Skip to content

搜尋引擎與 AI 爬蟲工具箱

by penguindriver.com · remote · no sign-in to list tools · v1.0.0 · published by com.penguindriver

搜尋引擎與 AI 爬蟲工具箱：搜尋指令、爬蟲驗證、收錄與 AEO 健檢。台灣繁體中文 MCP 工具。

Changes · 8
CompareRegistry entry

14 tools: 8 change things and 6 only read.

Scanned Oct 21, 2026

No check matched anything in the tool definitions. No finding is not a safety guarantee. How the checks work.

claude mcp add --transport http seo https://seo.penguindriver.com/mcp

Tools

Open a tool for its reasons and full description. Descriptions are the publisher's own words, shown as they are.

14 tools

Changes things 8Claude Code: ask
  • check_site_crawlers檢查網站的 robots.txt、Sitemap、llms.txt，以及 Googlebot、bingbot、GPTBot、ClaudeBot、PerplexityBot 等是否被封鎖，附改善建議。Can send data outNo findings

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.

    What it can reach

    • outboundThe input takes a URL (input.url): a request to a URL can carry data to whoever runs it.
    Description, as the server wrote it
    檢查網站的 robots.txt、Sitemap、llms.txt，以及 Googlebot、bingbot、GPTBot、ClaudeBot、PerplexityBot 等是否被封鎖，附改善建議。
  • generate_meta_tags產生 title、description、canonical、Open Graph、Twitter 卡片與 JSON-LD。Can send data outNo findings

    Why it is in this group

    • The name "generate_meta_tags" says "generate": a word for a change.

    What it can reach

    • outboundThe input takes a URL (input.url): a request to a URL can carry data to whoever runs it.
    Description, as the server wrote it
    產生 title、description、canonical、Open Graph、Twitter 卡片與 JSON-LD。
  • generate_robots_txt產生 robots.txt：allow_all、block_training（封鎖 AI 訓練保留搜尋）、block_all_ai、block_all，可加不抓路徑與 Sitemap。No findings

    Why it is in this group

    • The name "generate_robots_txt" says "generate": a word for a change.
    Description, as the server wrote it
    產生 robots.txt：allow_all、block_training（封鎖 AI 訓練保留搜尋）、block_all_ai、block_all，可加不抓路徑與 Sitemap。
  • geo_citation_auditAEO／GEO 引用準備度健檢：檢查網頁能否被 ChatGPT、Perplexity、Google AI 摘要等答案引擎引用（爬蟲可讀、開頭直接回答、問句標題、表格、外部與權威來源、更新日期、JSON-LD citation、llms.txt、Markdown 版、Content-Digest），給分數與優先修正清單。Can send data outNo findings

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.

    What it can reach

    • outboundThe input takes a URL (input.url): a request to a URL can carry data to whoever runs it.
    Description, as the server wrote it
    AEO／GEO 引用準備度健檢：檢查網頁能否被 ChatGPT、Perplexity、Google AI 摘要等答案引擎引用（爬蟲可讀、開頭直接回答、問句標題、表格、外部與權威來源、更新日期、JSON-LD citation、llms.txt、Markdown 版、Content-Digest），給分數與優先修正清單。
  • indexnow_submit用 IndexNow 通知 Bing、Yandex、Naver 等搜尋引擎網址已更新（需先在網站放金鑰檔，最多 100 個網址）。Can send data outNo findings

    Why it is in this group

    • The name "indexnow_submit" says "submit": a word for a change.

    What it can reach

    • outboundThe input takes a URL (input.urls): a request to a URL can carry data to whoever runs it.
    Description, as the server wrote it
    用 IndexNow 通知 Bing、Yandex、Naver 等搜尋引擎網址已更新（需先在網站放金鑰檔，最多 100 個網址）。
  • test_robots_txt依 RFC 9309 測試某個 User-Agent 能否抓取某路徑。No findings

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.
    Description, as the server wrote it
    依 RFC 9309 測試某個 User-Agent 能否抓取某路徑。
  • verify_crawler_ip驗證 IP 是否真的來自 Googlebot、bingbot、GPTBot、ClaudeBot、PerplexityBot、Applebot、Baiduspider 等（官方 IP 清單＋反查 DNS）。No findings

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.
    Description, as the server wrote it
    驗證 IP 是否真的來自 Googlebot、bingbot、GPTBot、ClaudeBot、PerplexityBot、Applebot、Baiduspider 等（官方 IP 清單＋反查 DNS）。
  • youtube_seo_check檢查 YouTube 章節時間碼（0:00 起、至少 3 段、每段 10 秒）與標題、說明、標籤、主題標籤數量上限。No findings

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.
    Description, as the server wrote it
    檢查 YouTube 章節時間碼（0:00 起、至少 3 段、每段 10 秒）與標題、說明、標籤、主題標籤數量上限。
Only reads 6Claude Code: allow, ask for 1 outbound
  • ai_crawler_listAI 與搜尋引擎爬蟲 User-Agent 名單：業者、用途、是否遵守 robots.txt、官方 IP 清單。No findings

    Why it is in this group

    • The name "ai_crawler_list" says "list": a word for reading.
    Description, as the server wrote it
    AI 與搜尋引擎爬蟲 User-Agent 名單：業者、用途、是否遵守 robots.txt、官方 IP 清單。
  • build_search_urls一次產生 Google、Bing、Yahoo 奇摩、百度、YouTube 的進階搜尋網址（關鍵字、完全符合、排除字、限定網站、檔案類型、時間）。Reads text others writeNo findings

    Why it is in this group

    • The name "build_search_urls" says "search": a word for reading.

