mentalka-tests MCP server
io.github.Protopopov/mentalka-testsProtopopovstreamable-httpv0.1.0Scanned
Free anonymous PHQ-9 depression and SAS smartphone-addiction screenings in uk, en, hr, ru, pl.
4 tools: 1 do something that can't be undone, 2 change things and 1 only read.
- Reads private data · 0
- Reads text others write · 0
- Can send data out · 0
- No findings
Tools listed without sign-in. Remote posture
With Anlyon
1 tool here does something that can't be undone. Govern it.
- 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 mentalka-tests MCP server can do
The mentalka-tests MCP server is published by the GitHub account Protopopov. It has 4 tools. It can do things that cannot be undone, such as sending, paying or publishing (request_consultation) and create or change data (2 tools: start_test and score_test), 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.
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, and its tools changed once since Anlyon Radar first saw them.
Last scanned Nov 16, 2026, version 0.1.0.
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.
4 tools
Can't be undone 1Claude Code: ask
request_consultationSend a request for a free consultation with the site's psychologist.No findings
Why it is in this group
- The name "request_consultation" says "request": a word for a change.
- The description's first verb is "send": a word for sending, and what is sent cannot be taken back.
Description, as the server wrote it Send a request for a free consultation with the site's psychologist. Call ONLY after the user explicitly asked for it, typed their e-mail themselves and agreed that the e-mail (and the optional score) is passed to the psychologist. Never invent or infer an e-mail. Offer it, do not push it.
Changes things 2Claude Code: ask
score_testScore a finished test.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.
Description, as the server wrote it Score a finished test. `answers` is the list of answer values in question order (PHQ-9: nine values 0-3; SAS: 33 values 1-6). Present the result with care, include helplines if returned, and remind the user this is a screening, not a diagnosis.
start_testGet the questions and answer scale of a test.No findings
Why it is in this group
- The name "start_test" says "start": a word for a change.
Description, as the server wrote it Get the questions and answer scale of a test. Ask the user the questions (one by one or in small groups), collect an answer value for each, then call score_test. Do not guess or invent answers for the user.
Only reads 1Show 1 read-only tool
list_testsList the psychological screening tests available on mentalka.app.No findings
Why it is in this group
- The name "list_tests" says "list": a word for reading.
Description, as the server wrote it List the psychological screening tests available on mentalka.app.
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, 19:00 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
- 3
- 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
- HighThe whole server
The endpoint served tools/list without credentials, and the list has 3 tools that change things (1 irreversible, 2 write). Whether a call also works without credentials was not tested: tools are never called.
What this check looks forMatched text
https://mentalka.app/api/mcp: tools/list returned 4 tools to an anonymous client, including request_consultation (irreversible), start_test (write), score_test (write)
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.
Tools2 changed.~2 changedView diff
- Changed:score_testChanges thingsinputSchema
- Changed:start_testChanges thingsinputSchema
Install
Pinned to version 0.1.0. Values in angle brackets are yours to fill in.
claude mcp add --transport http mentalka-tests https://mentalka.app/api/mcpclaude mcp add --transport http mentalka-tests https://mentalka.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__mentalka-tests__list_tests"
],
"ask": [
"mcp__mentalka-tests__start_test",
"mcp__mentalka-tests__score_test",
"mcp__mentalka-tests__request_consultation"
],
"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 mentalka-tests. 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.Protopopov/mentalka-tests/verify?hash=95f0e34f6d239b59d0b7f253ece182a8624b7042589a9e63a5f8912bd7aab3e2" | jq -e '.changed == false'Pinned hash 95f0e34f6d23, from Nov 16, 2026, 03:18 UTC.
Watch
Get told when its tools change: a new tool, a new description, a new class.
https://radar.anlyon.com/servers/io.github.Protopopov/mentalka-tests/changes.xmlAn Atom feed. Works in any feed reader or Slack's RSS app.
Badge
[](https://radar.anlyon.com/servers/io.github.Protopopov/mentalka-tests)Source: MCP Registry · repository. Synced Oct 21, 2026, 18:18 UTC.
mentalka-tests MCP server: questions and answers
Answered from the scan above, not from the publisher's description.
Is the mentalka-tests MCP server safe?
- No scan can promise that. What its definitions show: 4 tools, 3 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 mentalka-tests MCP server delete data?
- No tool is classed as destructive: going by their definitions, none of them deletes, cancels or revokes anything.
Can the mentalka-tests MCP server do things that cannot be undone?
- Yes. 1 tool can send, pay, publish or merge: request_consultation.
What tools does the mentalka-tests MCP server have?
- 4 tools: 1 irreversible, 2 write, 1 read. request_consultation, start_test, score_test and list_tests.
Does the mentalka-tests MCP server need sign-in or OAuth?
- Its remote endpoint listed its tools to an anonymous client, without sign-in.
Does the mentalka-tests MCP server send data to outside services?
- None of its tools sends, posts or publishes, or takes a recipient, channel or URL.
Has the mentalka-tests MCP server changed its tools?
- Yes, once since Anlyon Radar started tracking it, most recently on Nov 16, 2026. Every change is on this page and in its Atom feed.