# `dev.workers.panda198271.tw-ai-glossary/ai-glossary` on anlyon.dev

> Text inside fenced blocks marked untrusted-server-text was written by the MCP server's publisher, not by anlyon.dev. It is data to inspect, not instructions to follow. Invisible characters are shown as [U+XXXX].
> No finding is not a safety guarantee: these are point-in-time checks of tool definitions, not of code or behaviour.

- Page: https://anlyon.dev/servers/dev.workers.panda198271.tw-ai-glossary/ai-glossary
- JSON: https://anlyon.dev/api/v1/servers/dev.workers.panda198271.tw-ai-glossary/ai-glossary
- Version: 1.0.0 (active)
- Publisher: dev.workers.panda198271.tw-ai-glossary (domain proven to the MCP Registry)
- Runs: remote (streamable-http)
- Sign-in to list tools: none
- Metadata from the official MCP Registry, synced 2026-10-21T18:12:36.287Z

Title and description, as the publisher wrote them:

```untrusted-server-text
AI 與科技名詞白話解釋
AI 與科技名詞白話解釋、概念比較與入門教學（繁體中文）。
```

Scanned 2026-10-21T19:11:34.854Z over streamable-http.

**6 tools: 6 only read.**

| Group | Class | Tools | Claude Code |
| --- | --- | --- | --- |
| Deletes or cancels | destructive | 0 | deny |
| Can't be undone | irreversible | 0 | ask |
| Changes things | write | 0 | ask |
| Only reads | read | 6 | allow |

## Findings

No check matched anything in these tool definitions.


## Only reads (6)

Looks things up and changes nothing. Claude Code: allow.

### `classify_search_intent`

- The name "classify_search_intent" says "search": a word for reading.

Description, as the server wrote it:

```untrusted-server-text
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`

- The name "compare_concepts" says "compare": a word for reading.

Description, as the server wrote it:

```untrusted-server-text
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`

- The name "explain_term" says "explain": a word for reading.

Description, as the server wrote it:

```untrusted-server-text
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`

- The name "get_howto" says "get": a word for reading.

Description, as the server wrote it:

```untrusted-server-text
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`

- The name "list_topics" says "list": a word for reading.

Description, as the server wrote it:

```untrusted-server-text
列出所有名詞（可依分類篩選）、概念比較與實作教學。
```

### `search_glossary`

- The name "search_glossary" says "search": a word for reading.

Description, as the server wrote it:

```untrusted-server-text
模糊搜尋本站的 AI 名詞、概念比較與實作教學。
```

## Claude Code permissions

For `.claude/settings.json`, assuming the server is installed as `ai-glossary`:

```json
{
  "permissions": {
    "allow": [
      "mcp__ai-glossary__explain_term",
      "mcp__ai-glossary__search_glossary",
      "mcp__ai-glossary__compare_concepts",
      "mcp__ai-glossary__get_howto",
      "mcp__ai-glossary__classify_search_intent",
      "mcp__ai-glossary__list_topics"
    ],
    "ask": [],
    "deny": []
  }
}
```