# AI 與科技名詞白話解釋

> AI 與科技名詞白話解釋：MCP、RAG、AI 代理人等名詞的白話定義。台灣繁體中文 MCP 工具。

- name: com.penguindriver/glossary
- version: 1.0.0
- connection class: R0 (autonomous)
- trust: 82/100 flags: no-repository
- quality: 79/100 (good)
- owner: not claimed
- descriptor: https://api.protogrid.dev/v1/servers/com.penguindriver%2Fglossary
- tools: https://api.protogrid.dev/v1/servers/com.penguindriver%2Fglossary/tools

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

## Connection (mcpServers)

```json
{
  "mcpServers": {
    "glossary": {
      "type": "http",
      "url": "https://glossary.penguindriver.com/mcp"
    }
  }
}
```


## Trust

- hygiene: 80
- liveness: 99
- freshness: 100
- provenance: 55
- drivers: +dns-namespace +website +reachable +uptime-96% +updated-22d-ago -no-repository
- Derived from observable signals (official registry feed and our own credential-free probes); no code audit performed.

## Quality 79/100 (good)

### protocol: 75 (weight 25)

- warn `protocol.modern`: newest supported version is 2025-11-25; 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: explain_term (readOnlyHint, destructiveHint, idempotentHint, openWorldHint); search_glossary (readOnlyHint, destructiveHint, idempotentHint, openWorldHint); get_howto (readOnlyHint, destructiveHint, idempotentHint, openWorldHint); …
- pass `tools.token_cost`: about 282 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: n/a (weight 15)

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

- tools: 6, about 282 tokens to load them all
- tool set hash: 73351f761178f31cd455ce9f9c320575
- badge: [![protogrid quality](https://protogrid.dev/badge/com.penguindriver/glossary.svg)](https://protogrid.dev/servers/com.penguindriver/glossary)
- 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://glossary.penguindriver.com/mcp (streamable-http, auth none, reachable true, uptime30d 0.9647059)

## Packages

_none_

## Tools (6)

- `classify_search_intent`: 判斷一句搜尋或提問屬於資訊探索、商業比較、技術除錯或行動指引哪種意圖，並給出建議答案結構、結構化資料類型與本站相關內容。
- `compare_concepts`: 比較兩個 AI 概念差在哪（如 RAG vs 微調、MCP vs API、SEO vs GEO），回傳結論、比較表與各自適用情境。可給 id，或 a、b 兩個名詞。
- `explain_term`: 用白話解釋 AI 或科技名詞（如 MCP、RAG、AI 代理人、幻覺、GEO、x402），回傳定義、運作方式、例子、常見誤解、FAQ 與原始來源。可用中文、英文或別名。
- `get_howto`: 取得 AI 實作教學（建立 MCP 伺服器、llms.txt、FAQPage JSON-LD、robots.txt 封鎖 AI 訓練、x402 流程、計算 Token），含需求、步驟、程式碼與常見錯誤。
- `list_topics`: 列出所有名詞（可依分類篩選）、概念比較與實作教學。
- `search_glossary`: 模糊搜尋本站的 AI 名詞、概念比較與實作教學。