapshot

Best first call for 'how recovered am I', 'should I train hard today', 'how did I sleep last night'. One compact object: that night's sleep (score, stages, HR, respiration), HRV vs baseline and status, resting HR, Body Battery, each compared with the user's previous 7 days; training load (last 7 days vs 28-day weekly average); and activities from the last 3 days. Sleep is filed under the date the user woke up, so use 'today' for last night.

Input parameters:

- `date`: YYYY-MM-DD, or 'today' / 'yesterday' (resolved in the user's Garmin time zone).

### `summarize_wellness` (~223 tokens)

Summarize wellness trends

Best tool for wellness trends over weeks or months ('has my sleep improved', 'resting HR trend this year', 'stress lately'). Returns per-period averages only: steps, resting HR, stress, Body Battery high/low, intensity minutes (totals), respiration, sleep hours/deep/REM/score, overnight HRV, with min-max ranges for key metrics and day counts where data is missing. group_by='weekday' answers 'which days do I sleep worst / most stressed'. Range up to 366 days; fetches and aggregates in the server.

Input parameters:

- `end_date` (string): Last day, YYYY-MM-DD, inclusive. Defaults to today.
- `group_by` (string)
- `include` (array): Data sources to include. Drop ones the question doesn't need for a faster answer.
- `period` (string): Named period resolved in the user's time zone (weeks start Monday). Use instead of start_date/end_date.
- `start_date` (string): First day, YYYY-MM-DD, inclusive. Required unless period is given.

### `get_daily_summaries` (~162 tokens)

Daily summaries

One flat row per day: steps, distance, floors, calories, resting/min/max HR, intensity minutes, stress, Body Battery, respiration, SpO2, hydration. For trends over more than a few weeks use summarize_wellness instead.

Input parameters:

- `detail` (string): compact (default) keeps the meaningful fields in readable units; full returns Garmin's raw payload.
- `end_date` (string): Last day, YYYY-MM-DD, inclusive. Defaults to start_date. Max span 92 days.
- `period` (string): Named period resolved in the user's time zone (weeks start Monday). Use instead of start_date/end_date.
- `start_date` (string): First day, YYYY-MM-DD, inclusive. Required unless period is given.

### `get_profile` (~34 tokens)

Profile and HR zones

User profile settings (units, measurement system, birth year, etc.) and heart-rate zones. Useful context before interpreting training data.

### `get_sleep_summaries` (~301 tokens)

Sleep summaries

Night-by-night sleep over a range, one compact row per night filed under the date the user woke up: start_local/end_local as local 'YYYY-MM-DD HH:MM'; hours of sleep, deep, light, REM and awake (and naps); sleep score with its quality and factor ratings; average HR, stress and respiration (avg/low/high); SpO2 average/lowest; sleep need vs baseline in minutes with what drove it (training load, e.g. HIGH_ACWR_AND_CHRONIC, HRV, sleep history, naps) and next night's need; Garmin's insights. For last night alone use get_readiness or get_sleep; for trends over weeks or months use summarize_wellness. Up to 92 days per call: pass a period (e.g. last_7_days, last_30_days, this_month) or start_date/end_date. detail='full' returns Garmin's raw records.

Input parameters:

- `detail` (string): compact (default) keeps the meaningful fields in readable units; full returns Garmin's raw payload.
- `end_date` (string): Last day, YYYY-MM-DD, inclusive. Defaults to start_date. Max span 92 days.
- `period` (string): Named period resolved in the user's time zone (weeks start Monday). Use instead of start_date/end_date.
- `start_date` (string): First day, YYYY-MM-DD, inclusive. Required unless period is given.

### `get_sleep` (~84 tokens)

Sleep (one night)

One night's sleep, same compact shape as get_sleep_summaries. Use detail='full' for Garmin's complete record.

Input parameters:

- `date` (required): YYYY-MM-DD, or 'today' / 'yesterday' (resolved in the user's Garmin time zone).
- `detail` (string): compact (default) keeps the meaningful fields in readable units; full returns Garmin's raw payload.

### `get_hrv_summaries` (~114 tokens)

HRV summaries

Daily heart rate variability over a range: overnight average, 5-minute high, 7-day average, baseline band, status.

