Agentlist
Search AI agents and MCP servers by task or name, then read profiles with source links.
我該用這個嗎
品質與安全性
A
根據工具定義與協定合規性的自動化分析。
上下文成本
~267Token(工具定義)
~797 B典型回應大小
極小的注意力影響(128k 上下文的 0.21%)
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": {
"agentlist": {
"url": "https://mcp.agentlist.io"
}
}
}遠端端點
https://mcp.agentlist.iostreamable-httphttps://mcp.agentlist.io/?listing=registrystreamable-http它能做什麼
工具清單
工具(2)
🟢 唯讀🟡 寫入🔴 刪除⚪ 未知
🟢search_agents(query, limit)
Find agents and MCP tools by name or task keywords. Returns matching catalog text, stable slugs, and listing URLs. Use get_agent for sources.
輸入結構描述
{
"type": "object",
"properties": {
"query": {
"type": "string",
"minLength": 1,
"maxLength": 240
},
"limit": {
"default": 5,
"type": "integer",
"minimum": 1,
"maximum": 20
}
},
"required": [
"query"
],
"$schema": "http://json-schema.org/draft-07/schema#"
}🟢get_agent(slug, resultRef)
Read one catalog profile by its exact search result slug. Includes dated facts, source links and known limitations.
輸入結構描述
{
"type": "object",
"properties": {
"slug": {
"type": "string",
"minLength": 1,
"maxLength": 160
},
"resultRef": {
"description": "Optional. Pass the selected result’s resultRef to link this read to its search in catalog analytics.",
"type": "string"
}
},
"required": [
"slug"
],
"$schema": "http://json-schema.org/draft-07/schema#"
}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