    What it can reach

    • untrusted-inputThe name "build_search_urls" says "search" and "url": it reads web pages, which anyone can write.
    Description, as the server wrote it
    一次產生 Google、Bing、Yahoo 奇摩、百度、YouTube 的進階搜尋網址（關鍵字、完全符合、排除字、限定網站、檔案類型、時間）。
  • search_engine_market_share台灣與全球搜尋引擎市佔率（Google、Bing、Yahoo、百度等，StatCounter 最新月份）。No findings

    Why it is in this group

    • The name "search_engine_market_share" says "search": a word for reading.
    Description, as the server wrote it
    台灣與全球搜尋引擎市佔率（Google、Bing、Yahoo、百度等，StatCounter 最新月份）。
  • search_operators搜尋指令（site:、filetype:、intitle:、before: 等）在 Google、Bing、Yahoo、百度的支援對照與已失效指令。No findings

    Why it is in this group

    • The name "search_operators" says "search": a word for reading.
    Description, as the server wrote it
    搜尋指令（site:、filetype:、intitle:、before: 等）在 Google、Bing、Yahoo、百度的支援對照與已失效指令。
  • search_submit_guide如何讓 Google、Bing、Yahoo、百度、YouTube、AI 搜尋收錄網站：工具、步驟與 API。No findings

    Why it is in this group

    • The name "search_submit_guide" says "search": a word for reading.
    Description, as the server wrote it
    如何讓 Google、Bing、Yahoo、百度、YouTube、AI 搜尋收錄網站：工具、步驟與 API。
  • serp_preview預覽 Google 搜尋結果標題與描述，估算中文像素寬度與截斷位置。Reads text others writeCan send data outNo findings

    Why it is in this group

    • The name "serp_preview" says "preview": a word for reading.

    What it can reach

    • untrusted-inputThe input takes a URL (input.url), and the tool reads it: it reads web pages, which anyone can write.
    • outboundThe input takes a URL (input.url): a request to a URL can carry data to whoever runs it.

    Claude Code: ask, because it is tagged outbound.

    Description, as the server wrote it
    預覽 Google 搜尋結果標題與描述，估算中文像素寬度與截斷位置。

This is not a safety rating, and no finding is not a safety guarantee. The groups and findings come from fixed checks of the tool definitions the server returned on the date shown, not from its code or what it does when called. How the checks work.

Exfil surface

Which tools read private data, which read text someone else can write, and which can send data out. One of each is a path a prompt injection can use.

No private-data, untrusted-input, outbound path in this server alone: no tool is tagged private-data.

Reads private data0
Reads files, mail, messages, databases, secrets, calendars or repositories.
Reads text others write2
Brings in text someone else can write: web pages, inbound email, messages, issues and comments.
Can send data out5
Can carry data to people or systems: it sends, posts or publishes, or takes a recipient, channel or URL.

Other servers in the same agent add their own tools to these paths. Audit your whole setup to see them together.

Install

Pinned to version 1.0.0. Values in angle brackets are yours to fill in.

claude mcp add --transport http seo https://seo.penguindriver.com/mcp

Run in a terminal.

Claude Code permissions

Allow the reads, ask before a change or a way out, deny the deletes. Paste into .claude/settings.json.

.claude/settings.json
{
  "permissions": {
    "allow": [
      "mcp__seo__build_search_urls",
      "mcp__seo__search_operators",
      "mcp__seo__ai_crawler_list",
      "mcp__seo__search_engine_market_share",
      "mcp__seo__search_submit_guide"
    ],
    "ask": [
      "mcp__seo__generate_robots_txt",
      "mcp__seo__test_robots_txt",
      "mcp__seo__check_site_crawlers",
      "mcp__seo__verify_crawler_ip",
      "mcp__seo__serp_preview",
      "mcp__seo__generate_meta_tags",
      "mcp__seo__youtube_seo_check",
      "mcp__seo__indexnow_submit",
      "mcp__seo__geo_citation_audit"
    ],
    "deny": []
  }
}

Tools that only read are allowed, tools that change things ask first, tools that delete or cancel are denied. A read that can send data out (it takes a URL, say) asks first too. It assumes the server is installed as seo. Review it before you use it.

Capability tags behind 6 rules
  • mcp__seo__build_search_urls untrusted-input
  • mcp__seo__check_site_crawlers outbound
  • mcp__seo__serp_preview untrusted-input, outbound
  • mcp__seo__generate_meta_tags outbound
  • mcp__seo__indexnow_submit outbound
  • mcp__seo__geo_citation_audit outbound