Input parameters:

- `end_date` (string): Last day, YYYY-MM-DD, inclusive. Defaults to start_date. Max span 92 days.
- `period` (string): Named period resolved in the user's time zone (weeks start Monday). Use instead of start_date/end_date.
- `start_date` (string): First day, YYYY-MM-DD, inclusive. Required unless period is given.

### `get_hrv` (~69 tokens)

HRV detail (one night)

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.

Input parameters:

- `date` (required): YYYY-MM-DD, or 'today' / 'yesterday' (resolved in the user's Garmin time zone).

### `get_body_battery` (~272 tokens)

Body Battery

Daily Body Battery (Garmin's 0-100 energy estimate) over a range, one compact row per day: charged, drained, highest and lowest; the key readings the Personal API provides, in local time (about 6 a day: midnight, overnight peak, morning, afternoon, last); the events that moved it (sleep, activities, stress); and Garmin's end-of-day feedback. Event and feedback times are local too. For today's state use get_readiness; for trends over weeks or months use summarize_wellness (Body Battery high/low per period). Up to 92 days per call: pass a period (e.g. last_7_days, last_30_days, this_month) or start_date/end_date. detail='full' returns Garmin's raw report.

Input parameters:

- `detail` (string): compact (default) keeps the meaningful fields in readable units; full returns Garmin's raw payload.
- `end_date` (string): Last day, YYYY-MM-DD, inclusive. Defaults to start_date. Max span 92 days.
- `period` (string): Named period resolved in the user's time zone (weeks start Monday). Use instead of start_date/end_date.
- `start_date` (string): First day, YYYY-MM-DD, inclusive. Required unless period is given.

### `get_stress` (~221 tokens)

Stress

Day-by-day all-day stress over a range, one row per day as Garmin returns it: calendarDate, then values with overallStressLevel (Garmin's 0-100 score) and highStressDuration, mediumStressDuration, lowStressDuration and restStressDuration in seconds. For trends over weeks or months, or 'which weekday am I most stressed', use summarize_wellness (stress per period, group_by='weekday'); stress during sleep is avg_stress in get_sleep_summaries. Up to 92 days per call: pass a period (e.g. last_7_days, last_30_days, this_month) or start_date/end_date.

Input parameters:

- `end_date` (string): Last day, YYYY-MM-DD, inclusive. Defaults to start_date. Max span 92 days.
- `period` (string): Named period resolved in the user's time zone (weeks start Monday). Use instead of start_date/end_date.
- `start_date` (string): First day, YYYY-MM-DD, inclusive. Required unless period is given.

### `get_heart_rate` (~198 tokens)

Heart rate (one day)

Heart rate for one day: resting, min, max, 7-day resting average, and hourly min/avg/max in local time. Give from/to (local HH:MM) to also get every ~2-minute reading in that window, e.g. overnight or around a workout. detail='full' returns Garmin's raw payload (every reading, large).

Input parameters:

- `date` (required): YYYY-MM-DD, or 'today' / 'yesterday' (resolved in the user's Garmin time zone).
- `detail` (string): compact (default) keeps the meaningful fields in readable units; full returns Garmin's raw payload.
- `from` (string): Start of a full-resolution window, local HH:MM. Defaults to 00:00 when only 'to' is given.
- `to` (string): End of the window, local HH:MM, inclusive. Defaults to 23:59 when only 'from' is given.

### `get_steps` (~183 tokens)

Steps

Day-by-day steps over a range, one row per day as Garmin returns it: calendarDate, totalSteps, totalDistance (metres) and stepGoal. get_daily_summaries has the same steps alongside floors, calories, HR and stress; for weekly or monthly averages over longer spans use summarize_wellness. Up to 92 days per call: pass a period (e.g. last_7_days, last_30_days, this_month) or start_date/end_date.

Input parameters:

- `end_date` (string): Last day, YYYY-MM-DD, inclusive. Defaults to start_date. Max span 92 days.
- `period` (string): Named period resolved in the user's time zone (weeks start Monday). Use instead of start_date/end_date.
- `start_date` (string): First day, YYYY-MM-DD, inclusive. Required unless period is given.

### `get_wellness_activity_summaries` (~176 tokens)

Wellness activity summaries

Garmin's wellness activity summaries over a range: all-day movement records kept apart from recorded workouts, returned as Garmin sends them. Often empty; for daily movement use get_daily_summaries or get_steps, and for workouts search_activities or summarize_activities. Up to 92 days per call: pass a period (e.g. last_7_days, last_30_days, this_month) or start_date/end_date.

