搜尋引擎與 AI 爬蟲工具箱 MCP server
com.penguindriver/seopenguindriver.comstreamable-httpv1.0.1Scanned
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。
14 tools: 8 change things and 6 only read.
- Reads private data · 0
- Reads text others write · 14
- Can send data out · 5
- 2 findings
Tools listed without sign-in. Remote posture
With Anlyon
8 tools here change things. Govern them.
- Anlyon lists the tools and adopts none.
- Each tool you adopt gets approvals and receipts.
- Your agent never holds the key.
A tool your agent calls directly is not routed through Anlyon and is not governed by it. Anlyon Radar only lists and labels, and these labels are the same either way.
What the 搜尋引擎與 AI 爬蟲工具箱 MCP server can do
The 搜尋引擎與 AI 爬蟲工具箱 MCP server is published by penguindriver.com, a domain the MCP Registry verified. It has 14 tools. It can create or change data (8 tools: generate_robots_txt, test_robots_txt, check_site_crawlers, verify_crawler_ip and 4 more), but cannot delete data. 6 tools only read.
14 tools bring in text other people can write (build_search_urls, search_operators, generate_robots_txt and 11 more); 5 tools can send data out of your system (check_site_crawlers, serp_preview, generate_meta_tags and 2 more).
The fixed checks matched 2 findings (annotation-conflict). Each one comes with the text it matched.
Its remote endpoint lists its tools without sign-in, and its tools changed once since Anlyon Radar first saw them.
Last scanned Nov 18, 2026, version 1.0.1.
Tools
Grouped by what each tool does, most consequential first. Open one for its reasons and full description; descriptions are the publisher's own words.
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。Reads text others writeCan 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.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
- 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。
Annotations the server declares
- title: 檢查網站的 robots.txt、Sitemap、llms.txt
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: true
generate_meta_tags產生 title、description、canonical、Open Graph、Twitter 卡片與 JSON-LD。Reads text others writeCan send data out1 finding
Why it is in this group
- The name "generate_meta_tags" says "generate": a word for a change.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
- outboundThe input takes a URL (input.url): a request to a URL can carry data to whoever runs it.
Findings
- Warn
The server marks "generate_meta_tags" read-only (readOnlyHint: true), and its own name, description or input give the class "write".
What this check looks forMatched text
annotations: {"readOnlyHint":true,"destructiveHint":false,"idempotentHint":true,"openWorldHint":true}; The name "generate_meta_tags" says "generate": a word for a change.
Description, as the server wrote it 產生 title、description、canonical、Open Graph、Twitter 卡片與 JSON-LD。
Annotations the server declares
- title: generate_meta_tags
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: true
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。Reads text others write1 finding
Why it is in this group
- The name "generate_robots_txt" says "generate": a word for a change.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Findings
- Warn
The server marks "generate_robots_txt" read-only (readOnlyHint: true), and its own name, description or input give the class "write".
What this check looks forMatched text
annotations: {"readOnlyHint":true,"destructiveHint":false,"idempotentHint":true,"openWorldHint":true}; 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。
Annotations the server declares
- title: 產生 robots.txt
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: true
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。Reads text others writeCan 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.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
- 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。
Annotations the server declares
- title: AEO/GEO 引用準備度健檢
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: true
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)。Reads text others writeCan 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
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
- 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)。
Annotations the server declares
- title: indexnow_submit
- readOnlyHint: false
- destructiveHint: false
- idempotentHint: true
- openWorldHint: true
test_robots_txt依 RFC 9309 測試某個 User-Agent 能否抓取某路徑。Reads text others writeNo findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it 依 RFC 9309 測試某個 User-Agent 能否抓取某路徑。
Annotations the server declares
- title: 依 RFC 9309 測試某個 User-Agent 能否抓取某路徑
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: true
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)。Reads text others writeNo findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
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)。
Annotations the server declares
- title: verify_crawler_ip
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: true
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。Reads text others writeNo findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
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。
Annotations the server declares
- title: 檢查 YouTube 章節時間碼
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: true
Only reads 6Show 6 read-only tools
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。Reads text others writeNo findings
Why it is in this group
- The name "ai_crawler_list" says "list": a word for reading.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
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。
Annotations the server declares
- title: AI 與搜尋引擎爬蟲 User-Agent 名單
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: true
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 server marks it openWorldHint: true: it reaches things outside the server's own data.
