Juno Open Health Tools MCP server
io.github.MarshallBear1/juno-open-health-toolsMarshallBear1streamable-httpv1.1.0Scanned
Consent-gated tools that turn user health notes into non-diagnostic appointment-prep materials.
5 tools: 4 change things and 1 only read.
- Reads private data · 0
- Reads text others write · 0
- Can send data out · 0
- 5 findings
Tools listed without sign-in. Remote posture
With Anlyon
4 tools here change things. Govern them.
- Anlyon lists the tools and adopts none.
- Each tool you adopt gets approvals and receipts.
- Your agent never holds the key.
A tool your agent calls directly is not routed through Anlyon and is not governed by it. Anlyon Radar only lists and labels, and these labels are the same either way.
What the Juno Open Health Tools MCP server can do
The Juno Open Health Tools MCP server is published by the GitHub account MarshallBear1. It has 5 tools. It can create or change data (4 tools: build_health_timeline, prepare_appointment_brief, reflect_on_flare and render_appointment_brief), but cannot delete data. 1 tool only reads.
None of its tools reads private data, brings in text other people write, or sends data out.
The fixed checks matched 5 findings (credentials-mention). Each one comes with the text it matched.
Its remote endpoint lists its tools without sign-in.
Last scanned Nov 16, 2026, version 1.1.0.
Tools
Grouped by what each tool does, most consequential first. Open one for its reasons and full description; descriptions are the publisher's own words.
5 tools
Changes things 4Claude Code: ask
build_health_timelineSorts non-identifying, user-authored observations into a factual chronology while preserving supplied dates and uncertainty.1 finding
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
Findings
- Info
The input schema at properties.consentConfirmed.description mentions "credentials".
What this check looks forMatched text
inputSchema.properties.consentConfirmed.description: "...al-record identifiers, contact details, credentials, or provider documents."
Description, as the server wrote it 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.
Annotations the server declares
- title: Build health timeline
- readOnlyHint: true
- destructiveHint: false
- openWorldHint: false
prepare_appointment_briefStructures non-identifying goals, changes, impacts, user-stated medicines and questions into an appointment brief.1 finding
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
Findings
- Info
The input schema at properties.consentConfirmed.description mentions "credentials".
What this check looks forMatched text
inputSchema.properties.consentConfirmed.description: "...al-record identifiers, contact details, credentials, or provider documents."
Description, as the server wrote it 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.
Annotations the server declares
- title: Prepare appointment brief
- readOnlyHint: true
- destructiveHint: false
- openWorldHint: false
reflect_on_flareStructures non-identifying before, during and recovery observations, presenting suspected patterns as questions rather than causes.1 finding
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
Findings
- Info
The input schema at properties.consentConfirmed.description mentions "credentials".
What this check looks forMatched text
inputSchema.properties.consentConfirmed.description: "...al-record identifiers, contact details, credentials, or provider documents."
Description, as the server wrote it 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.
Annotations the server declares
- title: Reflect on a flare
- readOnlyHint: true
- destructiveHint: false
- openWorldHint: false
render_appointment_briefRenders a supplied, complete, non-identifying appointment brief as an accessible card.1 finding
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
Findings
- Info
The input schema at properties.consentConfirmed.description mentions "credentials".
What this check looks forMatched text
inputSchema.properties.consentConfirmed.description: "...al-record identifiers, contact details, credentials, or provider documents."
Description, as the server wrote it 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.
Annotations the server declares
- title: Render appointment brief
- readOnlyHint: true
- destructiveHint: false
- openWorldHint: false
Only reads 1Show 1 read-only tool
find_symptom_wordsOrganises a non-identifying, user-authored sensation description into neutral sensation, timing, pattern and impact vocabulary.1 finding
Why it is in this group
- The name "find_symptom_words" says "find": a word for reading.
Findings
- Info
The input schema at properties.consentConfirmed.description mentions "credentials".
What this check looks forMatched text
inputSchema.properties.consentConfirmed.description: "...al-record identifiers, contact details, credentials, or provider documents."
Description, as the server wrote it 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.
Annotations the server declares
- title: Find symptom words
- readOnlyHint: true
- destructiveHint: false
- openWorldHint: false
This is not a safety rating, and no finding is not a safety guarantee. The groups and findings come from fixed checks of the tool definitions the server returned on the date shown, not from its code or what it does when called. How the checks work.
Exfil surface
Which tools read private data, which read text someone else can write, and which can send data out. One of each is a path a prompt injection can use.
No private-data, untrusted-input, outbound path in this server alone: no tool is tagged private-data or untrusted-input or outbound.
- Reads private data0
- Reads files, mail, messages, databases, secrets, calendars or repositories.
- Reads text others write0
- Brings in text someone else can write: web pages, inbound email, messages, issues and comments.
- Can send data out0
- Can carry data to people or systems: it sends, posts or publishes, or takes a recipient, channel or URL.
Other servers in the same agent add their own tools to these paths. Audit your whole setup to see them together.
Remote posture
What anyone on the internet sees at the remote endpoint: an anonymous initialize and tools/list, and the public OAuth metadata.
Looked at Nov 20, 2026, 18:59 UTC, unchanged since Oct 22, 2026. No credentials were sent and no tool was called. What is looked at.