Input parameters:

- `end_date` (string): Last day, YYYY-MM-DD, inclusive. Defaults to start_date. Max span 92 days.
- `period` (string): Named period resolved in the user's time zone (weeks start Monday). Use instead of start_date/end_date.
- `start_date` (string): First day, YYYY-MM-DD, inclusive. Required unless period is given.

### `get_spo2` (~105 tokens)

Pulse Ox (one day)

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.

Input parameters:

- `date` (required): YYYY-MM-DD, or 'today' / 'yesterday' (resolved in the user's Garmin time zone).
- `detail` (string): compact (default) keeps the meaningful fields in readable units; full returns Garmin's raw payload.

### `get_fitness_age` (~154 tokens)

Fitness age

Garmin's fitness age as of a date: chronologicalAge, fitnessAge (a decimal; round it) and previousFitnessAge, plus the components behind it, each with a value and a stale flag: rhr (resting HR), vigorousDaysAvg and vigorousMinutesAvg (weekly averages over numOfWeeksForIm recent weeks), and bmi with its lastMeasurementDate. BMI comes from the last weight entry, so it is often old. It changes slowly, so date='today' is usually all you need. This is not VO2 max, which the Personal API doesn't provide.

Input parameters:

- `date` (required): YYYY-MM-DD, or 'today' / 'yesterday' (resolved in the user's Garmin time zone).

### `get_weight` (~225 tokens)

Weight

Weight and body composition measurements over a range, from a Garmin smart scale or entered manually in Garmin Connect, returned as Garmin sends them: weights are in grams (74000 = 74 kg); date is the local measurement time, 'YYYY-MM-DD HH:MM'. Often empty, since it needs a smart scale or manual entries. When nothing was recorded in the range, the result holds only previousDateWeight, the last measurement before it: check its calendarDate before treating it as current. Up to 92 days per call: pass a period (e.g. last_7_days, last_30_days, this_month) or start_date/end_date. For longer histories, make several calls.

Input parameters:

- `end_date` (string): Last day, YYYY-MM-DD, inclusive. Defaults to start_date. Max span 92 days.
- `period` (string): Named period resolved in the user's time zone (weeks start Monday). Use instead of start_date/end_date.
- `start_date` (string): First day, YYYY-MM-DD, inclusive. Required unless period is given.

### `get_hydration` (~180 tokens)

Hydration

Water intake the user logged in Garmin Connect, day by day over a range, as Garmin returns it. Usually empty: Garmin only records hydration that is logged, so an empty result means nothing was logged, not that the user drank nothing. get_daily_summaries also carries hydration_ml per day. Up to 92 days per call: pass a period (e.g. last_7_days, last_30_days, this_month) or start_date/end_date.

Input parameters:

- `end_date` (string): Last day, YYYY-MM-DD, inclusive. Defaults to start_date. Max span 92 days.
- `period` (string): Named period resolved in the user's time zone (weeks start Monday). Use instead of start_date/end_date.
- `start_date` (string): First day, YYYY-MM-DD, inclusive. Required unless period is given.

### `search_activities` (~529 tokens)

Search activities

List individual recorded activities (runs, rides, swims, strength, etc.) with the activity_id needed for get_activity and get_activity_analysis. Filter by date, type, race, distance, duration, elevation gain, name text or a lat/long box. For totals, averages or trends over weeks/months, use summarize_activities instead: it is far smaller. Default detail='compact' returns key stats only (startTimeLocal as local 'YYYY-MM-DD HH:MM', distance m, duration/movingDuration s, averageSpeed/maxSpeed m/s, HR, elevation, calories, cadence, power, training effect). Use detail='full' only when a field you need is missing, and with a small limit. Sport-specific extras such as golf scorecards, shot data or dive logs are NOT available.

