GoAI Moat Web Scrape
Scrape any URL into clean LLM-ready Markdown, or crawl a whole site.
我該用這個嗎
品質與安全性
A
發現項目(1)
- LOW在 crawl_website 中
根據工具定義與協定合規性的自動化分析。
上下文成本
~207Token(工具定義)
~996 B典型回應大小
極小的注意力影響(128k 上下文的 0.16%)
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": {
"web-scrape": {
"url": "https://scrape.mcp.goaimoat.com/mcp"
}
}
}遠端端點
https://scrape.mcp.goaimoat.com/mcpstreamable-http它能做什麼
工具清單
工具(2)
🟢 唯讀🟡 寫入🔴 刪除⚪ 未知
⚪scrape_url(url, email, license_key)
Scrape a URL into clean, LLM-ready Markdown.
輸入結構描述
{
"type": "object",
"properties": {
"url": {
"type": "string",
"description": "The full URL to scrape (e.g. https://example.com/article)."
},
"email": {
"default": "",
"type": "string"
},
"license_key": {
"default": "",
"type": "string"
}
},
"required": [
"url"
],
"additionalProperties": false
}輸出結構描述
{
"type": "object",
"additionalProperties": true
}⚪crawl_website(url, limit, email, license_key)
Crawl a website and return clean Markdown for each page.
輸入結構描述
{
"type": "object",
"properties": {
"url": {
"type": "string",
"description": "The starting URL."
},
"limit": {
"default": 10,
"type": "integer",
"description": "Max pages to crawl (default 10)."
},
"email": {
"default": "",
"type": "string"
},
"license_key": {
"default": "",
"type": "string"
}
},
"required": [
"url"
],
"additionalProperties": false
}輸出結構描述
{
"type": "object",
"additionalProperties": true
}社群
證據
近期觀測
已驗證未記錄版本2 個工具
已驗證未記錄版本2 個工具