Comprehensive Model Context Protocol server for managing Home Assistant through AI assistants.
Nothing to run from here
Oura Ring (read-only) 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.
94/100
trust score
603
downloads a day
local
runs on your machine
14
tools declared
What it does
Read-only access to your Oura Ring readiness, sleep, activity, HRV, heart rate and trends.
Quickstart
# 1 — add it to Claude Code
claude mcp add --scope user oura-ring-read-only-mcp '--' npx -y @royreznik/oura-ring-mcp
# 2 — ask your agent for something these tools do
# get_profile, get_daily_overview, get_trends and 11 more
Oura Ring (read-only) costs nothing on mcprush: there is no plan to choose here, no cap to set and nothing mcprush can bill you for.
Publishernot claimed
ROAll 1 server
royreznik1 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 Oura Ring (read-only) 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. The '--' is in quotes so that PowerShell passes it on.
claude mcp add --scope user oura-ring-read-only-mcp '--' npx -y @royreznik/oura-ring-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 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
14 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.
Get the user's Oura profile and ring hardware: age, height, weight, biological sex and email; each ring's model, size, color, firmware and setup date; and the latest battery level with its timestamp. Use it for questions about the person or the device, or to put scores in context (e.g. age next to…
No parameter schema on file.
Get everything Oura recorded for one day in a single call: readiness (score, contributors, temperature deviation), sleep score and the night's main sleep (stages, HRV, lowest heart rate, efficiency), naps, activity (score, steps, calories), stress, resilience, SpO2, cardiovascular age, VO2 max,…
| Parameter | Type | Required | Notes |
|---|---|---|---|
| date | string | no | Day to show (YYYY-MM-DD); a night's sleep belongs to the day you woke up. Defaults to the latest day. |
Summarize the last N days (default 14, up to 90, including today) as a day-by-day table plus avg/min/max for readiness, sleep and activity scores, sleep hours and stages, HRV, lowest heart rate, temperature deviation, steps, active calories and stress, with readiness-zone counts and workouts per…
| Parameter | Type | Required | Notes |
|---|---|---|---|
| days | integer | no | How many days to look back, including today (1-90). |
List daily readiness scores (0-100, with Oura's zone: optimal 85+, good 70-84, pay_attention below 70) and their contributors: HRV balance, resting heart rate, recovery index, body temperature, sleep balance, previous night, previous-day activity, activity balance and sleep regularity, plus…
| Parameter | Type | Required | Notes |
|---|---|---|---|
| start | string | no | First day to include (YYYY-MM-DD). |
| end | string | no | Last day to include (YYYY-MM-DD). Defaults to today. |
| days | integer | no | Shortcut for start: the last N days up to end. Ignored when start is set. |
| next_token | string | no | Pass the next_token from a previous call to get the following records. |
| raw | boolean | no | Return Oura's raw API objects instead of compact summaries with friendly units. |
List daily sleep scores (0-100, with Oura's zone) and the contributors behind them: total sleep, efficiency, restfulness, REM, deep sleep, latency and timing. Use it for 'how well did I sleep' over a range; for hours, stages, HRV and heart rate use list_sleep_periods, and for one night's hypnogram…
| Parameter | Type | Required | Notes |
|---|---|---|---|
| start | string | no | First day to include (YYYY-MM-DD). |
| end | string | no | Last day to include (YYYY-MM-DD). Defaults to today. |
| days | integer | no | Shortcut for start: the last N days up to end. Ignored when start is set. |
| next_token | string | no | Pass the next_token from a previous call to get the following records. |
| raw | boolean | no | Return Oura's raw API objects instead of compact summaries with friendly units. |
List individual sleep periods (nights and, by default, naps) with bedtime, hours in bed and asleep, deep/REM/light/awake hours, latency, efficiency, average and lowest heart rate, average HRV, breathing rate and the readiness score each produced. Use it for sleep duration, stages and overnight HRV…
| Parameter | Type | Required | Notes |
|---|---|---|---|
| include_naps | boolean | no | Set false to return only long (main) sleeps. |
Get one sleep period in full detail by its sleep_id: the same summary as list_sleep_periods plus a hypnogram (deep/light/REM/awake segments at 5-minute resolution, in local time), heart-rate and HRV curves through the night (downsampled to at most 120 points, with avg/min/max), and the readiness…
| Parameter | Type | Required | Notes |
|---|---|---|---|
| sleep_id | string | yes | Sleep period id (from list_sleep_periods or get_daily_overview). |
| raw | yes | — |
List daily activity: activity score (0-100) and contributors, steps, active, total and target calories, walking-equivalent distance in km, minutes of high/medium/low activity, sedentary, resting and non-wear hours, and inactivity alerts. Use it for movement, step and calorie questions over a…
| Parameter | Type | Required | Notes |
|---|---|---|---|
| start | string | no | First day to include (YYYY-MM-DD). |
| end | string | no | Last day to include (YYYY-MM-DD). Defaults to today. |
| days | integer | no | Shortcut for start: the last N days up to end. Ignored when start is set. |
| next_token | string | no | Pass the next_token from a previous call to get the following records. |
| raw | boolean | no | Return Oura's raw API objects instead of compact summaries with friendly units. |
List workouts, auto-detected by the ring or added manually, with activity type, label, intensity (easy/moderate/hard), source, start and end time, duration in minutes, calories and distance in km. Use it for training questions such as 'how many runs this month'; narrow it with activity, a…
