# Juno Open Health Tools

> Consent-gated tools that turn user health notes into non-diagnostic appointment-prep materials.

- name: io.github.MarshallBear1/juno-open-health-tools
- version: 1.1.0
- connection class: R0 (autonomous)
- trust: 91/100
- quality: 79/100 (good)
- owner: not claimed
- descriptor: https://api.protogrid.dev/v1/servers/io.github.MarshallBear1%2Fjuno-open-health-tools
- tools: https://api.protogrid.dev/v1/servers/io.github.MarshallBear1%2Fjuno-open-health-tools/tools

**An agent can connect right now, no human step.** Remote endpoint, no authentication, reachable on the last probe.

## Connection (mcpServers)

```json
{
  "mcpServers": {
    "juno-open-health-tools": {
      "type": "http",
      "url": "https://juno-health-tools.vercel.app/api/mcp"
    }
  }
}
```


## Trust

- hygiene: 100
- liveness: 100
- freshness: 85
- provenance: 80
- drivers: +repository +namespace-matches-repo +reachable +uptime-100% ~updated-81d-ago
- Derived from observable signals (official registry feed and our own credential-free probes); no code audit performed.

## Quality 79/100 (good)

### protocol: 88 (weight 25)

- pass `protocol.modern`: supports 2026-07-28 (server/discover)
- pass `protocol.stateless`: answers without a session
- pass `protocol.transport`: streamable HTTP
- warn `protocol.list_ttl`: tools/list declares ttlMs 0, so clients re-fetch it on every use

### authorization: n/a (weight 15)

- n/a `auth.prm`, `auth.as_metadata`, `auth.cimd`: no remote uses OAuth
- n/a `auth.secret_in_url`: no templated URL

### tool hygiene: 86 (weight 30)

- pass `tools.descriptions`: every tool has a description
- pass `tools.description_length`: descriptions are concise
- pass `tools.schemas`: every tool has an object input schema
- pass `tools.annotations`: 5 of 5 tools declare readOnlyHint or destructiveHint
- fail `tools.directory_hints`: no tool declares all four of readOnlyHint, destructiveHint, idempotentHint and openWorldHint; missing: render_appointment_brief (idempotentHint); prepare_appointment_brief (idempotentHint); find_symptom_words (idempotentHint); …
- pass `tools.token_cost`: about 1,478 tokens to load every tool
- pass `tools.api_dump`: tools are not a one-to-one API dump

### stability: 50 (weight 15)

- pass `stability.changes`: 5 tool changes in 30 days
- fail `stability.rug_pull`: 5 tools kept their name but changed most of their description in 30 days; review before trusting them

### dependencies: n/a (weight 15)

- n/a `deps.known_vulns`, `deps.mcp_sdk_version`, `deps.resolvable`: no npm or PyPI package

- tools: 5, about 1,478 tokens to load them all
- tool set hash: f9e087f5feab74c44eb90db32eabb9aa
- tools last changed: 2026-10-12T20:21:02.426Z
- badge: [![protogrid quality](https://protogrid.dev/badge/io.github.MarshallBear1/juno-open-health-tools.svg)](https://protogrid.dev/servers/io.github.MarshallBear1/juno-open-health-tools)
- Checks run on what our credential-free, read-only probes observe; tools are never called and no code audit is performed.

### Tool changes

- 2026-10-12 `render_appointment_brief` changed (description, annotations) **meaning changed**
  - before: After the user's existing consent, render the non-identifying output of prepare_appointment_brief as an accessible card. Call prepare_appointment_brief first; do not add PHI.
  - after: Renders a supplied, complete, non-identifying appointment brief as an accessible card. Requires explicit consent for transient processing. Preserves the supplied fields and disclaimer; PHI is outside its scope.
- 2026-10-12 `reflect_on_flare` changed (description, annotations) **meaning changed**
  - before: After explicit consent, structure only non-identifying, user-authored before, during, and after observations; turn suspected patterns into questions, not causal claims. Do not accept PHI.
  - after: Structures non-identifying before, during and recovery observations, presenting suspected patterns as questions rather than causes. Requires explicit consent for transient processing. PHI is outside its scope.
- 2026-10-12 `prepare_appointment_brief` changed (description, annotations) **meaning changed**
  - before: After explicit consent, turn minimal non-identifying goals, changes, impact, user-stated medicines, and questions into a concise appointment brief. Do not accept PHI or provide medical advice.
  - after: Structures non-identifying goals, changes, impacts, user-stated medicines and questions into an appointment brief. Requires explicit consent for transient processing. PHI, diagnosis and treatment advice are outside its scope.
- 2026-10-12 `build_health_timeline` changed (description, annotations) **meaning changed**
  - before: After explicit consent, sort only non-identifying, user-authored observations into a factual chronology while preserving uncertainty. Do not accept PHI or invent dates or diagnoses.
  - after: Sorts non-identifying, user-authored observations into a factual chronology while preserving supplied dates and uncertainty. Requires explicit consent for transient processing. PHI and diagnosis are outside its scope.
- 2026-10-12 `find_symptom_words` changed (description, annotations) **meaning changed**
  - before: After explicit consent, organise only the user's non-identifying description into neutral sensation, timing, pattern, and impact vocabulary. Do not accept PHI or infer a diagnosis or cause.
  - after: Organises a non-identifying, user-authored sensation description into neutral sensation, timing, pattern and impact vocabulary. Requires explicit consent for transient processing. PHI and diagnostic inference are outside its scope.

Full history: https://api.protogrid.dev/v1/servers/io.github.MarshallBear1%2Fjuno-open-health-tools/changes

## Remotes

- https://juno-health-tools.vercel.app/api/mcp (streamable-http, auth none, reachable true, uptime30d 1)

## Packages

_none_

## Tools (5)

- `build_health_timeline`: Sorts non-identifying, user-authored observations into a factual chronology while preserving supplied dates and uncertainty. Requires explicit consent for transient processing. PHI and diagnosis are outside its scope.
- `find_symptom_words`: Organises a non-identifying, user-authored sensation description into neutral sensation, timing, pattern and impact vocabulary. Requires explicit consent for transient processing. PHI and diagnostic inference are outside its scope.
- `prepare_appointment_brief`: Structures non-identifying goals, changes, impacts, user-stated medicines and questions into an appointment brief. Requires explicit consent for transient processing. PHI, diagnosis and treatment advice are outside its scope.
- `reflect_on_flare`: Structures non-identifying before, during and recovery observations, presenting suspected patterns as questions rather than causes. Requires explicit consent for transient processing. PHI is outside its scope.
- `render_appointment_brief`: Renders a supplied, complete, non-identifying appointment brief as an accessible card. Requires explicit consent for transient processing. Preserves the supplied fields and disclaimer; PHI is outside its scope.