# io.github.Yuikij/mcp-turtle-noir (npm · mcp-turtle-noir)

Play Turtle Soup (lateral thinking puzzles) against a strict AI host with yes/no questioning.

- Trust score: 59/100 (low)
- Change this week: +13
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-08-03

## Components

- remote · `turtlenoir.com`: 65/100, [markdown](https://verifymcp.io/servers/yuikij-mcp-turtle-noir/turtlenoir.md), [page](https://verifymcp.io/servers/yuikij-mcp-turtle-noir/turtlenoir)
- npm · `mcp-turtle-noir`: 59/100 (this document), [markdown](https://verifymcp.io/servers/yuikij-mcp-turtle-noir/mcp-turtle-noir.md), [page](https://verifymcp.io/servers/yuikij-mcp-turtle-noir/mcp-turtle-noir)

## Channel facts

- Registry: `npm`
- Package: `mcp-turtle-noir`
- Version: `1.2.2`
- Transport: `stdio`

## Trust breakdown

How this component scores in each security and reliability category. Every signal is checked automatically from public evidence about the published package, including repeated runs of it in an isolated sandbox, and we only credit what we can confirm. Scores are 0–100 per category. Scoring method: https://verifymcp.io/docs/scoring (what has changed: https://verifymcp.io/docs/scoring/changelog)

Scored 2026-08-03.

- **Supply Chain Security**: 70/100
  - No malware found by supply-chain analysis.
  - CVE check failed: a known high-severity CVE affects @modelcontextprotocol/sdk 0.5.0, a direct dependency. A fixed version is available.
  - No install/post-install scripts declared.
  - Only part of the dependency tree could be resolved (14 of 15), so this covers what we could see, not the whole tree.
- **Provenance & Transparency**: 45/100
  - Source repository is publicly reachable at the declared URL.
  - Provenance check failed: no build-provenance attestation is published.
  - Clear OSI-approved license (MIT).
  - Actively maintained (last published 12 days ago).
  - Disclosure check failed: no security disclosure policy was found in the source repository.
- **Schema Quality & AI Usability**: 71/100
  - AI-judged instruction clarity (good).
  - Tool/resource definitions use about 271 tokens (~90/item across 3 items; 3 tools + 0 resources), lean.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 27/100
  - Stability observed for 8 of 30 days with no destabilising changes; credit accrues until the full window elapses.
- **Tool Coverage**: 100/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 100% of tool parameters carry a description.
- **Capabilities**: 20/100
  - Spec-recency check failed: implements MCP spec 2024-11-05; the latest is 2026-07-28.

## Install

### Claude

```bash
claude mcp add yuikij-mcp-turtle-noir -- npx -y mcp-turtle-noir
```

### Codex

```bash
codex mcp add yuikij-mcp-turtle-noir -- npx -y mcp-turtle-noir
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "yuikij-mcp-turtle-noir": {
      "type": "local",
      "command": [
        "npx",
        "-y",
        "mcp-turtle-noir"
      ],
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add yuikij-mcp-turtle-noir --command npx --arg -y --arg mcp-turtle-noir
```

### Hermes

```yaml
mcp_servers:
  yuikij-mcp-turtle-noir:
    command: "npx"
    args: ["-y", "mcp-turtle-noir"]
```

### Other

```json
{
  "mcpServers": {
    "yuikij-mcp-turtle-noir": {
      "command": "npx",
      "args": [
        "-y",
        "mcp-turtle-noir"
      ]
    }
  }
}
```

## Changelog

Every change recorded for this component, newest first. Days that predate change tracking, or that we cannot explain, say so: "we were watching and nothing happened" and "we were not watching" are different claims.

### 2026-08-02 (score 59, +21)

- [security regression] CVE-2025-66414 affects this package: high
- [security regression] Known CVEs: unverified → fail
- [security regression] Install scripts: pass → unverified
- [security regression] Provenance: fail → unverified
- [security improvement] Malware scan: unverified → pass
- [functional regression] License: pass → unverified
- [functional regression] Maintenance: pass → unverified
- [functional improvement] Dependency health: unverified → partial
- [functional improvement] Stability: unverified → 0.23
- [functional] Licence: MIT

### 2026-08-01 (score 38, 0)

- [functional] We updated how we score, so this day's move reflects our rubric, not a change to the server

### 2026-07-31 (score 38, +11)

- [security regression] Provenance: unverified → fail
- [security regression] Malware scan: pass → unverified
- [security improvement] Install scripts: unverified → pass
- [functional regression] Dependency health: partial → unverified
- [functional improvement] Tool coverage: unverified → 100
- [functional improvement] License: unverified → pass
- [functional improvement] Maintenance: unverified → pass
- [functional] Licence: MIT

### 2026-07-29 (score 27, −9)

- [security regression] Known CVEs: partial → unverified

### 2026-07-28 (score 36, −10)

- [security improvement] Known CVEs: unverified → partial
- [functional regression] Tool coverage: 100 → unverified
- [functional improvement] Dependency health: unverified → partial
- [functional] First check of Schema quality: unverified

### 2026-07-27 (score 46)

First indexed and scored.

## MCP tools (3)

### `start_session` (~110 tokens)

Start a new Turtle Soup session. Detect user language and pass language (zh-CN/en-US/ja-JP). Optional: region, difficulty, keyword.

Input parameters:

- `difficulty` (string): Optional difficulty preference
- `keyword` (string): Optional fuzzy keyword on title/surface/tags
- `language` (string): User language for localized response, e.g. zh-CN/en-US/ja-JP
- `region` (string): Optional region code, e.g. US/CN/JP

### `ask_question` (~83 tokens)

Ask a question for the active session. Detect user language and pass language (zh-CN/en-US/ja-JP).

Input parameters:

- `language` (string): User language for localized response, e.g. zh-CN/en-US/ja-JP
- `question` (string, required): Detective question to judge
- `session_id` (string, required): Session ID returned by start_session

### `give_up_and_reveal` (~78 tokens)

Give up the current session and reveal the full story. Detect user language and pass language (zh-CN/en-US/ja-JP).

Input parameters:

- `language` (string): User language for localized response, e.g. zh-CN/en-US/ja-JP
- `session_id` (string, required): Session ID returned by start_session

## Diagnostics

Captured diagnostic sections: Provenance, Vulnerabilities, Dependencies. The full working is on the page: https://verifymcp.io/servers/yuikij-mcp-turtle-noir/mcp-turtle-noir#diagnostics

## Score history

- 2026-08-03: 59
- 2026-08-02: 59
- 2026-08-01: 38
- 2026-07-31: 38
- 2026-07-29: 27
- 2026-07-28: 36
- 2026-07-27: 46

## Links

- npm package: https://www.npmjs.com/package/mcp-turtle-noir
- Socket report: https://socket.dev/npm/package/mcp-turtle-noir
- Repository: https://github.com/Yuikij/mcp-turtle-noir
- Website: https://turtlenoir.com/
- Changelog RSS feed: https://verifymcp.io/servers/yuikij-mcp-turtle-noir/mcp-turtle-noir/changelog.xml
- Changelog JSON feed: https://verifymcp.io/servers/yuikij-mcp-turtle-noir/mcp-turtle-noir/changelog.json
- HTML version of this page: https://verifymcp.io/servers/yuikij-mcp-turtle-noir/mcp-turtle-noir