Connect 搜尋引擎與 AI 爬蟲工具箱 and your agent gets 14 tools, among them ai_crawler_list, build_search_urls, check_site_crawlers. It answers at https://tw-search-seo.panda198271.workers.dev/mcp over streamable HTTP, and it listed its tools to an anonymous client, so no sign-in was needed for that. Our probes reached it 4 of 4 times since 27 September 2026; the last check, on 12 November 2026, succeeded.
檢查網站爬蟲設定、驗證爬蟲 IP、IndexNow 提交與 YouTube SEO 檢查。
Description as the publisher wrote it.
| Tool | What it does |
|---|---|
ai_crawler_list | 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。 Inputs: type |
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)。 Inputs: q, exact, exclude, site, filetype, time |
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。 Inputs: url |
generate_meta_tags | 產生 title、description、canonical、Open Graph、Twitter 卡片與 JSON-LD。 Inputs: title, description, url, image, site_name, type |
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。 Inputs: mode, disallow, sitemap |
geo_citation_audit | 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。 Inputs: url |
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)。 Inputs: host, key, urls, keyLocation |
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)。 |
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。 Inputs: engine |
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。 |
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。 Inputs: title, description, url |
test_robots_txt | 依 RFC 9309 測試某個 User-Agent 能否抓取某路徑。 Inputs: robots, user_agent, path |
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)。 Inputs: ip, bot |
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。 Inputs: chapters, duration, title, description, tags |
Every block below points at https://tw-search-seo.panda198271.workers.dev/mcp. Pick your client and copy.
claude mcp add --transport http ai https://tw-search-seo.panda198271.workers.dev/mcp
{
"mcpServers": {
"ai": {
"command": "npx",
"args": ["-y", "mcp-remote", "https://tw-search-seo.panda198271.workers.dev/mcp"]
}
}
}{
"mcpServers": {
"ai": {
"url": "https://tw-search-seo.panda198271.workers.dev/mcp"
}
}
}{
"servers": {
"ai": {
"type": "http",
"url": "https://tw-search-seo.panda198271.workers.dev/mcp"
}
}
}{
"context_servers": {
"ai": {
"url": "https://tw-search-seo.panda198271.workers.dev/mcp"
}
}
}{
"mcpServers": {
"ai": {
"serverUrl": "https://tw-search-seo.panda198271.workers.dev/mcp"
}
}
}{
"mcpServers": {
"ai": {
"url": "https://tw-search-seo.panda198271.workers.dev/mcp"
}
}
}name: 搜尋引擎與 AI 爬蟲工具箱
version: 0.0.1
schema: v1
mcpServers:
- name: 搜尋引擎與 AI 爬蟲工具箱
type: streamable-http
url: https://tw-search-seo.panda198271.workers.dev/mcp{
"mcpServers": {
"ai": {
"httpUrl": "https://tw-search-seo.panda198271.workers.dev/mcp"
}
}
}{
"mcpServers": {
"ai": {
"type": "http",
"url": "https://tw-search-seo.panda198271.workers.dev/mcp"
}
}
}{
"mcpServers": {
"ai": {
"url": "https://tw-search-seo.panda198271.workers.dev/mcp"
}
}
}goose://extension?url=https%3A%2F%2Ftw-search-seo.panda198271.workers.dev%2Fmcp&type=streamable_http&id=ai&name=%E6%90%9C%E5%B0%8B%E5%BC%95%E6%93%8E%E8%88%87%20AI%20%E7%88%AC%E8%9F%B2%E5%B7%A5%E5%85%B7%E7%AE%B1
It answered our last check on 12 November 2026 in 228 ms. Over 4 checks since 27 September 2026 it answered 4. Status here comes from Neuronto's own probes, not from the publisher.
14, as returned by the server's own tools/list on 16 November 2026: ai_crawler_list, build_search_urls, check_site_crawlers, generate_meta_tags, generate_robots_txt, geo_citation_audit, indexnow_submit, search_engine_market_share, and 6 more.
It answered our last check on 12 November 2026 in 228 ms. Over 4 checks since 27 September 2026 it answered 4.
Put the server under mcpServers in ~/.cursor/mcp.json with the URL https://tw-search-seo.panda198271.workers.dev/mcp. The exact JSON is above, with the same setup for Claude Code, Claude Desktop, VS Code, Windsurf, Zed, Gemini CLI and the rest.
It listed its tools to an anonymous client, so reading the tool list needs no key. Individual tools can still ask for credentials in their own inputs.
Publisher: dev.workers.panda198271.tw-search-seo. Endpoint host: tw-search-seo.panda198271.workers.dev. ARD identifier: urn:air:dev.workers.panda198271.tw-search-seo:mcp:search-seo.
First indexed 27 September 2026. The tools are exactly what the server returned; nothing on this page
is inferred from its name. Ranking in Neuronto search is never for sale.