OwnMetrics
PYPI · OWNMETRICS-MCP
Ask AI apps about your own Garmin data via Garmin's official Personal API. Unofficial.
Available components
Last scanned (3 hours ago)
Scores higher than 88% of PyPI servers
Category Health and Science
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. How we score → Why this is hard to score →
Supply Chain Security100
- No malware found by supply-chain analysis.Pass
- No known CVEs affecting this package version or its production dependencies.Pass
- Runs hatchling.build at install time, a recognised build step with no custom scripting around it. View diagnostics → Pass
- 1 of 33 dependencies flagged as unhealthy. View diagnostics → Partial
Provenance & Transparency100
- Source repository is publicly reachable at the declared URL. View diagnostics → Pass
- Cryptographically verified build provenance (signed, bound to badisbenhamida/ownmetrics-mcp). View diagnostics → Pass
- Clear OSI-approved license (MIT).Pass
- Actively maintained (last published 7 days ago).Pass
- Publishes a security disclosure policy (SECURITY.md).Pass
Schema Quality & AI Usability72
- AI-judged instruction clarity (excellent).Pass
- Context-footprint check failed: tool/resource definitions use about 1968 tokens (~140/item across 14 items; 14 tools + 0 resources), over budget; trim descriptions and params. See how to fix → Fail
- Usage-examples check failed: none of the tools include examples. See how to fix → Fail
Stability & Change Management33
- Stability observed for 10 of 30 days with no destabilising changes; credit accrues until the full window elapses.Partial
Tool Coverage100
- 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
- 100% of tool parameters carry a description.Pass
- Structured output schemas are declared (100% of tools); any adoption earns full credit.Pass
Tool Safety100
- No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.Pass
- We read all 14 captured tool definition(s), and no name or description among them implies an irreversible operation.Pass
- An AI judge read all 15 captured unit(s) of tool text and found none that tries to manipulate the model reading it.Pass
Capabilities100
- Implements a current MCP spec version (2026-07-28).Pass
Every change we have recorded for this component, newest first. Security-relevant changes are always shown. ▲ marks a change for the better, ▼ a change for the worse; unmarked changes are neutral.
- 5 Nov 26 +16
- Malware scan: unverified → pass ▲ security
- 3 Nov 26 +1
No change was recorded against any check on this day. Stability & Change Management went from 23 to 27. That category is still filling its 30-day observation window: 7 days of observed history at the previous scan, 8 at this one. The score rises as the window fills, whether or not the server changes.
- 1 Nov 26 +1
No change was recorded against any check on this day. Stability & Change Management went from 17 to 20. That category is still filling its 30-day observation window: 5 days of observed history at the previous scan, 6 at this one. The score rises as the window fills, whether or not the server changes.
- 30 Oct 26 −14
- Malware scan: pass → unverified ▼ security
- 29 Oct 26 +15
- Malware scan: unverified → pass ▲ security
- 28 Oct 26 −14
- Malware scan: pass → unverified ▼ security
- Schema quality: 1771 → 1968 ▼ functional
- Stability: unverified → 0.07 ▲ functional
- Package version: 0.2.1 → 0.3.1 functional
- Package version: 0.2.1 → 0.3.0 functional
- 27 Oct 26 +15
- Malware scan: unverified → pass ▲ security
- 26 Oct 26 66
First indexed and scored.
Diagnostic detail from the automated scan of this channel: what the scanner observed at each step, so you can see exactly where a check passed or failed. It is informational only and never changes the trust score.
Captured 5 Nov 2026 · Analysed pypi/ownmetrics-mcp@0.3.1
Provenance Verified
A signed build attestation was found and verified, binding this exact artifact to the source repository it claims to come from.
| Result | Verified |
|---|---|
| Ecosystem | pypi |
| Reason | Verified |
| Discovered via | Registry attestation endpoint |
| Source repo | badisbenhamida/ownmetrics-mcp |
| Certificate issuer | https://token.actions.githubusercontent.com |
| Certificate SAN | https://github.com/badisbenhamida/ownmetrics-mcp/.github/workflows/release.yml@refs/tags/v0.3.1 |
| Rekor log index | 3545225606 |
| Predicate type | PyPI publish attestation https://docs.pypi.org/attestations/publish/v1 |
| Subject digest | sha256:2844488d3ff6f719570bf22c83206ee7bd43ebc2543d8112e681a0e57d50ed3c |
Background: How many MCP packages publish verified provenance →
Install scripts 1 script
| Hook | Tier | Command |
|---|---|---|
| build_backend | allowlisted | hatchling.build |
Background: Why install scripts are a supply-chain risk →
Dependencies 33 packages
| Packages resolved | 33 |
|---|---|
| No linked repository | 1 |
| Tree resolution | Complete |
Background: SBOMs and build attestations, explained →
The tools this component advertises to a client, with an estimated token cost for each. Expand a tool to see its parameters and schema. The per-tool counts are indicative and are not scored directly; the schema's total context footprint is one signal in Schema Quality & AI Usability. A tool's description is untrusted text the model reads on every call, which is what makes this list a security surface and not just an inventory: how tool poisoning works →
compare_periods ~169
I2. Compare two periods (each up to 366 days), e.g. this October vs last October: average sleep, HRV, resting heart rate, stress, Body Battery, steps and training per week, with change and % change and how many days of data each side has. Results are informational, not medical advice. Fields Garmin did not record say 'not recorded'; never treat them as zero.
