Skills/PyPI/my-oura-mcp

my-oura-mcp@0.4.2

CAUTION· not started

Publisher claims: "MCP server for Oura Ring data: sleep, readiness, HRV, resting heart rate" Observed in sandbox: no network, touches nothing outside the project, writes no memory.

Registry PyPI (MCP server)Publisher antvsl · publishing for 109 daysInstalls 266Last detonated 40 h ago
What would fix thisWatchDispute verdict

Coverage

Not started: dependency install failed; the server itself was not observed.
Tested
the dependency install step · every file read, file written and host contacted by what ran
Not tested
server startup · the tool list · tool behavior

What this means for the label: Caution here covers what ran. The server's tools were not exercised with a real credential, so nothing about their behavior is asserted; the credential summary below says what to do with that.

Before you give it your token

It will ask for
OURA_CLIENT_SECRETOURA_MCP_TOKENOURA_OAUTH_ALLOWED_REDIRECT_ORIGINS or --bearer-token-env-varConfiguration, not credentials: OURA_API_MODE, OURA_CACHE_DB, OURA_CLIENT_ID, OURA_PUBLIC_URL, OURA_REDIRECT_URI, OURA_TZ
Where it talks to
ouraring.com (its own)Also claude.ai, chatgpt.com — not the publisher's domain; check what for before connecting.
What the honeypot saw
no credential files read · no network
What we could not test
server startup · the tool list · tool behavior

Connect it with a scoped credential, under the guard, and read the third-party hosts first. The code names claude.ai, chatgpt.com as well as its own vendor. The guard injects OURA_CLIENT_SECRET, OURA_MCP_TOKEN, OURA_OAUTH_ALLOWED_REDIRECT_ORIGINS only into requests to ouraring.com (and its subdomains) and refuses the rest.

$vet-skills run --secrets OURA_CLIENT_SECRET=ouraring.com,OURA_MCP_TOKEN=ouraring.com,OURA_OAUTH_ALLOWED_REDIRECT_ORIGINS=ouraring.com -- uvx my-oura-mcp

Never paste a credential into a chat, a ticket or a report, including ours. How the guard holds it.

Is [email protected] safe to install?

KillerSkills ran it in the KillerSkills honeypot sandbox (2 scenarios; not started: dependency install failed; the server itself was not observed) on 2026-11-12 and scored it 76/100 (Caution). It is not known to be malicious, but it has behaviour or code a security policy should decide on before install. Notable findings: Access to sensitive file paths; Access to sensitive file paths; Access to sensitive file paths. Summary: no network, touches nothing outside the project, writes no memory.

Behavior trace

Honeypot run · 0 s · 2 scenarios · 0 deviations
t+CategoryObserved action
0.0sprocessno install scripts in bundle
0.1sprocessdependency install exit 1 ·
0.1sclaimednot started: dependency install failed (exit 1); the server itself was not observed
0.1sprocessscript backend runs setup only
0.1sprocessno install scripts to re-run