| Parameter | Type | Required | Notes |
|---|---|---|---|
| activity | string | no | Only return workouts whose activity contains this text (case-insensitive), e.g. "running". |
List mindfulness sessions recorded in the Oura app (meditation, breathing, relaxation, nap, rest, body status) with mood, start and end time, duration, and heart-rate and HRV stats (avg/min/max). Use it for questions about guided practice and how it affected heart rate or HRV; sleep is in…
| Parameter | Type | Required | Notes |
|---|---|---|---|
| start | string | no | First day to include (YYYY-MM-DD). |
| end | string | no | Last day to include (YYYY-MM-DD). Defaults to today. |
| days | integer | no | Shortcut for start: the last N days up to end. Ignored when start is set. |
| next_token | string | no | Pass the next_token from a previous call to get the following records. |
| raw | boolean | no | Return Oura's raw API objects instead of compact summaries with friendly units. |
List per-day health metrics joined by date: stress (day summary, minutes of high stress and high recovery), resilience level and contributors, average SpO2 and breathing disturbance index, cardiovascular age, VO2 max, and bedtime guidance (Oura's optimal bedtime window). Use it for stress,…
| Parameter | Type | Required | Notes |
|---|---|---|---|
| start | yes | — | |
| end | yes | — | |
| days | yes | — |
List the tags and notes the user logged in the Oura app (e.g. alcohol, caffeine, late meal, sickness, travel, custom tags) with their time, end time if any, and comments, merging classic and enhanced tags into one list sorted by time. Use it to explain unusual readiness or sleep, then cross-check…
| Parameter | Type | Required | Notes |
|---|---|---|---|
| start | yes | — | |
| end | yes | — | |
| days | yes | — |
List Rest Mode periods, which the user turns on when sick, injured or recovering, with start and end day (an ongoing period has no end) and the symptom tags logged during each. Use it to explain dips in readiness or activity, or to check whether the user was unwell on given days. Covers the last…
| Parameter | Type | Required | Notes |
|---|---|---|---|
| start | yes | — | |
| end | yes | — | |
| days | integer | no | The last N days up to end. Ignored when start is set. |
| raw | yes | — |
Get the heart-rate time series between two times, aggregated into buckets aligned to local time (5min, 15min, hour or day) with avg/min/max bpm and the dominant source, plus overall and per-source stats (awake, rest, sleep, workout, session, live). Use it for heart rate at particular times, during…
| Parameter | Type | Required | Notes |
|---|---|---|---|
| start | string | no | Start: a date (YYYY-MM-DD, local midnight) or ISO 8601 date-time. Defaults to 24 hours ago. |
| end | string | no | End: a date (includes that whole day) or ISO 8601 date-time. Defaults to now. |
| resolution | string | no | Bucket size. "raw" returns individual samples (truncated after …). |
| source | string | no | Only include samples recorded in this context. |
| latest | boolean | no | Return only the most recent sample; other arguments are ignored. |
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 Oura Ring (read-only) 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 94 / 100
Release 1.0.0 · scanned 19 Oct 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 score94
Findings1 threat · 0 capability
Capabilityhigh
Coveragesource
Verificationsource
Surface digest04ef72f57acf42a8171cdf6e30312753f456292ac3afd09174b8a13740a9fdc8
Score vectorthreat 100 → client 94
| Term | Level | What it prices | Points |
|---|---|---|---|
| capability-exposure | high | capability blast radius (high) — client exposure if the model is manipulated | −6 |
| 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 (14 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. high is the level these add up to.
| Tool | Capability tags | Why the tag was assigned |
|---|---|---|
| get_profile | untrusted-input | untrusted-input: declares openWorldHint: true (interacts with entities outside the server) |
| get_daily_overview | untrusted-input | untrusted-input: declares openWorldHint: true (interacts with entities outside the server) |
| get_trends | untrusted-input | untrusted-input: declares openWorldHint: true (interacts with entities outside the server) |
| list_daily_readiness | untrusted-input | untrusted-input: declares openWorldHint: true (interacts with entities outside the server) |
| list_daily_sleep | untrusted-input | untrusted-input: declares openWorldHint: true (interacts with entities outside the server) |
| list_sleep_periods | untrusted-input | untrusted-input: declares openWorldHint: true (interacts with entities outside the server) |
| get_sleep_period | untrusted-input | untrusted-input: declares openWorldHint: true (interacts with entities outside the server) |
| list_daily_activity | untrusted-input | untrusted-input: declares openWorldHint: true (interacts with entities outside the server) |
| list_workouts | untrusted-input | untrusted-input: declares openWorldHint: true (interacts with entities outside the server) |
| list_sessions | untrusted-input | untrusted-input: declares openWorldHint: true (interacts with entities outside the server) |
| list_daily_health | untrusted-input | untrusted-input: declares openWorldHint: true (interacts with entities outside the server) |
| list_tags | untrusted-input | untrusted-input: declares openWorldHint: true (interacts with entities outside the server) |
| list_rest_mode_periods | 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) |
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 digest04ef72f57acf42a8
Scanned2026-10-19
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 1.0.0. Pin a release below and the command asks for exactly that one.
1.0.0
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 Oura Ring (read-only) 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.