Input parameters:

- `activity_subtype` (string): Subtype key within activity_type, e.g. trail_running, treadmill_running, road_cycling.
- `activity_type` (string): Parent type key, e.g. running, cycling, swimming, strength_training, walking, hiking.
- `area` (object): Only activities that started inside this latitude/longitude box (decimal degrees).
- `detail` (string)
- `end_date` (string): Only activities on/before this date.
- `event_type` (string): Only activities tagged with this event type, e.g. race.
- `exclude_children` (boolean): Hide the legs of multisport activities (e.g. a triathlon's swim/bike/run), keeping the parent.
- `limit` (integer): Max results (1-100).
- `max_distance_m` (integer): Maximum distance in metres.
- `max_duration_min` (number): Maximum duration in minutes.
- `max_elevation_gain_m` (number): Maximum elevation gain in metres.
- `min_distance_m` (integer): Minimum distance in metres.
- `min_duration_min` (number): Minimum duration in minutes.
- `min_elevation_gain_m` (number): Minimum elevation gain in metres.
- `name_contains` (string): Text the activity name contains (case-insensitive), e.g. 'parkrun' or 'tempo'.
- `period` (string): Named period resolved in the user's time zone (weeks start Monday). Use instead of start_date/end_date.
- `sort_by` (string): Sort field. Use distance or averageSpeed to find longest or fastest.
- `sort_order` (string)
- `start` (integer): Offset for paging.
- `start_date` (string): Only activities on/after this date.

### `summarize_activities` (~538 tokens)

Summarize activities

Best tool for activity totals and trends (e.g. 'how far did I run each month', 'has my pace improved'). Fetches every matching activity in the range and returns only aggregates per period and type: count, distance (km and mi), moving time, elevation, longest, average speed and pace (distance-weighted), fastest average pace, average HR, training load, and time in HR zones 1-5 (minutes and %, for zone 2 / 80-20 questions). With group_by 'week' or 'month' it also returns load_trend: load per period, % change vs the previous period, and the acute:chronic ratio at the end of each, with flags for a ratio above 1.3 or a rise over 30%. Use group_by='week' for 'am I building too fast / ramping up too quickly', and for 'compare this block with my last one' (e.g. last_90_days by week, or two ranges). Range up to 366 days.

Input parameters:

- `activity_subtype` (string): Subtype key within activity_type, e.g. trail_running, treadmill_running, road_cycling.
- `activity_type` (string): Parent type key, e.g. running, cycling, swimming, strength_training, walking, hiking.
- `area` (object): Only activities that started inside this latitude/longitude box (decimal degrees).
- `end_date` (string): Last day, YYYY-MM-DD, inclusive. Defaults to today.
- `event_type` (string): Only activities tagged with this event type, e.g. race.
- `exclude_children` (boolean): Hide the legs of multisport activities (e.g. a triathlon's swim/bike/run), keeping the parent.
- `group_by` (string)
- `max_distance_m` (integer): Maximum distance in metres.
- `max_duration_min` (number): Maximum duration in minutes.
- `max_elevation_gain_m` (number): Maximum elevation gain in metres.
- `min_distance_m` (integer): Minimum distance in metres.
- `min_duration_min` (number): Minimum duration in minutes.
- `min_elevation_gain_m` (number): Minimum elevation gain in metres.
- `name_contains` (string): Text the activity name contains (case-insensitive), e.g. 'parkrun' or 'tempo'.
- `period` (string): Named period resolved in the user's time zone (weeks start Monday). Use instead of start_date/end_date.
- `start_date` (string): First day, YYYY-MM-DD, inclusive. Required unless period is given.

### `get_personal_bests` (~385 tokens)

Personal bests and race estimates

Fastest 1 km, 1 mile, 5 km, 10 km, half and marathon across many activities, each with date, activity, pace, avg HR and the next two best efforts; plus race time estimates for 5 km to marathon from the last 90 days of the range: your actual time where you ran the distance, otherwise Riegel from the effort closest in distance. Use for 'what's my 5k PB', 'fastest half this year', 'what could I run a 10k in'. These are computed from the user's activity files (fastest continuous stretch within each run), NOT Garmin's official personal records, which the Personal API doesn't provide; estimates are estimates, not Garmin's race predictor. Analyses the newest 150 matching activities per call. The first call over a long range is slow (each activity's file is downloaded once, then cached). The result starts with complete. If complete is false (the fields are then named provisional_*), the bests are NOT final: call again with the same arguments (it continues from the cache) until complete is true, or tell the user the results are partial. Defaults to the last 365 days and running.

Input parameters:

- `activity_type` (string): Parent type key, e.g. running (includes trail and treadmill), walking, hiking.
- `distances` (array): Distances to report. Defaults to all six.
- `end_date` (string): Last day, YYYY-MM-DD, inclusive. Defaults to today.
- `period` (string): Named period resolved in the user's time zone (weeks start Monday). Use instead of start_date/end_date.
- `start_date` (string): First day, YYYY-MM-DD, inclusive. Defaults to 365 days ago.
- `unit` (string): Pace unit. Defaults to the user's Garmin unit setting.