- 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)。
Annotations the server declares
- title: build_search_urls
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: true
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。Reads text others writeNo findings
Why it is in this group
- The name "search_operators" says "search": a word for reading.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
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。
Annotations the server declares
- title: 搜尋指令
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: true
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。Reads text others writeNo findings
Why it is in this group
- The name "search_submit_guide" says "search": a word for reading.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
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。
Annotations the server declares
- title: search_submit_guide
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: true
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 server marks it openWorldHint: true: it reaches things outside the server's own data.
- 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。
Annotations the server declares
- title: 預覽 Google 搜尋結果標題與描述
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: true
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 write14
- 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.
Remote posture
What anyone on the internet sees at the remote endpoint: an anonymous initialize and tools/list, and the public OAuth metadata.
Looked at Nov 20, 2026, 19:27 UTC, unchanged since Oct 22, 2026. No credentials were sent and no tool was called. What is looked at.
- Reachable
- yes
- HTTP status of an anonymous initialize
- 200
- tools/list served without credentials
- yes
- Tools that change things, listed without credentials
- 8
- Protocol version
- 2025-06-18
- WWW-Authenticate on 401
- not observed
- resource_metadata in WWW-Authenticate
- not observed
- RFC 9728 protected resource metadata
- not observed
- Authorization servers
- not observed
- Legacy HTTP+SSE transport
- no
- Dynamic client registration
- not observed
- Client ID metadata documents
- not observed
- WarnThe whole server
The endpoint served tools/list without credentials, and the list has 8 tools that change things (8 write). Whether a call also works without credentials was not tested: tools are never called.
What this check looks forMatched text
https://seo.penguindriver.com/mcp: tools/list returned 14 tools to an anonymous client, including generate_robots_txt (write), test_robots_txt (write), check_site_crawlers (write), verify_crawler_ip (write), generate_meta_tags (write) and 3 more
Findings
Matches of fixed checks, with the text they matched.
The server marks "generate_robots_txt" read-only (readOnlyHint: true), and its own name, description or input give the class "write".
What this check looks forMatched text
annotations: {"readOnlyHint":true,"destructiveHint":false,"idempotentHint":true,"openWorldHint":true}; The name "generate_robots_txt" says "generate": a word for a change.
The server marks "generate_meta_tags" read-only (readOnlyHint: true), and its own name, description or input give the class "write".
What this check looks forMatched text
annotations: {"readOnlyHint":true,"destructiveHint":false,"idempotentHint":true,"openWorldHint":true}; The name "generate_meta_tags" says "generate": a word for a change.
History
Changes to its tool definitions and to its remote endpoint, newest first.
Tools14 changed.~14 changedView diff
- Changed:ai_crawler_listOnly readstitleannotations
- Changed:build_search_urlsOnly readstitleannotations
- Changed:check_site_crawlersChanges thingstitleannotations
- Changed:generate_meta_tagsChanges thingstitleannotations
- Changed:generate_robots_txtChanges thingstitleannotations
- Changed:geo_citation_auditChanges thingstitleannotations
- Changed:indexnow_submitChanges thingstitleannotations
- Changed:search_engine_market_shareOnly readstitleannotations
- Changed:search_operatorsOnly readstitleannotations
- Changed:search_submit_guideOnly readstitleannotations
- Changed:serp_previewOnly readstitleannotations
- Changed:test_robots_txtChanges thingstitleannotations
- Changed:verify_crawler_ipChanges thingstitleannotations
- Changed:youtube_seo_checkChanges thingstitleannotations
Install
Pinned to version 1.0.1. Values in angle brackets are yours to fill in.
claude mcp add --transport http seo https://seo.penguindriver.com/mcpclaude mcp add --transport http seo https://seo.penguindriver.com/mcpRun 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.
