directory
Discover and query every business on ANOTS — search, ask, or find-and-ask over MCP.
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": {
"directory": {
"url": "https://api.anots.com/mcp"
}
}
}遠端端點
https://api.anots.com/mcpstreamable-http它能做什麼
工具清單
工具（3）
🟢search_businesses(query, limit)
Search the ANOTS directory for businesses whose AI agent can answer a question or need. Returns matching businesses with their slug, name, what they do, and agent-card URL. Use this first to discover which agents to ask.
輸入結構描述
{
"type": "object",
"properties": {
"query": {
"type": "string",
"description": "What you are looking for (e.g. \"honest product reviews\", \"coffee subscription that ships internationally\")"
},
"limit": {
"type": "number",
"description": "Max businesses to return (default 5, max 10)"
}
},
"required": [
"query"
]
}🟢ask_business(slug, question)
Ask a specific business's ANOTS agent a question, by slug. The agent answers from that business's own knowledge base and tools (live data, not scraped HTML). Get the slug from search_businesses.
輸入結構描述
{
"type": "object",
"properties": {
"slug": {
"type": "string",
"description": "The business slug (e.g. \"gyibb\")"
},
"question": {
"type": "string",
"description": "The question to ask that business agent"
}
},
"required": [
"slug",
"question"
]
}🟢find_and_ask(query, limit)
Discover the most relevant ANOTS businesses for a need AND ask each one in a single step, returning their answers side by side. The fastest way to answer a purchase-intent or research question across the directory.
輸入結構描述
{
"type": "object",
"properties": {
"query": {
"type": "string",
"description": "The need or question to route across the directory"
},
"limit": {
"type": "number",
"description": "How many businesses to ask (default 3, max 5)"
}
},
"required": [
"query"
]
}社群
證據