- Reachable
- yes
- HTTP status of an anonymous initialize
- 200
- tools/list served without credentials
- yes
- Tools that change things, listed without credentials
- 4
- Protocol version
- 2025-06-18
- WWW-Authenticate on 401
- not observed
- resource_metadata in WWW-Authenticate
- not observed
- RFC 9728 protected resource metadata
- not observed
- Authorization servers
- not observed
- Legacy HTTP+SSE transport
- no
- Dynamic client registration
- not observed
- Client ID metadata documents
- not observed
- WarnThe whole server
The endpoint served tools/list without credentials, and the list has 4 tools that change things (4 write). Whether a call also works without credentials was not tested: tools are never called.
What this check looks forMatched text
https://juno-health-tools.vercel.app/api/mcp: tools/list returned 5 tools to an anonymous client, including build_health_timeline (write), prepare_appointment_brief (write), reflect_on_flare (write), render_appointment_brief (write)
Findings
Matches of fixed checks, with the text they matched.
The input schema at properties.consentConfirmed.description mentions "credentials".
What this check looks forMatched text
inputSchema.properties.consentConfirmed.description: "...al-record identifiers, contact details, credentials, or provider documents."
The input schema at properties.consentConfirmed.description mentions "credentials".
What this check looks forMatched text
inputSchema.properties.consentConfirmed.description: "...al-record identifiers, contact details, credentials, or provider documents."
The input schema at properties.consentConfirmed.description mentions "credentials".
What this check looks forMatched text
inputSchema.properties.consentConfirmed.description: "...al-record identifiers, contact details, credentials, or provider documents."
- Inforeflect_on_flare
The input schema at properties.consentConfirmed.description mentions "credentials".
What this check looks forMatched text
inputSchema.properties.consentConfirmed.description: "...al-record identifiers, contact details, credentials, or provider documents."
The input schema at properties.consentConfirmed.description mentions "credentials".
What this check looks forMatched text
inputSchema.properties.consentConfirmed.description: "...al-record identifiers, contact details, credentials, or provider documents."
History
Changes to its tool definitions and to its remote endpoint, newest first.
No change seen yet. Its tools are rescanned every day, and a remote endpoint is looked at once a week.
Install
Pinned to version 1.1.0. Values in angle brackets are yours to fill in.
claude mcp add --transport http juno-open-health-tools https://juno-health-tools.vercel.app/api/mcpclaude mcp add --transport http juno-open-health-tools https://juno-health-tools.vercel.app/api/mcpRun in a terminal.
Claude Code permissions
Allow the reads, ask before a change or a way out, deny the deletes. Paste into .claude/settings.json.
{
"permissions": {
"allow": [
"mcp__juno-open-health-tools__find_symptom_words"
],
"ask": [
"mcp__juno-open-health-tools__build_health_timeline",
"mcp__juno-open-health-tools__prepare_appointment_brief",
"mcp__juno-open-health-tools__reflect_on_flare",
"mcp__juno-open-health-tools__render_appointment_brief"
],
"deny": []
}
}Tools that only read are allowed, tools that change things ask first, tools that delete or cancel are denied. A read that can send data out (it takes a URL, say) asks first too. It assumes the server is installed as juno-open-health-tools. Review it before you use it.
Pin
Keep the decision: fail CI when the tools change, follow every change, or show a badge.
Pin in CI
Fail a build when the tools you reviewed are not the tools the server serves today.
curl -s "https://radar.anlyon.com/api/v1/servers/io.github.MarshallBear1/juno-open-health-tools/verify?hash=262672b0c74a87743bd409b85cbf8a51f4732194dab134b95aad8011a0ad29a2" | jq -e '.changed == false'Pinned hash 262672b0c74a, from Nov 16, 2026, 01:17 UTC.
Watch
Get told when its tools change: a new tool, a new description, a new class.
https://radar.anlyon.com/servers/io.github.MarshallBear1/juno-open-health-tools/changes.xmlAn Atom feed. Works in any feed reader or Slack's RSS app.
Badge
[](https://radar.anlyon.com/servers/io.github.MarshallBear1/juno-open-health-tools)Source: MCP Registry · repository. Synced Oct 21, 2026, 18:17 UTC.
Juno Open Health Tools MCP server: questions and answers
Answered from the scan above, not from the publisher's description.
Is the Juno Open Health Tools MCP server safe?
- No scan can promise that. What its definitions show: 5 tools, 4 of which can change, send or delete something, and 5 findings from fixed checks. Allow the reads, ask before each change, and deny the deletes; the permissions block on this page does that.
Can the Juno Open Health Tools MCP server delete data?
- No tool is classed as destructive: going by their definitions, none of them deletes, cancels or revokes anything.
Can the Juno Open Health Tools MCP server do things that cannot be undone?
- No tool is classed as irreversible: none of them sends, pays, publishes or merges, going by their definitions.
What tools does the Juno Open Health Tools MCP server have?
- 5 tools: 4 write, 1 read. build_health_timeline, prepare_appointment_brief, reflect_on_flare, render_appointment_brief and find_symptom_words.
Does the Juno Open Health Tools MCP server need sign-in or OAuth?
- Its remote endpoint listed its tools to an anonymous client, without sign-in.
Does the Juno Open Health Tools MCP server send data to outside services?
- None of its tools sends, posts or publishes, or takes a recipient, channel or URL.
Has the Juno Open Health Tools MCP server changed its tools?
- Not since Anlyon Radar started tracking it. Last scanned Nov 16, 2026.