SnoopScan
Web scraping for agents: scrape, crawl, map, search and extract pages as clean markdown or JSON.
使うべきか
品質と安全性
ツール定義とプロトコルへの準拠に関する自動分析に基づいています。
コンテキストコスト
これは、サーバーのツールがモデルのコンテキストに読み込まれるたびに消費されるおおよそのトークン数です。数が多いほど、ほかのタスクに使える注意が減ります。
インストール
ワンクリックインストール
これを `claude_desktop_config.json` ファイルに追加してください:
{
"mcpServers": {
"snoopscan": {
"url": "https://api.snoopscan.com/mcp-oauth"
}
}
}リモートエンドポイント
https://api.snoopscan.com/mcp-oauthstreamable-httphttps://api.snoopscan.com/mcpstreamable-httpできること
ツール一覧
ツール（3）
🟢scrape(url, formats, onlyMainContent, maxChars, maxAge, ...)
Fetch a single web page and return its content as clean markdown. Use this when you have a specific URL and need to read what is on it. For finding pages first, use `search` or `map`.
入力スキーマ
{
"type": "object",
"properties": {
"url": {
"title": "Url",
"type": "string"
},
"formats": {
"anyOf": [
{
"items": {
"type": "string"
},
"type": "array"
},
{
"type": "null"
}
],
"default": null,
"title": "Formats"
},
"onlyMainContent": {
"default": true,
"title": "Onlymaincontent",
"type": "boolean"
},
"maxChars": {
"default": 20000,
"title": "Maxchars",
"type": "integer"
},
"maxAge": {
"default": 172800000,
"title": "Maxage",
"type": "integer"
},
"waitFor": {
"default": 0,
"title": "Waitfor",
"type": "integer"
}
},
"required": [
"url"
],
"title": "scrapeArguments"
}出力スキーマ
{
"type": "object",
"properties": {
"result": {
"title": "Result",
"type": "string"
}
},
"required": [
"result"
],
"title": "scrapeOutput"
}🟢parse(url, maxChars)
Read a document at a URL, such as a PDF, and return its text as markdown. Use this for a link to a document rather than a web page. A URL that turns out to be an ordinary page is returned as that page. Billed per document page.
入力スキーマ
{
"type": "object",
"properties": {
"url": {
"title": "Url",
"type": "string"
},
"maxChars": {
"default": 20000,
"title": "Maxchars",
"type": "integer"
}
},
"required": [
"url"
],
"title": "parseArguments"
}出力スキーマ
{
"type": "object",
"properties": {
"result": {
"title": "Result",
"type": "string"
}
},
"required": [
"result"
],
"title": "parseOutput"
}🟢search(query, limit, fetchContent, maxCharsPerResult)
Search the web and return results. Optionally fetch the content of each result. Fetching content is much slower and more expensive — only set `fetchContent` when you actually need the page bodies rather than just the links and snippets.
入力スキーマ
{
"type": "object",
"properties": {
"query": {
"title": "Query",
"type": "string"
},
"limit": {
"default": 5,
"title": "Limit",
"type": "integer"
},
"fetchContent": {
"default": false,
"title": "Fetchcontent",
"type": "boolean"
},
"maxCharsPerResult": {
"default": 5000,
"title": "Maxcharsperresult",
"type": "integer"
}
},
"required": [
"query"
],
"title": "searchArguments"
}出力スキーマ
{
"type": "object",
"properties": {
"result": {
"title": "Result",
"type": "string"
}
},
"required": [
"result"
],
"title": "searchOutput"
}コミュニティ
エビデンス