Static findings

HIGH
Access to sensitive file pathssrc/my_oura_mcp/config.py:84 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system filesнего на два уровня и записывать туда .env/токены нельзя.Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
MEDIUM
File permission modification commandsrc/my_oura_mcp/cache.py:76 · File permission modification command — agent changes file ownership/permissions# /tmp, и chmod родителя там был бы опасным побочным эффектом.Fix: Request the narrowest permission that works; replace wildcards with the exact paths or hosts.
AST05
HIGH
Access to sensitive file pathscompose.caddy.yml:20 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system filesOURA_DOMAIN: ${OURA_DOMAIN:?укажи OURA_DOMAIN в .env}Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
HIGH
Access to sensitive file pathscompose.tunnel.yml:25 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system filesTUNNEL_TOKEN: ${CLOUDFLARE_TUNNEL_TOKEN:?укажи CLOUDFLARE_TUNNEL_TOKEN в .env}Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
HIGH
Access to sensitive file pathssrc/my_oura_mcp/authflow.py:140 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system files"Переключи OURA_API_MODE=production в .env, чтобы работать со своими данными."Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
HIGH
Access to sensitive file pathscompose.server.yml:25 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system files# в Compose перекрывает `env_file`, и перенос локального .env на сервер неFix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
MEDIUM
Access to sensitive file pathscompose.yml:15 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system filesenv_file: .envFix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
HIGH
Access to sensitive file pathssrc/my_oura_mcp/auth.py:271 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system filesVPS, где в .env остались плейсхолдеры. Проверка переносит отказ на старт,Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
HIGH
Access to sensitive file pathssrc/my_oura_mcp/config.py:3 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system filesЕдинственное место, где читается .env. Всё остальное получает готовыйFix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
HIGH
Access to sensitive file pathssrc/my_oura_mcp/config.py:75 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system files"в .env — возьми их на https://developer.ouraring.com/applications"Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
HIGH
Access to sensitive file pathssrc/my_oura_mcp/http.py:111 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system files"Сгенерируй секрет и добавь его в .env:\n"Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
HIGH
Access to sensitive file pathsAGENTS.md:17 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system filesNever print, commit, or put real values from `.env`, `.oura/`, bearer headers,Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
MEDIUM
Access to sensitive file pathscompose.yml:33 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system filesOURA_DOMAIN: ${OURA_DOMAIN:?укажи OURA_DOMAIN в .env}Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
CRITICAL
HTML comment carrying imperative instructions to the agentREADME.md:357 · HTML comment carrying imperative instructions to the agentOwnership proof for the MCP registry: this token ties the PyPI package to the server name in server.json, and the registry refuses to publish without it. Kept iFix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.
AST01
HIGH
Access to sensitive file pathscompose.server.yml:22 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system filesenv_file: .envFix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
MEDIUM
Access to sensitive file pathstests/test_packaging.py:57 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system files"""Дефолтный тег в compose: с ним сервер поднимается без OURA_TAG в .env.Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
HIGH
Access to sensitive file pathssrc/my_oura_mcp/config.py:95 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system filesload_dotenv(env_file or root / ".env")Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
HIGH
Access to sensitive file pathscompose.server.yml:24 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system files# Эти четыре значения заданы здесь, а не в .env, намеренно: `environment`Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
MEDIUM
File permission modification commandDockerfile:19 · File permission modification command — agent changes file ownership/permissions&& chown -R oura /data /appFix: Request the narrowest permission that works; replace wildcards with the exact paths or hosts.
AST05
MEDIUM
Access to sensitive file pathstests/test_oauth_wiring.py:123 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system files"""Пустая переменная в .env — обычное дело, и она не должна включать OAuth."""Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
HIGH
Access to sensitive file pathsskills/oura-mcp-maintenance/SKILL.md:21 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system files- Treat `.env`, `.oura/`, bearer tokens, OAuth codes, and token stores asFix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
HIGH
Access to sensitive file pathssrc/my_oura_mcp/tools.py:262 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system files"Переключи OURA_API_MODE=production в .env после OAuth."Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
MEDIUM
Dense URL-encoded contenttests/test_auth.py:216 · Dense URL-encoded content — may be obfuscating payloadsassert body["code"] == "%D0%BA%D0%BE%D0%B4" # urlencodedFix: Put hosts, commands and strings in plain source. Decoding at runtime looks identical to malware and costs points on its own.
AST07
LOW
Authorization escalation languagedocs/DEPLOY.md:201 · Authorization escalation language · informational: not an instruction fileВ ChatGPT включи developer mode, затем создай custom app: **Settings → Apps →Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
LOW
Prompt injectiondocs/DEPLOY.md:201 · Prompt injection — known jailbreak technique reference · informational: not an instruction fileВ ChatGPT включи developer mode, затем создай custom app: **Settings → Apps →Fix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.
AST01

Cost to the agent

Instructions loaded
≈2,448 tok
3 files · 63 in bundle
Tool list per prompt
≈0 tok
0 tools · 0 per tool
Handshake
no reply
launch to tools/list, stdio
Undocumented tools
0
description under 20 chars · avg 0

Tokens estimated at four characters each. The tool list is re-read by the agent on every turn, so it is the number to compare between servers that do the same job: ranked across the index.

Known vulnerabilities

No advisories in OSV for my-oura-mcp@0.4.2 as of 40 h ago. This is the package itself, not its dependencies.

What would make this Verified

4 points to 80 · weights: behavior 45%, static 25%, prompt 15%, publisher 15%
  1. Unclaimed publisher≈ +8 on the totalClaim antvsl: a verified publisher gets +50 on publisher trust. It is free and usually instant with GitHub sign-in.
  2. Hidden instructions≈ +6 on the totalRemove HTML comments, zero-width characters and white-on-white text that carry instructions. Everything the agent is meant to read should be visible to the person reading the file.
  3. Access to sensitive file paths≈ +4 on the totalStop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
  4. File permission modification command≈ +2 on the totalRequest the narrowest permission that works; replace wildcards with the exact paths or hosts.
  5. Dense URL-encoded content≈ +2 on the totalPut hosts, commands and strings in plain source. Decoding at runtime looks identical to malware and costs points on its own.
Publish a new version to PyPI, then queue it here. Not your skill? Claim the handle to get verdict changes by email.Claim antvslPropose a patch to the maintainer