Boolsai Scan
Live tech-stack scan of any public site — vendors, account IDs, scripts, JSON-LD. 2 tools.
我該用這個嗎
品質與安全性
根據工具定義與協定合規性的自動化分析。
上下文成本
這是每次將伺服器的工具載入模型上下文時所消耗的約略 token 數量。數量越高，可用於其他工作的注意力就越少。
安裝
一鍵安裝
將以下內容加入你的 `claude_desktop_config.json` 檔案：
{
"mcpServers": {
"scan": {
"url": "https://boolsai.ai/mcp"
}
}
}遠端端點
https://boolsai.ai/mcpstreamable-http它能做什麼
工具清單
工具（2）
⚪boolsai_scan(url)
Scan a public website. Returns its full tech stack — every external host the page talks to, every fetch/xhr/beacon endpoint, every inline-script signal, parsed JSON-LD, and the internal DOM/route trie — as structured JSON. Hostnames are returned raw; recognise vendors from them using your own knowledge.
輸入結構描述
{
"type": "object",
"properties": {
"url": {
"type": "string",
"description": "URL or bare domain, e.g. \"gymshark.com\" or \"https://allbirds.com/products/legacy-tee\"."
}
},
"required": [
"url"
]
}🟢boolsai_scan_paths(url, paths)
Scan multiple paths on the same site in parallel and merge the external-host lists. Returns per-path host lists, a unified merged set, and a homepage_missed list (hosts that appeared ONLY on non-home paths). Use when the homepage understates the stack — common on Shopify Plus and consent-gated sites where pixels lazy-load on PDP / cart / checkout. Recommended for ecom audits: paths = ["/", "/products/<any>", "/cart", "/checkout"]. Max 5 paths per call.
輸入結構描述
{
"type": "object",
"properties": {
"url": {
"type": "string",
"description": "Base URL or bare domain (e.g. \"gymshark.com\")."
},
"paths": {
"type": "array",
"items": {
"type": "string"
},
"description": "Path strings to scan, relative to the base (e.g. [\"/\", \"/products/legacy-tee\", \"/cart\"]). Max 5. If omitted, scans just \"/\"."
}
},
"required": [
"url"
]
}比較
同類比較
將此伺服器與同一類別中的其他伺服器比較。
社群
證據