# 病み期の読み物

> Read-only MCP for public mental-health workflows and Evidence from 病み期の読み物.

- name: io.github.Shiryu-go/mentalhealth
- version: 0.17.0
- connection class: unknown (unknown)
- trust: 44/100 flags: no-repository, unreachable
- quality: 87/100 (good)
- owner: not claimed
- descriptor: https://api.protogrid.dev/v1/servers/io.github.Shiryu-go%2Fmentalhealth
- tools: https://api.protogrid.dev/v1/servers/io.github.Shiryu-go%2Fmentalhealth/tools

**Not classified yet.** The remote endpoints have not been probed successfully, or the listing has nothing to connect to.

## Connection (mcpServers)

```json
{
  "mcpServers": {
    "mentalhealth": {
      "type": "http",
      "url": "https://yami.shiryu.work/mcp"
    }
  }
}
```


## Trust

- hygiene: 80
- liveness: 0
- freshness: 85
- provenance: 35
- drivers: -unreachable(12 failures) ~updated-43d-ago -no-repository
- Derived from observable signals (official registry feed and our own credential-free probes); no code audit performed.

## Quality 87/100 (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 carries no ttlMs, so clients re-fetch it

### 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`: 3 of 3 tools declare readOnlyHint or destructiveHint
- fail `tools.directory_hints`: no tool declares all four of readOnlyHint, destructiveHint, idempotentHint and openWorldHint; missing: list_workflows (idempotentHint); get_evidence (idempotentHint); get_workflow_bundle (idempotentHint)
- pass `tools.token_cost`: about 527 tokens to load every tool
- pass `tools.api_dump`: tools are not a one-to-one API dump

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

- n/a `stability.changes`, `stability.rug_pull`: tool history not recorded yet

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

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

- tools: 3, about 527 tokens to load them all
- badge: [![protogrid quality](https://protogrid.dev/badge/io.github.Shiryu-go/mentalhealth.svg)](https://protogrid.dev/servers/io.github.Shiryu-go/mentalhealth)
- Checks run on what our credential-free, read-only probes observe; tools are never called and no code audit is performed.

### Tool changes

_No tool definition changes recorded._

## Remotes

- https://yami.shiryu.work/mcp (streamable-http, auth none, reachable false, uptime30d 0.29411766)

## Packages

_none_

## Tools (3)

- `get_evidence`: Use this when the user or model needs to verify provenance, support scope, or limitations behind a public workflow or claim. Returns one sanitized public Evidence record by stable ID. Do not use it to decide whether a treatment is appropriate for a person, and do not send personal health information.
- `get_workflow_bundle`: Use this after the user has chosen or explicitly asked to try a candidate returned by list_workflows. Returns an allow-listed structured execution contract together with review and Evidence references. Pass only the public workflow ID; do not send personal health narrative.
- `list_workflows`: Use this when the user wants to explore which small self-help options from 病み期の読み物 may be relevant. Returns only generalized public options, Japanese display names, and repository-defined discovery conditions. Do not use it to diagnose, score suitability, select treatment on the user's behalf, or send personal health narrative to the server.