Connect

8 clients · secrets stay placeholders

JSON (mcpServers)Claude CodeCodexOpenCodeCursorVS CodeGemini CLIGoose

{
  "mcpServers": {
    "mentalka-tests": {
      "type": "http",
      "url": "https://mentalka.app/api/mcp"
    }
  }
}

claude mcp add --transport http mentalka-tests https://mentalka.app/api/mcp

[mcp_servers.mentalka-tests]
url = "https://mentalka.app/api/mcp"

{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "mentalka-tests": {
      "type": "remote",
      "url": "https://mentalka.app/api/mcp",
      "enabled": true
    }
  }
}

{
  "mcpServers": {
    "mentalka-tests": {
      "type": "http",
      "url": "https://mentalka.app/api/mcp"
    }
  },
  "deeplink": "cursor://anysphere.cursor-deeplink/mcp/install?name=mentalka-tests&config=eyJ0eXBlIjoiaHR0cCIsInVybCI6Imh0dHBzOi8vbWVudGFsa2EuYXBwL2FwaS9tY3AifQ%3D%3D"
}

{
  "servers": {
    "mentalka-tests": {
      "type": "http",
      "url": "https://mentalka.app/api/mcp"
    }
  }
}

{
  "mcpServers": {
    "mentalka-tests": {
      "httpUrl": "https://mentalka.app/api/mcp"
    }
  }
}

extensions:
  "mentalka-tests":
    enabled: true
    name: "mentalka-tests"
    type: streamable_http
    uri: "https://mentalka.app/api/mcp"
    timeout: 300

Quality 83 / 100good

protocol88 · weight 25

pass
protocol.modernsupports 2026-07-28 (server/discover)
pass
protocol.statelessanswers without a session
pass
protocol.transportstreamable HTTP
warn
protocol.list_ttltools/list declares ttlMs 0, so clients re-fetch it on every use

authorizationn/a · weight 15

n/a
auth.prm, auth.as_metadata, auth.cimdno remote uses OAuth
n/a
auth.secret_in_urlno templated URL

tool hygiene71 · weight 30

pass
tools.descriptionsevery tool has a description
pass
tools.description_lengthdescriptions are concise
pass
tools.schemasevery tool has an object input schema
fail
tools.annotationsno tool declares readOnlyHint or destructiveHint, so clients cannot tell safe calls from risky ones
fail
tools.directory_hintsno tool declares all four of readOnlyHint, destructiveHint, idempotentHint and openWorldHint; missing: list_tests (readOnlyHint, destructiveHint, idempotentHint, openWorldHint); start_test (readOnlyHint, destructiveHint, idempotentHint, openWorldHint); score_test (readOnlyHint, destructiveHint, idempotentHint, openWorldHint); …
pass
tools.token_costabout 644 tokens to load every tool
pass
tools.api_dumptools are not a one-to-one API dump

stability100 · weight 15

pass
stability.changesno tool changes in 30 days
pass
stability.rug_pullno tool changed its meaning under the same name

dependenciesn/a · weight 15

n/a
deps.known_vulns, deps.mcp_sdk_version, deps.resolvableno npm or PyPI package

4 tools, about 644 tokens to load them all · tool set a59ecc0460f0 · checked 2026-10-20 11:08 UTC

Tool changes

No tool definition changes recorded. A server's first observation is its baseline; later probes record what changes.

Checks run on what our credential-free, read-only probes observe; tools are never called and no code audit is performed. How it is computed.

Trust 97 / 100

provenance90

liveness100

freshness100

hygiene100

+repository +namespace-matches-repo +website +reachable +uptime-100% +updated-12d-ago

Derived from observable signals (official registry feed and our own credential-free probes); no code audit performed. How it is computed.

Endpoints

remote	auth	reachable	uptime 30d	p50	protocol	last ok
`https://mentalka.app/api/mcp` streamable-http	none	yes	100%	508 ms	2026-07-28	2026-10-20

Tools (4)

`list_tests`	List the psychological screening tests available on mentalka.app.
`request_consultation`	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.
`score_test`	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_test`	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.

Schemas: list_tools.

Similar MCP servers

Official server.json

{
  "name": "io.github.Protopopov/mentalka-tests",
  "$schema": "https://static.modelcontextprotocol.io/schemas/2025-07-09/server.schema.json",
  "remotes": [
    {
      "url": "https://mentalka.app/api/mcp",
      "type": "streamable-http"
    }
  ],
  "version": "0.1.0",
  "repository": {
    "url": "https://github.com/Protopopov/emotion_recognition",
    "source": "github"
  },
  "websiteUrl": "https://mentalka.app/ai",
  "description": "Free anonymous PHQ-9 depression and SAS smartphone-addiction screenings in uk, en, hr, ru, pl."
}