# io.github.Yuikij/mcp-turtle-noir

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

- name: io.github.Yuikij/mcp-turtle-noir
- version: 1.3.0
- connection class: R0 (autonomous)
- trust: 90/100
- quality: 77/100 (good)
- owner: not claimed
- descriptor: https://api.protogrid.dev/v1/servers/io.github.Yuikij%2Fmcp-turtle-noir
- tools: https://api.protogrid.dev/v1/servers/io.github.Yuikij%2Fmcp-turtle-noir/tools

**An agent can connect right now, no human step.** Remote endpoint, no authentication, reachable on the last probe.

## Connection (mcpServers)

```json
{
  "mcpServers": {
    "mcp-turtle-noir": {
      "type": "http",
      "url": "https://turtlenoir.com/mcp"
    }
  }
}
```


## Trust

- hygiene: 100
- liveness: 99
- freshness: 65
- provenance: 90
- drivers: +repository +namespace-matches-repo +website +reachable +uptime-98% ~updated-91d-ago
- Derived from observable signals (official registry feed and our own credential-free probes); no code audit performed.

## Quality 77/100 (good)

### protocol: 75 (weight 25)

- warn `protocol.modern`: newest supported version is 2025-06-18; 2026-07-28 not supported, older versions are deprecated until 2027-07-28
- n/a `protocol.stateless`: only applies to 2026-07-28 servers
- pass `protocol.transport`: streamable HTTP
- n/a `protocol.list_ttl`: only applies to 2026-07-28 servers

### 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: 71 (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
- fail `tools.annotations`: no tool declares readOnlyHint or destructiveHint, so clients cannot tell safe calls from risky ones
- fail `tools.directory_hints`: no tool declares all four of readOnlyHint, destructiveHint, idempotentHint and openWorldHint; missing: give_up_and_reveal (readOnlyHint, destructiveHint, idempotentHint, openWorldHint); ask_question (readOnlyHint, destructiveHint, idempotentHint, openWorldHint); start_session (readOnlyHint, destructiveHint, idempotentHint, openWorldHint)
- pass `tools.token_cost`: about 317 tokens to load every tool
- pass `tools.api_dump`: tools are not a one-to-one API dump

### stability: 100 (weight 15)

- pass `stability.changes`: no tool changes in 30 days
- pass `stability.rug_pull`: no tool changed its meaning under the same name

### dependencies: 67 (weight 15)

- pass `deps.known_vulns`: no known advisory in 16 resolved packages
- fail `deps.mcp_sdk_version`: @modelcontextprotocol/sdk 0.5.0 has 1 known advisory (GHSA-w48q-cv73-mx4w); update @modelcontextprotocol/sdk to 1.24.0 or later
- pass `deps.resolvable`: mcp-turtle-noir@1.2.2 resolved: 16 packages

- tools: 3, about 317 tokens to load them all
- tool set hash: fac776b2629db7a59de3c532b174872e
- badge: [![protogrid quality](https://protogrid.dev/badge/io.github.Yuikij/mcp-turtle-noir.svg)](https://protogrid.dev/servers/io.github.Yuikij/mcp-turtle-noir)
- 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._

## Dependencies

- npm mcp-turtle-noir@1.2.2: resolved, 15 dependencies, MCP SDK @modelcontextprotocol/sdk 0.5.0
  - GHSA-w48q-cv73-mx4w (high) in `` @modelcontextprotocol/sdk@0.5.0 ``, direct, fixed in `` 1.24.0 ``, advisory summary: "Model Context Protocol (MCP) TypeScript SDK does not enable DNS rebinding protection by default" https://osv.dev/vulnerability/GHSA-w48q-cv73-mx4w

Dependency graphs from deps.dev; advisories from OSV.dev, including the GitHub Advisory Database and the PyPI Advisory Database; all CC BY 4.0.

## Remotes

- https://turtlenoir.com/mcp (streamable-http, auth none, reachable true, uptime30d 0.9831933)

## Packages

- npm mcp-turtle-noir@1.2.2

## Tools (3)

- `ask_question`: Ask one yes/no style question about the current puzzle. The AI host answers with one of four judgments: 是(Yes) / 不是(No) / 是也不是(Both) / 没有关系(Irrelevant), plus solve progress (0-100).
- `give_up_and_reveal`: Reveal the hidden solution and end the session. Only allowed once solve progress reaches 60.
- `start_session`: Start a new Turtle Soup (lateral thinking puzzle) session. Returns the surface story; the hidden solution stays on the server. Optional filters: region (CN/US/JP), difficulty, keyword.