| Name | Type | Req | Description |
|---|---|---|---|
| a_end | string | yes | Period A last date, YYYY-MM-DD. |
| a_start | string | yes | Period A first date, YYYY-MM-DD. |
| b_end | string | yes | Period B last date, YYYY-MM-DD. |
| b_start | string | yes | Period B first date, YYYY-MM-DD. |
| metrics | – | – | Metrics to compare; leave empty for all. |
Structured output declared, but exposes no named fields.
No examples provided.
get_account_status ~78
T9. Check the Garmin connection: whether the key works, granted scopes, a warning if the key expires within a day, which data areas respond, and what Garmin does not provide. Use this first when something fails. Results are informational, not medical advice. Fields Garmin did not record say 'not recorded'; never treat them as zero.
Input schema present but exposes no named parameters.
Structured output declared, but exposes no named fields.
No examples provided.
get_activity ~82
T7. Details of one activity by id: duration, distance, pace, speed, heart rate, power, cadence, training effect and load, splits and structured workout steps. Results are informational, not medical advice. Fields Garmin did not record say 'not recorded'; never treat them as zero.
| Name | Type | Req | Description |
|---|---|---|---|
| activity_id | integer | yes | Activity id from list_activities. |
Structured output declared, but exposes no named fields.
No examples provided.
get_body_metrics ~110
T8. Body metrics over a date range: weigh-ins (kg), BMI, body fat, hydration; plus Pulse Ox (SpO2) and fitness age as of the end date. Results are informational, not medical advice. Fields Garmin did not record say 'not recorded'; never treat them as zero.
| Name | Type | Req | Description |
|---|---|---|---|
| end | string | yes | Last date, YYYY-MM-DD (inclusive); at most 90 days after start. |
| start | string | yes | First date, YYYY-MM-DD (inclusive). |
Structured output declared, but exposes no named fields.
No examples provided.
get_daily_overview ~92
T1. One day's overview: steps, distance, floors, resting/min/max heart rate, stress, Body Battery, calories, intensity minutes, sleep hours and sleep score. Results are informational, not medical advice. Fields Garmin did not record say 'not recorded'; never treat them as zero.
| Name | Type | Req | Description |
|---|---|---|---|
| date | string | yes | Date as YYYY-MM-DD, e.g. 2026-10-25. |
Structured output declared, but exposes no named fields.
No examples provided.
get_heart_rate ~85
T5. One day's heart rate (resting, min, max, 7-day resting average) and the user's heart rate zones. Results are informational, not medical advice. Fields Garmin did not record say 'not recorded'; never treat them as zero.
| Name | Type | Req | Description |
|---|---|---|---|
| date | string | yes | Date as YYYY-MM-DD, e.g. 2026-10-25. |
Structured output declared, but exposes no named fields.
No examples provided.
get_hrv ~121
T3. Heart rate variability (HRV) per night over a date range: last-night average, weekly average, 5-minute high, status and personal baseline, in milliseconds. Each night is labelled woke_up_on, the morning it ended. Results are informational, not medical advice. Fields Garmin did not record say 'not recorded'; never treat them as zero.
| Name | Type | Req | Description |
|---|---|---|---|
| end | string | yes | Last date, YYYY-MM-DD (inclusive); at most 90 days after start. |
| start | string | yes | First date, YYYY-MM-DD (inclusive). |
Structured output declared, but exposes no named fields.
No examples provided.
get_sleep ~120
T2. Sleep per night over a date range: hours, deep/light/REM/awake minutes, sleep score, Garmin's feedback, average heart rate, respiration and sleep stress. Each night is labelled woke_up_on, the morning it ended. Results are informational, not medical advice. Fields Garmin did not record say 'not recorded'; never treat them as zero.
| Name | Type | Req | Description |
|---|---|---|---|
| end | string | yes | Last date, YYYY-MM-DD (inclusive); at most 90 days after start. |
| start | string | yes | First date, YYYY-MM-DD (inclusive). |
Structured output declared, but exposes no named fields.
No examples provided.
get_stress_and_body_battery ~109
T4. Per day over a date range: average stress (0-100), minutes in each stress band, and Body Battery high, low, charged and drained. Results are informational, not medical advice. Fields Garmin did not record say 'not recorded'; never treat them as zero.
| Name | Type | Req | Description |
|---|---|---|---|
| end | string | yes | Last date, YYYY-MM-DD (inclusive); at most 90 days after start. |
| start | string | yes | First date, YYYY-MM-DD (inclusive). |
Structured output declared, but exposes no named fields.