{
"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 14 rules
- mcp__seo__build_search_urls untrusted-input
- mcp__seo__search_operators untrusted-input
- mcp__seo__generate_robots_txt untrusted-input
- mcp__seo__test_robots_txt untrusted-input
- mcp__seo__check_site_crawlers untrusted-input, outbound
- mcp__seo__ai_crawler_list untrusted-input
- mcp__seo__verify_crawler_ip untrusted-input
- mcp__seo__serp_preview untrusted-input, outbound
- mcp__seo__generate_meta_tags untrusted-input, outbound
- mcp__seo__youtube_seo_check untrusted-input
- mcp__seo__indexnow_submit untrusted-input, outbound
- mcp__seo__search_engine_market_share untrusted-input
- mcp__seo__search_submit_guide untrusted-input
- mcp__seo__geo_citation_audit untrusted-input, outbound
Pin
Keep the decision: fail CI when the tools change, follow every change, or show a badge.
Pin in CI
Fail a build when the tools you reviewed are not the tools the server serves today.
curl -s "https://radar.anlyon.com/api/v1/servers/com.penguindriver/seo/verify?hash=39f1f38cc56eee59dfd634e360d402e48a69f16f9a16d2503ddf2e2c89679c34" | jq -e '.changed == false'Pinned hash 39f1f38cc56e, from Nov 18, 2026, 20:19 UTC.
Watch
Get told when its tools change: a new tool, a new description, a new class.
https://radar.anlyon.com/servers/com.penguindriver/seo/changes.xmlAn Atom feed. Works in any feed reader or Slack's RSS app.
Badge
[](https://radar.anlyon.com/servers/com.penguindriver/seo)Source: MCP Registry · repository. Synced Nov 18, 2026, 20:17 UTC.
搜尋引擎與 AI 爬蟲工具箱 MCP server: questions and answers
Answered from the scan above, not from the publisher's description.
Is the 搜尋引擎與 AI 爬蟲工具箱 MCP server safe?
- No scan can promise that. What its definitions show: 14 tools, 8 of which can change, send or delete something, and 2 findings from fixed checks. Allow the reads, ask before each change, and deny the deletes; the permissions block on this page does that.
Can the 搜尋引擎與 AI 爬蟲工具箱 MCP server delete data?
- No tool is classed as destructive: going by their definitions, none of them deletes, cancels or revokes anything.
Can the 搜尋引擎與 AI 爬蟲工具箱 MCP server do things that cannot be undone?
- No tool is classed as irreversible: none of them sends, pays, publishes or merges, going by their definitions.
What tools does the 搜尋引擎與 AI 爬蟲工具箱 MCP server have?
- 14 tools: 8 write, 6 read. generate_robots_txt, test_robots_txt, check_site_crawlers, verify_crawler_ip, generate_meta_tags, youtube_seo_check, indexnow_submit, geo_citation_audit and 6 more.
Does the 搜尋引擎與 AI 爬蟲工具箱 MCP server need sign-in or OAuth?
- Its remote endpoint listed its tools to an anonymous client, without sign-in.
Does the 搜尋引擎與 AI 爬蟲工具箱 MCP server send data to outside services?
- 5 tools can carry data out (it sends, posts or publishes, or takes a recipient, channel or URL): check_site_crawlers, serp_preview, generate_meta_tags, indexnow_submit and geo_citation_audit.
Has the 搜尋引擎與 AI 爬蟲工具箱 MCP server changed its tools?
- Yes, once since Anlyon Radar started tracking it, most recently on Nov 18, 2026. Every change is on this page and in its Atom feed.