### `analyze_recovery_impact` (~381 tokens)

Recovery vs running performance

Does sleep, HRV or Body Battery relate to how the user runs? Pairs each run with the night before it (sleep score, hours slept, overnight HRV) and that morning's Body Battery, then compares runs after the best third of nights with runs after the worst third at the same heart rate: it fits the user's own speed-for-HR line across the runs and scores each run by how much faster or slower it was than expected for its HR, so easy and hard runs compare fairly. Returns each group's average HR and pace, the difference in s/km (or s/mi) at the same HR, and a correlation, called meaningful only at |r| >= 0.3 with 8+ runs per group. Warns when the groups' average HR differs by over 8 bpm (different kinds of runs). Races, runs under 20 minutes and manual entries are left out. Use for 'does poor sleep hurt my running', 'do I run better when my HRV is high'. Says when there's too little data to conclude; correlation, not proof. Defaults to the last 180 days and running; range up to 366 days.

Input parameters:

- `activity_type` (string): Parent type key, e.g. running, cycling, walking.
- `end_date` (string): Last day, YYYY-MM-DD, inclusive. Defaults to today.
- `measure` (string): Recovery measure to compare by; 'all' does each. Pick one for a faster answer.
- `period` (string): Named period resolved in the user's time zone (weeks start Monday). Use instead of start_date/end_date.
- `start_date` (string): First day, YYYY-MM-DD, inclusive. Defaults to 180 days ago.
- `unit` (string): Pace unit. Defaults to the user's Garmin unit setting.

### `get_activity` (~132 tokens)

Activity detail

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). detail='full' returns Garmin's raw record (200+ fields).

Input parameters:

- `activity_id` (string, required): Garmin activity ID, from search_activities.
- `detail` (string): compact (default) keeps the meaningful fields in readable units; full returns Garmin's raw payload.

### `compare_activities` (~75 tokens)

Compare activities

Side-by-side compact detail for 2-5 activities (same fields as get_activity), fetched in parallel. Use for 'compare my last two long runs' or 'how did this race compare with last year's'; get the IDs from search_activities.

Input parameters:

- `activity_ids` (array, required): 2-5 Garmin activity IDs.

### `get_activity_workouts` (~142 tokens)

Activity workouts

The planned workout linked to one recorded activity, if any: workoutName, sport and steps, each with intensity, durationType/durationValue (metres for DISTANCE) and a target (e.g. targetType SPEED with targetValueLow/High in m/s). An activity started from one of Garmin's daily suggested workouts may carry only a workoutPhrase (e.g. EASY_WEEK_LOAD_BASE); an empty result means no workout was linked. This is the plan; for how each rep actually went use get_activity_analysis (laps). Get the ID from search_activities.

Input parameters:

- `activity_id` (string, required): Garmin activity ID, from search_activities.

### `get_activity_analysis` (~326 tokens)

Activity analysis (splits, laps, best efforts)

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, computed from Garmin's original FIT file. Use for 'my km splits', 'did I negative split', 'fastest 5 km in this run', 'how long in zone 2', 'did my HR drift'. splits: one row per km/mile (time, pace, cumulative time, avg/max HR, cadence, power, elevation gain/loss), timer time so pauses don't count, final partial split labelled with its distance. laps: the watch's own laps with intensity (warmup/active/cooldown/rest) and trigger (manual, distance, ...). best_efforts: fastest continuous 1 km, 1 mile, 5 km, 10 km, half and marathon the activity is long enough for, with where each started. hr_zones: time in each HR zone, as the watch recorded it with the zones in effect then (matches Garmin Connect and summarize_activities). drift: first vs second half pace, HR and aerobic decoupling. Get the ID from search_activities. Manual entries and GPX/TCX imports return a short 'unavailable' note.

Input parameters:

- `activity_id` (string, required): Garmin activity ID, from search_activities.
- `include` (array): Sections to return. Drop ones the question doesn't need for a shorter answer.
- `unit` (string): Split length and pace unit. Defaults to the user's Garmin unit setting.

