Skip to content

Emora Health MCP server

com.emorahealth/mental-health-careemorahealth.comstreamable-httpv1.1.0Scanned

Find kids' and teens' mental health clinicians, check availability, get booking links and costs.

8 tools: 1 change things and 7 only read.

Tools: 0 delete, 0 irreversible, 1 write, 7 read.
  • Reads private data · 0
  • Reads text others write · 0
  • Can send data out · 0
  • No findings

Tools listed without sign-in. Remote posture

Anlyon alternative

1 of these tools change something. Run those as governed actions.

Declare what an action changes, and Anlyon puts it under a shared limit, binds every approval to the exact request, and grades the outcome. It works on any HTTPS API you can describe as an action.

Anlyon Radar does not run, proxy or govern this MCP server. A tool your own code calls directly is not routed through Anlyon and is not governed by it.

Import an OpenAPI spec →

What the Emora Health MCP server can do

The Emora Health MCP server is published by emorahealth.com, a domain the MCP Registry verified. It has 8 tools. It can create or change data (1 tool: recommend_care), but cannot delete data. 7 tools only read.

None of its tools reads private data, brings in text other people write, or sends data out.

None of the fixed checks matched anything in its tool definitions. That is not a safety guarantee.

Its remote endpoint lists its tools without sign-in.

Last scanned Nov 13, 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.

8 tools

Changes things 1Claude Code: ask
  • recommend_care[Step 1 of find_a_clinician · optional] Takes a parent's concern and returns a recommended path: crisis resources when there is danger, the service that fits (therapy, medication, …No findings

    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.
    Description, as the server wrote it
    [Step 1 of find_a_clinician · optional] Takes a parent's concern and returns a recommended path: crisis resources when there is danger, the service that fits (therapy, medication, ADHD or autism testing, or a clinical matching session), matched clinicians with their next opening, and related care resources. Says so when the family's state is not one Emora serves. Use when: A parent has described a concern and the next step (crisis help, a clinician, reading, or all three) is not yet clear. Don't use when: A clinician is already chosen: get_availability and get_booking_link cover the rest. Example: recommend_care({ concern: "Teacher thinks my 9-year-old may have ADHD", state: "Texas", age: 9, insurance: "Aetna" })

    Annotations the server declares

    • readOnlyHint: true
    • untrustedContentHint: true
Only reads 7Show 7 read-only tools
  • get_availability[Step 3 of find_a_clinician] Returns open appointment times for one clinician and service, grouped by day and labelled in the family's state time zone.No findings

    Why it is in this group

    • The name "get_availability" says "get": a word for reading.
    Description, as the server wrote it
    [Step 3 of find_a_clinician] Returns open appointment times for one clinician and service, grouped by day and labelled in the family's state time zone. Each time carries the date_time value that get_booking_link takes. Use when: A family has chosen a clinician and wants to see open times. Don't use when: No clinician is chosen yet: search_providers or recommend_care find one. Example: get_availability({ state: 'Texas', service: 'adhd-testing', provider_id: '7598079' })

    Annotations the server declares

    • readOnlyHint: true
  • get_cost_estimate[Step 1 of cost_check] Returns a general cost range and a link to the cost estimate page, pre-filled with the plan and service, where the family sees the exact amount for their pla…No findings

    Why it is in this group

    • The name "get_cost_estimate" says "get": a word for reading.
    Description, as the server wrote it
    [Step 1 of cost_check] Returns a general cost range and a link to the cost estimate page, pre-filled with the plan and service, where the family sees the exact amount for their plan. Use when: A parent asks what care costs, about a copay, or whether a plan is covered. Example: get_cost_estimate({ insurance: 'Aetna', service: 'adhd-testing' })

    Annotations the server declares

    • readOnlyHint: true
  • get_crisis_resources[Step 1 of crisis] Returns 911, the 988 Suicide & Crisis Lifeline and the Crisis Text Line, for a child or teen in danger now.No findings

    Why it is in this group

    • The name "get_crisis_resources" says "get": a word for reading.
    Description, as the server wrote it
    [Step 1 of crisis] Returns 911, the 988 Suicide & Crisis Lifeline and the Crisis Text Line, for a child or teen in danger now. Use when: Any mention of self-harm, suicidal thoughts, or someone in immediate danger. Example: get_crisis_resources({})

    Annotations the server declares

    • readOnlyHint: true
  • get_emora_overview[Step 1 of explore_information · optional] Describes Emora Health: services, states served, insurance accepted, ages seen, how care works, and how to reach the care team.No findings

    Why it is in this group

    • The name "get_emora_overview" says "get": a word for reading.
    Description, as the server wrote it
    [Step 1 of explore_information · optional] Describes Emora Health: services, states served, insurance accepted, ages seen, how care works, and how to reach the care team. Use when: A parent asks what Emora is, what it offers, where it works, or which plans it takes. Example: get_emora_overview({})

    Annotations the server declares

    • readOnlyHint: true
  • search_care_resources[Step 2 of explore_information] Searches Emora's clinician-reviewed resources for parents by words: articles on behavior, conditions, treatment and medication, free self-tests, act…No findings

