Niches · Health records & wellness data
Answer a person's questions from their wearable data
No company's docs show a full fit yet. The listings below do the job with a limit, or not at all.
What counts as done
The agent reads the person's normalised sleep, activity and body data for the asked range, including sleep stages and HRV where the device records them, and every value comes from the source rather than a truncated sample.
Measured, for our own tests: a 30-day sleep summary in under 3 calls. No docs we read state these figures, so they don't count against a listing here.
How agents ask for it: how did I sleep this week
, is my HRV trending down
, summarise my training load
, compare my resting heart rate to last month
Does the job, with a limit 3
It does the job, but something in the docs or a user's account will get in an agent's way. The limit is named in each row.
| Listing | Why |
|---|---|
| ROOK C Rookeries Development Corp. | Normalised sleep (with stage times), physical and body summaries from Garmin, Oura, Polar, Fitbit, Apple Health and Health Connect can be queried by REST, but ROOK is a backend platform with no MCP or assistant connect route, and REST is a backup capped at 60 requests a minute. source |
| Terra API B Terra Enabling Developers Inc. | Terra AI's MCP has get_sleep_data (REM, deep, light, latency, HRV, SpO2), get_daily_data and get_activity_data with field lists, filters and server-side aggregation over a date range; acc-01 relies on Terra to normalise Polar data. But a person needs a developer plan from $499 a month, and the key is environment-wide. source |
| Validic Inform D Validic, Inc. | REST reads per user return summaries, sleep (REM, light, awake, total) and measurements in one schema across sources, but there is no documented agent route (the Enterprise MCP is unpublished), HRV is not listed, and the free tier's REST API is a preview on synthetic data. source |
Doesn't do this job 9
Listings in the category that do something else, with the reason.
| Listing | Why |
|---|---|
| 1upHealth D 1upHealth, Inc. | No wearable or phone health-store data. source |
| Aidbox B Health Samurai, Inc. | No wearable connectors. source |
| Health Gorilla C Health Gorilla, Inc. | No wearable data. source |
| Medblocks D Medblocks Inc. | The wearables and mobile page says coming soon. source |
| Medplum B Orangebot, Inc. | No wearable connectors. source |
| Metriport Medical API D Metriport Inc. | The Medical API covers clinical network data only. source |
| Particle Health E Particle Health, Inc. | No wearable data. source |
| Redox C Redox, Inc. | No wearable data. source |
| Zus Health C Zus Health, Inc. | No wearable data. source |
What stops agents finishing
- the metric the person wants is not in the provider's API
- unofficial MCP breaks or is rate limited at sign-in
- person will not send health data to a hosted model
Around it
Before: personal-assistants.connect. After: scheduling.write, messaging.send.
Where this comes from
Weight 25 of 100 in Health records & wellness data: 9 of 36 use-case citations across 34 accounts, scaled to 100; most accounts use Garmin, Oura or Apple Health directly, not a listing
The same as data: /api/v1/use-cases/health-data.wearable-summary.json, or the MCP tool get_use_case with id health-data.wearable-summary. Other jobs in this category: /api/v1/niches?category=health-data.
For companies
Do agents find, use and choose your tools?
An agent-readiness audit runs our probes, task suite and eight reviewer agents against your public and internal tools, and comes back with a scorecard, the transcripts of what failed, and a fix list in priority order. From $2,500, re-run included. We never take payment to move a rank. We do help companies earn one.