Faceabot Deep search
One question searched in science, world news, Internet Archive, GitHub and discussions. Free.
我該用這個嗎
品質與安全性
發現項目（3）
- HIGHTool poisoning patterns detected
- MEDIUMTool 'deep_search' description contains placeholder text在 deep_search 中
- INFOTool description contains placeholder or incomplete text在 deep_search 中
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": {
"deep-search": {
"url": "https://faceabot.com/tools-mcp/deep-search"
}
}
}遠端端點
https://faceabot.com/tools-mcp/deep-searchstreamable-http它能做什麼
工具清單
工具（2）
🟢deep_search(query, sources, lang, limit_per_source)
Search one question at once in sources a normal web search misses: science (arXiv, Crossref), world news in 100+ languages of the last 3 months (GDELT), Internet Archive, GitHub, Wikipedia, and what people say (Bluesky, Mastodon, Lemmy, Hacker News, forums). Results grouped by source, dated, with links. Use when: you need rich, hard-to-find, sourced information on a subject. Example: {"query":"agentic commerce paid placement","sources":["science","news"],"lang":"en"}
輸入結構描述
{
"type": "object",
"properties": {
"query": {
"type": "string",
"description": "The subject, any language (sources search it as written)"
},
"sources": {
"type": "array",
"items": {
"type": "string",
"enum": [
"science",
"news",
"archives",
"code",
"wikipedia",
"people"
]
},
"description": "Optional subset; default: all"
},
"lang": {
"type": "string",
"description": "Optional 2-letter language for news, Wikipedia and discussions, e.g. fr, ja, ru"
},
"limit_per_source": {
"type": "integer",
"minimum": 1,
"maximum": 10,
"default": 5
}
},
"required": [
"query"
]
}🟢list_deep_sources
The sources searched by deep_search and what each one covers.
輸入結構描述
{
"type": "object",
"properties": {}
}社群
證據