    Why it is in this group

    • The name "search_care_resources" says "search": a word for reading.
    Description, as the server wrote it
    [Step 2 of explore_information] Searches Emora's clinician-reviewed resources for parents by words: articles on behavior, conditions, treatment and medication, free self-tests, activities, condition and specialty pages, and clinical insights. Each result has a type, title, description and URL to cite. Use when: A parent wants to understand something (a behavior, a condition, a treatment, a medication question) or asks for a test, worksheet or activity. Don't use when: The parent wants a clinician: search_providers or recommend_care. Example: search_care_resources({ query: 'social anxiety test for teens' })

    Annotations the server declares

    • readOnlyHint: true
  • search_providers[Step 2 of find_a_clinician] Returns Emora clinicians who fit a state, service, insurance and child's age, ranked by clinical fit when concerns are given, then by availability and …No findings

    Why it is in this group

    • The name "search_providers" says "search": a word for reading.
    Description, as the server wrote it
    [Step 2 of find_a_clinician] Returns Emora clinicians who fit a state, service, insurance and child's age, ranked by clinical fit when concerns are given, then by availability and reviews. Each result has the clinician's next opening. Ten per page; limit and offset page through the rest. Use when: A family wants to see clinicians: therapists, psychiatric prescribers, psychologists for testing, or intake specialists (service clinical-matching). Don't use when: The family hasn't said what they're worried about yet: recommend_care orients first. Example: search_providers({ state: 'Florida', service: 'therapy', concerns: ['social-anxiety'], insurance: 'Aetna', client_age: 12 })

    Annotations the server declares

    • readOnlyHint: true
    • untrustedContentHint: true

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.

Tools listed without sign-in

Looked at Nov 20, 2026, 18:37 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
1
Protocol version
2025-06-18
WWW-Authenticate on 401
not observed
resource_metadata in WWW-Authenticate
not observed
RFC 9728 protected resource metadata
https://www.emorahealth.com/.well-known/oauth-protected-resource/api/mcp/v1
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 1 tool that changes things (1 write). Whether a call also works without credentials was not tested: tools are never called.

    Matched text

    https://www.emorahealth.com/api/mcp/v1: tools/list returned 8 tools to an anonymous client, including recommend_care (write)

    What this check looks for

Findings

Matches of fixed checks, with the text they matched.

No check matched anything in these tool definitions. That is not a safety guarantee.

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 mental-health-care https://www.emorahealth.com/api/mcp/v1
claude mcp add --transport http mental-health-care https://www.emorahealth.com/api/mcp/v1

Run 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.

.claude/settings.json
{
  "permissions": {
    "allow": [
      "mcp__mental-health-care__search_providers",
      "mcp__mental-health-care__get_availability",
      "mcp__mental-health-care__get_booking_link",
      "mcp__mental-health-care__search_care_resources",
      "mcp__mental-health-care__get_cost_estimate",
      "mcp__mental-health-care__get_emora_overview",
      "mcp__mental-health-care__get_crisis_resources"
    ],
    "ask": [
      "mcp__mental-health-care__recommend_care"
    ],
    "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 mental-health-care. 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/com.emorahealth/mental-health-care/verify?hash=2e147dfa3c5125ed32a6ed4ef9abd6925e60ab29235ea7f0296bbfd3a53af7b4" | jq -e '.changed == false'

Pinned hash 2e147dfa3c51, from Nov 13, 2026, 03:17 UTC.

Watch

Get told when its tools change: a new tool, a new description, a new class.

https://radar.anlyon.com/servers/com.emorahealth/mental-health-care/changes.xml

An Atom feed. Works in any feed reader or Slack's RSS app.

Badge

Anlyon Radar badge for com.emorahealth/mental-health-care
[![Anlyon Radar](https://radar.anlyon.com/badge/com.emorahealth/mental-health-care.svg)](https://radar.anlyon.com/servers/com.emorahealth/mental-health-care)

Source: MCP Registry. Synced Oct 21, 2026, 17:54 UTC.

Emora Health MCP server: questions and answers

Answered from the scan above, not from the publisher's description.

Is the Emora Health MCP server safe?

No scan can promise that. What its definitions show: 8 tools, 1 of which can change, send or delete something, and 0 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 Emora Health MCP server delete data?

No tool is classed as destructive: going by their definitions, none of them deletes, cancels or revokes anything.

Can the Emora Health 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 Emora Health MCP server have?

8 tools: 1 write, 7 read. recommend_care, search_providers, get_availability, get_booking_link, search_care_resources, get_cost_estimate, get_emora_overview and get_crisis_resources.

Does the Emora Health MCP server need sign-in or OAuth?

Its remote endpoint listed its tools to an anonymous client, without sign-in.

Does the Emora Health MCP server send data to outside services?

None of its tools sends, posts or publishes, or takes a recipient, channel or URL.

Has the Emora Health MCP server changed its tools?

Not since Anlyon Radar started tracking it. Last scanned Nov 13, 2026.