### `get_nutrition` (~56 tokens)

Nutrition (one day)

Food log for one day: nutrition goals, calories and nutrients consumed, and per-meal breakdown.

Input parameters:

- `date` (required): YYYY-MM-DD, or 'today' / 'yesterday' (resolved in the user's Garmin time zone).

### `get_weight_goals` (~170 tokens)

Weight goals

The weight goal the user set in Garmin Connect that was in effect over a range, with its goal range, returned as Garmin sends it. Empty ({}) when no weight goal is set, which is common. Pair with get_weight to track progress. Up to 92 days per call: pass a period (e.g. last_7_days, last_30_days, this_month) or start_date/end_date.

Input parameters:

- `end_date` (string): Last day, YYYY-MM-DD, inclusive. Defaults to start_date. Max span 92 days.
- `period` (string): Named period resolved in the user's time zone (weeks start Monday). Use instead of start_date/end_date.
- `start_date` (string): First day, YYYY-MM-DD, inclusive. Required unless period is given.

### `get_menstrual_cycle` (~113 tokens)

Menstrual cycle (one day)

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). Empty unless the user tracks their cycle in Garmin Connect. date accepts YYYY-MM-DD, 'today' or 'yesterday'; call once per date.

Input parameters:

- `date` (required): YYYY-MM-DD, or 'today' / 'yesterday' (resolved in the user's Garmin time zone).

## Diagnostics

Captured diagnostic sections: Provenance, Dependencies. The full working is on the page: https://verifymcp.io/servers/colincooperio-garmin-mcp/garmin-mcp#diagnostics

## Score history

- 2026-11-21: 87
- 2026-11-20: 87
- 2026-11-19: 86
- 2026-11-18: 86
- 2026-11-17: 86
- 2026-11-16: 85
- 2026-11-15: 85
- 2026-11-14: 73
- 2026-11-13: 84
- 2026-11-12: 83
- 2026-11-11: 83
- 2026-11-10: 82
- 2026-11-09: 70

## Common questions

### What is the io.github.colincooperio/garmin-mcp server?

io.github.colincooperio/garmin-mcp is listed in the public MCP registry as io.github.colincooperio/garmin-mcp. Ask your AI assistant about your Garmin training, sleep and recovery data. This page covers its npm package (garmin-mcp).

### Is the io.github.colincooperio/garmin-mcp server safe to use?

io.github.colincooperio/garmin-mcp scores 87 out of 100 on VerifyMCP. We found no known CVEs affecting it as of 21 November 2026. It declares no install or post-install scripts. Its build provenance is signed and verified. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.

### What tools does the io.github.colincooperio/garmin-mcp server expose?

io.github.colincooperio/garmin-mcp exposes 28 tools: get_readiness, summarize_wellness, get_daily_summaries, get_profile, get_sleep_summaries, and 23 more. Their descriptions and schemas cost roughly 5,690 tokens of context every time the server is loaded.

### Is the io.github.colincooperio/garmin-mcp server still maintained?

io.github.colincooperio/garmin-mcp is still listed as active in the MCP registry. We last reached this channel on 21 November 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.

### What licence is the io.github.colincooperio/garmin-mcp server under?

io.github.colincooperio/garmin-mcp declares the MIT licence, which is OSI-approved. That covers the source only, and says nothing about the cost of any service it calls.

### What did VerifyMCP test on the io.github.colincooperio/garmin-mcp server?

VerifyMCP ran 16 checks on io.github.colincooperio/garmin-mcp, covering Malware scan, Known CVEs, Install scripts, Dependency health and 12 more. Endpoint Security and Transport & Reachability do not apply to an npm package, so they were not tested. The score does not measure everything, and the scoring documentation lists what it leaves out.

## Links

- npm package: https://www.npmjs.com/package/garmin-mcp
- Socket report: https://socket.dev/npm/package/garmin-mcp
- Repository: https://github.com/colincooperio/garmin-mcp
- Changelog RSS feed: https://verifymcp.io/servers/colincooperio-garmin-mcp/garmin-mcp.xml
- Changelog JSON feed: https://verifymcp.io/servers/colincooperio-garmin-mcp/garmin-mcp/changelog.json
- Trust report (JSON): https://verifymcp.io/servers/colincooperio-garmin-mcp/garmin-mcp.json
- HTML version of this page: https://verifymcp.io/servers/colincooperio-garmin-mcp/garmin-mcp