No examples provided.
list_activities ~148
T6. List activities in a date range, newest first, optionally filtered by Garmin activity type key (e.g. running, cycling, indoor_cycling, lap_swimming, strength_training). Returns ids for get_activity. Results are informational, not medical advice. Fields Garmin did not record say 'not recorded'; never treat them as zero.
| Name | Type | Req | Description |
|---|---|---|---|
| activity_type | – | – | Optional Garmin activity type key, e.g. 'running'. |
| end | string | yes | Last date, YYYY-MM-DD (inclusive); at most 90 days after start. |
| limit | integer | – | Maximum activities, 1-100. |
| start | string | yes | First date, YYYY-MM-DD (inclusive). |
Structured output declared, but exposes no named fields.
No examples provided.
recovery_correlations ~180
I3. Does training go with better or worse sleep and HRV? Over up to 366 days, pairs each day's training with the night after it: correlations with sample size and strength, plus averages for training vs rest days and evening vs earlier sessions. Can focus on one sport. Correlation is not cause; say so when answering. Results are informational, not medical advice. Fields Garmin did not record say 'not recorded'; never treat them as zero.
| Name | Type | Req | Description |
|---|---|---|---|
| activity_type | – | – | Optional sport to look at on its own, matched by name (e.g. 'tennis', 'running', 'cycling'). Days with only other sports are left out. |
| end | string | yes | Last date, YYYY-MM-DD (inclusive); at most 366 days after start. |
| start | string | yes | First date, YYYY-MM-DD (inclusive). |
Structured output declared, but exposes no named fields.
No examples provided.
training_summary ~137
I1. Training totals over up to 366 days, by week or month: sessions, hours, hours per week, evening sessions, average aerobic training effect, and a per-sport breakdown. Use for 'how much did I train' questions. Results are informational, not medical advice. Fields Garmin did not record say 'not recorded'; never treat them as zero.
| Name | Type | Req | Description |
|---|---|---|---|
| end | string | yes | Last date, YYYY-MM-DD (inclusive); at most 366 days after start. |
| group_by | string | – | Group by 'week' or 'month'. |
| start | string | yes | First date, YYYY-MM-DD (inclusive). |
Structured output declared, but exposes no named fields.
No examples provided.
trend ~145
I4. Trend of one metric over up to 366 days, by day, week or month: the series, change per 30 days and whether it is going up, down or flat. Daily grouping adds a 7-day rolling average. Results are informational, not medical advice. Fields Garmin did not record say 'not recorded'; never treat them as zero.
| Name | Type | Req | Description |
|---|---|---|---|
| end | string | yes | Last date, YYYY-MM-DD (inclusive); at most 366 days after start. |
| group_by | string | – | Group by day, week or month. |
| metric | string | yes | The metric to follow. |
| start | string | yes | First date, YYYY-MM-DD (inclusive). |
Structured output declared, but exposes no named fields.
No examples provided.
weekly_review ~184
I5. Weekly review, the same every time: training, sleep, HRV, resting heart rate, stress and Body Battery for the Monday-to-Sunday week containing week_of (default: this week so far), against the same days last week and the previous 28 days; best and worst nights; and highlights from fixed rules. Use for 'weekly review' or 'how was my week' questions. For a general weekly review, call it once with no week_of; pass week_of only when the user names a week (e.g. 'last week'). Results are informational, not medical advice. Fields Garmin did not record say 'not recorded'; never treat them as zero.
| Name | Type | Req | Description |
|---|---|---|---|
| week_of | – | – | Any date in the week to review, YYYY-MM-DD. Leave empty for this week so far; use a date from last week for the last full week. |
Structured output declared, but exposes no named fields.
No examples provided.
How do I install the OwnMetrics MCP server?
OwnMetrics runs locally as a PyPI package, launched with uvx ownmetrics-mcp. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.
pypi · ownmetrics-mcp
claude mcp add badisbenhamida-ownmetrics-mcp -- uvx ownmetrics-mcp
What is the OwnMetrics MCP server?
OwnMetrics is an MCP server listed in the public MCP registry as io.github.badisbenhamida/ownmetrics-mcp. Ask AI apps about your own Garmin data via Garmin's official Personal API. Unofficial. This page covers its PyPI package (ownmetrics-mcp).
Is the OwnMetrics MCP server safe to use?
OwnMetrics scores 86 out of 100 on VerifyMCP. We found no known CVEs affecting it as of 5 November 2026. 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 OwnMetrics MCP server expose?
OwnMetrics exposes 14 tools: get_daily_overview, get_sleep, get_hrv, get_stress_and_body_battery, get_heart_rate, and 9 more. Their descriptions and schemas cost roughly 1,760 tokens of context every time the server is loaded.
Is the OwnMetrics MCP server still maintained?
OwnMetrics is still listed as active in the MCP registry. We last reached this channel on 5 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 OwnMetrics MCP server under?
OwnMetrics declares the MIT licence, which is OSI-approved. That covers the source only, and says nothing about the cost of any service it calls.